diff options
Diffstat (limited to 'tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json')
| -rw-r--r-- | tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json | 2025 |
1 files changed, 1825 insertions, 200 deletions
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json index e1b9799e3036..ccf451534d16 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json @@ -1,11 +1,316 @@ [ { + "BriefDescription": "Address Match (Conflict) Count; Conflict Merges", + "EventCode": "0x17", + "EventName": "UNC_I_ADDRESS_MATCH.MERGE_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.; When two requests to the same address from the same source are received back to back, it is possible to merge the two of them together.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Address Match (Conflict) Count; Conflict Stalls", + "EventCode": "0x17", + "EventName": "UNC_I_ADDRESS_MATCH.STALL_COUNT", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when an inbound write (from a device to memory or another device) had an address match with another request in the write cache.; When it is not possible to merge two conflicting requests, a stall event occurs. This is bad for performance.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ack Pending Occupancy; Any Source", + "EventCode": "0x14", + "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ack Pending Occupancy; Select Source", + "EventCode": "0x14", + "EventName": "UNC_I_CACHE_ACK_PENDING_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes that have acquired ownership but have not yet returned their data to the uncore. These writes are generally queued up in the switch trying to get to the head of their queues so that they can post their data. The queue occuapancy increments when the ACK is received, and decrements when either the data is returned OR a tickle is received and ownership is released. Note that a single tickle can result in multiple decrements.; Tracks all requests from any source port.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Ownership Occupancy; Any Source", + "EventCode": "0x13", + "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Ownership Occupancy; Select Source", + "EventCode": "0x13", + "EventName": "UNC_I_CACHE_OWN_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore trying to acquire ownership in each cycle. This can be used with the write transaction count to calculate the average write latency in the uncore. The occupancy increments when a write request is issued, and decrements when the data is returned.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Read Occupancy; Any Source", + "EventCode": "0x10", + "EventName": "UNC_I_CACHE_READ_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Read Occupancy; Select Source", + "EventCode": "0x10", + "EventName": "UNC_I_CACHE_READ_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads that are outstanding in the uncore in each cycle. This can be used with the read transaction count to calculate the average read latency in the uncore. The occupancy increments when a read request is issued, and decrements when the data is returned.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Any Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Total Write Cache Occupancy; Select Source", + "EventCode": "0x12", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of reads and writes that are outstanding in the uncore in each cycle. This is effectively the sum of the READ_OCCUPANCY and WRITE_OCCUPANCY events.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Occupancy; Any Source", + "EventCode": "0x11", + "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.ANY", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.; Tracks all requests from any source port.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Outstanding Write Occupancy; Select Source", + "EventCode": "0x11", + "EventName": "UNC_I_CACHE_WRITE_OCCUPANCY.SOURCE", + "PerPkg": "1", + "PublicDescription": "Accumulates the number of writes (and write prefetches) that are outstanding in the uncore in each cycle. This can be used with the transaction count event to calculate the average latency in the uncore. The occupancy increments when the ownership fetch/prefetch is issued, and decrements the data is returned to the uncore.; Tracks only those requests that come from the port specified in the IRP_PmonFilter.OrderingQ register. This register allows one to select one specific queue. It is not possible to monitor multiple queues at a time.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Clocks in the IRP", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of clocks in the IRP.", + "Unit": "IRP" + }, + { + "EventCode": "0xb", + "EventName": "UNC_I_RxR_AK_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the AK Ingress is full. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Ingress Occupancy", + "EventCode": "0xa", + "EventName": "UNC_I_RxR_AK_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the AK Ingress. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "EventCode": "0xc", + "EventName": "UNC_I_RxR_AK_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the AK Ingress in each cycles. This queue is where the IRP receives responses from R2PCIe (the ring).", + "Unit": "IRP" + }, + { + "EventCode": "0x4", + "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - DRS", + "EventCode": "0x1", + "EventName": "UNC_I_RxR_BL_DRS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x7", + "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x5", + "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCB", + "EventCode": "0x2", + "EventName": "UNC_I_RxR_BL_NCB_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x8", + "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x6", + "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "BL Ingress Occupancy - NCS", + "EventCode": "0x3", + "EventName": "UNC_I_RxR_BL_NCS_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "EventCode": "0x9", + "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "Unit": "IRP" + }, + { + "BriefDescription": "Tickle Count; Ownership Lost", + "EventCode": "0x16", + "EventName": "UNC_I_TICKLES.LOST_OWNERSHIP", + "PerPkg": "1", + "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.; Tracks the number of requests that lost ownership as a result of a tickle. When a tickle comes in, if the request is not at the head of the queue in the switch, then that request as well as any requests behind it in the switch queue will lose ownership and have to re-acquire it later when they get to the head of the queue. This will therefore track the number of requests that lost ownership and not just the number of tickles.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Tickle Count; Data Returned", + "EventCode": "0x16", + "EventName": "UNC_I_TICKLES.TOP_OF_QUEUE", + "PerPkg": "1", + "PublicDescription": "Counts the number of tickles that are received. This is for both explicit (from Cbo) and implicit (internal conflict) tickles.; Tracks the number of cases when a tickle was received but the requests was at the head of the queue in the switch. In this case, data is returned rather than releasing ownership.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count: Read Prefetches", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.PD_PREFETCHES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Read Prefetches", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.RD_PREFETCHES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks the number of read prefetches.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Reads", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.READS", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only read requests (not including read prefetches).", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound Transaction Count; Writes", + "EventCode": "0x15", + "EventName": "UNC_I_TRANSACTIONS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore. This can be filtered based on request type in addition to the source queue. Note the special filtering equation. We do OR-reduction on the request type. If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests. Each write request should have a prefetch, so there is no need to explicitly track these requests. For writes that are tickled and have to retry, the counter will be incremented for each retry.", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD Egress Credit Stalls", + "EventCode": "0x18", + "EventName": "UNC_I_TxR_AD_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue a request to the R2PCIe because there are no AD Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x19", + "EventName": "UNC_I_TxR_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xe", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0xf", + "EventName": "UNC_I_TxR_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0xd", + "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "Write Ordering Stalls", + "EventCode": "0x1a", + "EventName": "UNC_I_WRITE_ORDERING_STALL_CYCLES", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when there are pending write ACK's in the switch but the switch->IRP pipeline is not utilized.", + "Unit": "IRP" + }, + { "BriefDescription": "Number of qfclks", "EventCode": "0x14", "EventName": "UNC_Q_CLOCKTICKS", "PerPkg": "1", "PublicDescription": "Counts the number of clocks in the QPI LL. This clock runs at 1/8th the GT/s speed of the QPI link. For example, a 8GT/s link will have qfclk or 1GHz. JKT does not support dynamic link speeds, so this frequency is fixed.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Count of CTO Events", @@ -13,7 +318,7 @@ "EventName": "UNC_Q_CTO_COUNT", "PerPkg": "1", "PublicDescription": "Counts the number of CTO (cluster trigger outs) events that were asserted across the two slots. If both slots trigger in a given cycle, the event will increment by 2. You can use edge detect to count the number of cases when both events triggered.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress Credits", @@ -22,7 +327,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits. Had there been enough credits, the spawn would have worked as the RBT bit was set and the RBT tag matched.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss", @@ -31,7 +336,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and there weren't enough Egress credits. The valid bit was set.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Invalid", @@ -40,7 +345,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because there were not enough Egress credits AND the RBT bit was not set, but the RBT tag matched.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - Egress and RBT Miss, Invalid", @@ -49,7 +354,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match, the valid bit was not set and there weren't enough Egress credits.", "UMask": "0x80", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss", @@ -58,7 +363,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match although the valid bit was set and there were enough Egress credits.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Invalid", @@ -67,7 +372,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the route-back table (RBT) specified that the transaction should not trigger a direct2core transaction. This is common for IO transactions. There were enough Egress credits and the RBT tag matched but the valid bit was not set.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Failure - RBT Miss and Invalid", @@ -76,7 +381,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn failed because the RBT tag did not match and the valid bit was not set although there were enough Egress credits.", "UMask": "0x40", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Direct 2 Core Spawning; Spawn Success", @@ -85,7 +390,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of DRS packets that we attempted to do direct2core on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.; The spawn was successful. There were sufficient credits, the RBT valid bit was set and there was an RBT tag match. The message was marked to spawn direct2core.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L1", @@ -93,205 +398,205 @@ "EventName": "UNC_Q_L1_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a QPI link. Use edge detect to count the number of instances when the QPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MATCH_MASK", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.AnyDataC", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.AnyResp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.AnyResp11flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.AnyResp9flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_E", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_E_Cmp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_E_FrcAckCnflt", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_F", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_F_Cmp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_F_FrcAckCnflt", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.DataC_M", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.WbEData", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.WbIData", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.DRS.WbSData", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.AnyReq", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.AnyResp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwd", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwdI", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwdIWb", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwdS", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespFwdSWb", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespIWb", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.HOM.RespSWb", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCB.AnyInt", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCB.AnyMsg", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCB.AnyMsg11flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCB.AnyMsg9flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCS.AnyMsg1or2flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCS.AnyMsg3flits", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NCS.NcRd", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.NDR.AnyCmp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "EventCode": "0x38", "EventName": "UNC_Q_MESSAGE.SNP.AnySnp", "PerPkg": "1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0p", @@ -299,7 +604,7 @@ "EventName": "UNC_Q_RxL0P_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0", @@ -307,7 +612,7 @@ "EventName": "UNC_Q_RxL0_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Bypassed", @@ -315,7 +620,7 @@ "EventName": "UNC_Q_RxL_BYPASSED", "PerPkg": "1", "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "CRC Errors Detected; LinkInit", @@ -324,7 +629,7 @@ "PerPkg": "1", "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during link initialization.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "CRC Errors Detected; Normal Operations", @@ -333,7 +638,7 @@ "PerPkg": "1", "PublicDescription": "Number of CRC errors detected in the QPI Agent. Each QPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the QPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).; CRC errors detected during normal operation.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; DRS", @@ -342,7 +647,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the DRS message class.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; HOM", @@ -351,7 +656,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the HOM message class.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; NCB", @@ -360,7 +665,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCB message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; NCS", @@ -369,7 +674,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NCS message class.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; NDR", @@ -378,7 +683,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the NDR message class.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN0 Credit Consumed; SNP", @@ -387,7 +692,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN0 credit for the SNP message class.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; DRS", @@ -396,7 +701,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the DRS message class.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; HOM", @@ -405,7 +710,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the HOM message class.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; NCB", @@ -414,7 +719,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCB message class.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; NCS", @@ -423,7 +728,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NCS message class.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; NDR", @@ -432,7 +737,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the NDR message class.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VN1 Credit Consumed; SNP", @@ -441,7 +746,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.; VN1 credit for the SNP message class.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VNA Credit Consumed", @@ -449,7 +754,7 @@ "EventName": "UNC_Q_RxL_CREDITS_CONSUMED_VNA", "PerPkg": "1", "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty", @@ -457,7 +762,7 @@ "EventName": "UNC_Q_RxL_CYCLES_NE", "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN0", @@ -466,7 +771,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - DRS; for VN1", @@ -475,7 +780,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors DRS flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN0", @@ -484,7 +789,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - HOM; for VN1", @@ -493,7 +798,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors HOM flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN0", @@ -502,7 +807,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NCB; for VN1", @@ -511,7 +816,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCB flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN0", @@ -520,7 +825,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NCS; for VN1", @@ -529,7 +834,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NCS flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN0", @@ -538,7 +843,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - NDR; for VN1", @@ -547,7 +852,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors NDR flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN0", @@ -556,7 +861,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Cycles Not Empty - SNP; for VN1", @@ -565,7 +870,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of cycles that the QPI RxQ was not empty. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy Accumulator event to calculate the average occupancy. This monitors SNP flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Data Tx Flits", @@ -574,7 +879,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits received over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Idle and Null Flits", @@ -583,7 +888,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of flits received over QPI that do not hold protocol payload. When QPI is not in a power saving state, it continuously transmits flits across the link. When there are no protocol flits to send, it will send IDLE and NULL flits across. These flits sometimes do carry a payload, such as credit returns, but are generally not considered part of the QPI bandwidth.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 0; Non-Data protocol Tx Flits", @@ -592,7 +897,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits received across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; DRS Flits (both Header and Data)", @@ -601,7 +906,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data.", "UMask": "0x18", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; DRS Data Flits", @@ -610,7 +915,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; DRS Header Flits", @@ -619,7 +924,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits received over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits received over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; HOM Flits", @@ -628,7 +933,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits received over QPI on the home channel.", "UMask": "0x6", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; HOM Non-Request Flits", @@ -637,7 +942,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits received over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; HOM Request Flits", @@ -646,7 +951,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request received over QPI on the home channel. This basically counts the number of remote memory requests received over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 1; SNP Flits", @@ -655,7 +960,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits received over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are received on the home channel.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent Rx Flits", @@ -664,7 +969,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", "UMask": "0xc", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent data Rx Flits", @@ -673,7 +978,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent non-data Rx Flits", @@ -682,7 +987,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Coherent standard Rx Flits", @@ -691,7 +996,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits received over QPI. This includes extended headers.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AD", @@ -700,7 +1005,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Received - Group 2; Non-Data Response Rx Flits - AK", @@ -709,7 +1014,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits received from the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits received over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations", @@ -717,7 +1022,7 @@ "EventName": "UNC_Q_RxL_INSERTS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - DRS", @@ -725,7 +1030,7 @@ "EventName": "UNC_Q_RxL_INSERTS_DRS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN0", @@ -734,7 +1039,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - DRS; for VN1", @@ -743,7 +1048,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only DRS flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - HOM", @@ -751,7 +1056,7 @@ "EventName": "UNC_Q_RxL_INSERTS_HOM", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN0", @@ -760,7 +1065,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - HOM; for VN1", @@ -769,7 +1074,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only HOM flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCB", @@ -777,7 +1082,7 @@ "EventName": "UNC_Q_RxL_INSERTS_NCB", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN0", @@ -786,7 +1091,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCB; for VN1", @@ -795,7 +1100,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCB flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCS", @@ -803,7 +1108,7 @@ "EventName": "UNC_Q_RxL_INSERTS_NCS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN0", @@ -812,7 +1117,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NCS; for VN1", @@ -821,7 +1126,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NCS flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NDR", @@ -829,7 +1134,7 @@ "EventName": "UNC_Q_RxL_INSERTS_NDR", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN0", @@ -838,7 +1143,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - NDR; for VN1", @@ -847,7 +1152,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only NDR flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - SNP", @@ -855,7 +1160,7 @@ "EventName": "UNC_Q_RxL_INSERTS_SNP", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN0", @@ -864,7 +1169,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Rx Flit Buffer Allocations - SNP; for VN1", @@ -873,7 +1178,7 @@ "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Rx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime. This monitors only SNP flits.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - All Packets", @@ -881,7 +1186,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - DRS", @@ -889,7 +1194,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_DRS", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - DRS; for VN0", @@ -898,7 +1203,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - DRS; for VN1", @@ -907,7 +1212,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors DRS flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - HOM", @@ -915,7 +1220,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_HOM", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - HOM; for VN0", @@ -924,7 +1229,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - HOM; for VN1", @@ -933,7 +1238,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors HOM flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCB", @@ -941,7 +1246,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_NCB", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCB; for VN0", @@ -950,7 +1255,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCB; for VN1", @@ -959,7 +1264,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCB flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCS", @@ -967,7 +1272,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_NCS", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCS; for VN0", @@ -976,7 +1281,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NCS; for VN1", @@ -985,7 +1290,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NCS flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NDR", @@ -993,7 +1298,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_NDR", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NDR; for VN0", @@ -1002,7 +1307,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - NDR; for VN1", @@ -1011,7 +1316,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors NDR flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - SNP", @@ -1019,7 +1324,7 @@ "EventName": "UNC_Q_RxL_OCCUPANCY_SNP", "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - SNP; for VN0", @@ -1028,7 +1333,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "RxQ Occupancy - SNP; for VN1", @@ -1037,7 +1342,7 @@ "PerPkg": "1", "PublicDescription": "Accumulates the number of elements in the QPI RxQ in each cycle. Generally, when data is transmitted across QPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime. This monitors SNP flits only.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - HOM", @@ -1046,7 +1351,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - DRS", @@ -1055,7 +1360,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - SNP", @@ -1064,7 +1369,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NDR", @@ -1073,7 +1378,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCS", @@ -1082,7 +1387,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; BGF Stall - NCB", @@ -1091,7 +1396,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; Egress Credits", @@ -1100,7 +1405,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled a packet because there were insufficient BGF credits. For details on a message class granularity, use the Egress Credit Occupancy events.", "UMask": "0x40", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN0; GV", @@ -1109,7 +1414,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 0; Stalled because a GV transition (frequency transition) was taking place.", "UMask": "0x80", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - HOM", @@ -1118,7 +1423,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the HOM message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - DRS", @@ -1127,7 +1432,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the DRS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - SNP", @@ -1136,7 +1441,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the SNP message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NDR", @@ -1145,7 +1450,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NDR message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCS", @@ -1154,7 +1459,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCS message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x20", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Stalls Sending to R3QPI on VN1; BGF Stall - NCB", @@ -1163,7 +1468,7 @@ "PerPkg": "1", "PublicDescription": "Number of stalls trying to send to R3QPI on Virtual Network 1.; Stalled a packet from the NCB message class because there were not enough BGF credits. In bypass mode, we will stall on the packet boundary, while in RxQ mode we will stall on the flit boundary.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0p", @@ -1171,7 +1476,7 @@ "EventName": "UNC_Q_TxL0P_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the QPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize QPI for snoops and their responses. Use edge detect to count the number of instances when the QPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles in L0", @@ -1179,7 +1484,7 @@ "EventName": "UNC_Q_TxL0_POWER_CYCLES", "PerPkg": "1", "PublicDescription": "Number of QPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Bypassed", @@ -1187,7 +1492,7 @@ "EventName": "UNC_Q_TxL_BYPASSED", "PerPkg": "1", "PublicDescription": "Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the QPI Link. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is almost full", @@ -1196,7 +1501,7 @@ "PerPkg": "1", "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is almost full, we block some but not all packets.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Cycles Stalled with no LLR Credits; LLR is full", @@ -1205,7 +1510,7 @@ "PerPkg": "1", "PublicDescription": "Number of cycles when the Tx side ran out of Link Layer Retry credits, causing the Tx to stall.; When LLR is totally full, we are not allowed to send any packets.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Cycles not Empty", @@ -1213,7 +1518,7 @@ "EventName": "UNC_Q_TxL_CYCLES_NE", "PerPkg": "1", "PublicDescription": "Counts the number of cycles when the TxQ is not empty. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 0; Data Tx Flits", @@ -1221,7 +1526,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of data flits transmitted over QPI. Each flit contains 64b of data. This includes both DRS and NCB data flits (coherent and non-coherent). This can be used to calculate the data bandwidth of the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This does not include the header flits that go in data packets.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 0; Non-Data protocol Tx Flits", @@ -1229,7 +1534,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. It includes filters for Idle, protocol, and Data Flits. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time (for L0) or 4B instead of 8B for L0p.; Number of non-NULL non-data flits transmitted across QPI. This basically tracks the protocol overhead on the QPI link. One can get a good picture of the QPI-link characteristics by evaluating the protocol flits, data flits, and idle/null flits. This includes the header flits for data packets.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; DRS Flits (both Header and Data)", @@ -1237,7 +1542,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency.", "UMask": "0x18", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; DRS Data Flits", @@ -1245,7 +1550,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of data flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the data flits (not the header).", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; DRS Header Flits", @@ -1253,7 +1558,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of protocol flits transmitted over QPI on the DRS (Data Response) channel. DRS flits are used to transmit data with coherency. This does not count data flits transmitted over the NCB channel which transmits non-coherent data. This includes only the header flits (not the data). This includes extended headers.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; HOM Flits", @@ -1261,7 +1566,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of flits transmitted over QPI on the home channel.", "UMask": "0x6", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; HOM Non-Request Flits", @@ -1269,7 +1574,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of non-request flits transmitted over QPI on the home channel. These are most commonly snoop responses, and this event can be used as a proxy for that.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; HOM Request Flits", @@ -1277,7 +1582,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of data request transmitted over QPI on the home channel. This basically counts the number of remote memory requests transmitted over QPI. In conjunction with the local read count in the Home Agent, one can calculate the number of LLC Misses.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 1; SNP Flits", @@ -1285,7 +1590,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for SNP, HOM, and DRS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the number of snoop request flits transmitted over QPI. These requests are contained in the snoop channel. This does not include snoop responses, which are transmitted on the home channel.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent Bypass Tx Flits", @@ -1294,7 +1599,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass flits. These packets are generally used to transmit non-coherent data across QPI.", "UMask": "0xc", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent data Tx Flits", @@ -1303,7 +1608,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass data flits. These flits are generally used to transmit non-coherent data across QPI. This does not include a count of the DRS (coherent) data flits. This only counts the data flits, not the NCB headers.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent non-data Tx Flits", @@ -1312,7 +1617,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of Non-Coherent Bypass non-data flits. These packets are generally used to transmit non-coherent data across QPI, and the flits counted here are for headers and other non-data flits. This includes extended headers.", "UMask": "0x8", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Coherent standard Tx Flits", @@ -1321,7 +1626,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Number of NCS (non-coherent standard) flits transmitted over QPI. This includes extended headers.", "UMask": "0x10", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AD", @@ -1330,7 +1635,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets to the local socket which use the AK ring.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Flits Transferred - Group 2; Non-Data Response Tx Flits - AK", @@ -1339,7 +1644,7 @@ "PerPkg": "1", "PublicDescription": "Counts the number of flits transmitted across the QPI Link. This is one of three groups that allow us to track flits. It includes filters for NDR, NCB, and NCS message classes. Each flit is made up of 80 bits of information (in addition to some ECC data). In full-width (L0) mode, flits are made up of four fits, each of which contains 20 bits of data (along with some additional ECC data). In half-width (L0p) mode, the fits are only 10 bits, and therefore it takes twice as many fits to transmit a flit. When one talks about QPI speed (for example, 8.0 GT/s), the transfers here refer to fits. Therefore, in L0, the system will transfer 1 flit at the rate of 1/4th the QPI speed. One can calculate the bandwidth of the link by taking: flits*80b/time. Note that this is not the same as data bandwidth. For example, when we are transferring a 64B cacheline across QPI, we will break it into 9 flits -- 1 with header information and 8 with 64 bits of actual data and an additional 16 bits of other information. To calculate data bandwidth, one should therefore do: data flits * 8B / time.; Counts the total number of flits transmitted over the NDR (Non-Data Response) channel. This channel is used to send a variety of protocol flits including grants and completions. This is only for NDR packets destined for Route-thru to a remote socket.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Allocations", @@ -1347,7 +1652,7 @@ "EventName": "UNC_Q_TxL_INSERTS", "PerPkg": "1", "PublicDescription": "Number of allocations into the QPI Tx Flit Buffer. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "Tx Flit Buffer Occupancy", @@ -1355,7 +1660,7 @@ "EventName": "UNC_Q_TxL_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Accumulates the number of flits in the TxQ. Generally, when data is transmitted across QPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN0", @@ -1364,7 +1669,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - HOM; for VN1", @@ -1373,7 +1678,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Home messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN0", @@ -1382,7 +1687,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD HOM; for VN1", @@ -1391,7 +1696,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for HOM messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", @@ -1400,7 +1705,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", @@ -1409,7 +1714,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for NDR messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN0", @@ -1418,7 +1723,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD NDR; for VN1", @@ -1427,7 +1732,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for NDR messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN0", @@ -1436,7 +1741,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - SNP; for VN1", @@ -1445,7 +1750,7 @@ "PerPkg": "1", "PublicDescription": "Number of link layer credits into the R3 (for transactions across the BGF) acquired each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN0", @@ -1454,7 +1759,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AD SNP; for VN1", @@ -1463,7 +1768,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of link layer credits into the R3 (for transactions across the BGF) available in each cycle. Flow Control FIFO for Snoop messages on AD.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", @@ -1471,7 +1776,7 @@ "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_ACQUIRED", "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN0", @@ -1480,7 +1785,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN1", @@ -1489,7 +1794,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. Local NDR message class to AK Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR", @@ -1497,7 +1802,7 @@ "EventName": "UNC_Q_TxR_AK_NDR_CREDIT_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN0", @@ -1506,7 +1811,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - AK NDR: for VN1", @@ -1515,7 +1820,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. Local NDR message class to AK Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN0", @@ -1524,7 +1829,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for VN1", @@ -1533,7 +1838,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - DRS; for Shared VN", @@ -1542,7 +1847,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. DRS message class to BL Egress.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN0", @@ -1551,7 +1856,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for VN1", @@ -1560,7 +1865,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL DRS; for Shared VN", @@ -1569,7 +1874,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. DRS message class to BL Egress.", "UMask": "0x4", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN0", @@ -1578,7 +1883,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - NCB; for VN1", @@ -1587,7 +1892,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCB message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN0", @@ -1596,7 +1901,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCB; for VN1", @@ -1605,7 +1910,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCB message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN0", @@ -1614,7 +1919,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - NCS; for VN1", @@ -1623,7 +1928,7 @@ "PerPkg": "1", "PublicDescription": "Number of credits into the R3 (for transactions across the BGF) acquired each cycle. NCS message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN0", @@ -1632,7 +1937,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", "UMask": "0x1", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "R3QPI Egress Credit Occupancy - BL NCS; for VN1", @@ -1641,7 +1946,7 @@ "PerPkg": "1", "PublicDescription": "Occupancy event that tracks the number of credits into the R3 (for transactions across the BGF) available in each cycle. NCS message class to BL Egress.", "UMask": "0x2", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VNA Credits Returned", @@ -1649,7 +1954,7 @@ "EventName": "UNC_Q_VNA_CREDIT_RETURNS", "PerPkg": "1", "PublicDescription": "Number of VNA credits returned.", - "Unit": "QPI LL" + "Unit": "QPI" }, { "BriefDescription": "VNA Credits Pending Return - Occupancy", @@ -1657,6 +1962,1326 @@ "EventName": "UNC_Q_VNA_CREDIT_RETURN_OCCUPANCY", "PerPkg": "1", "PublicDescription": "Number of VNA credits in the Rx side that are waitng to be returned back across the link.", - "Unit": "QPI LL" + "Unit": "QPI" + }, + { + "BriefDescription": "Number of uclks in domain", + "EventCode": "0x1", + "EventName": "UNC_R3_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Counts the number of uclks in the QPI uclk domain. This could be slightly different than the count in the Ubox because of enable/freeze delays. However, because the QPI Agent is close to the Ubox, they generally should not diverge by more than a handful of cycles.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO10", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 10", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO11", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 11", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO12", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 12", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO13", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 13", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO14", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 14&16", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO8", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 8", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2c", + "EventName": "UNC_R3_C_HI_AD_CREDITS_EMPTY.CBO9", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers higher CBoxes); Cbox 9", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO2", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 2", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO3", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 3", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO4", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 4", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO5", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 5", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO6", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 6", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "CBox AD Credits Empty", + "EventCode": "0x2b", + "EventName": "UNC_R3_C_LO_AD_CREDITS_EMPTY.CBO7", + "PerPkg": "1", + "PublicDescription": "No credits available to send to Cbox on the AD Ring (covers lower CBoxes); Cbox 7", + "UMask": "0x80", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA0", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA0", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.HA1", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; HA1", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCB", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCB Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "HA/R2 AD Credits Empty", + "EventCode": "0x2f", + "EventName": "UNC_R3_HA_R2_BL_CREDITS_EMPTY.R2_NCS", + "PerPkg": "1", + "PublicDescription": "No credits available to send to either HA or R2 on the BL Ring; R2 NCS Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 AD Credits Empty", + "EventCode": "0x29", + "EventName": "UNC_R3_QPI0_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI0 BL Credits Empty", + "EventCode": "0x2d", + "EventName": "UNC_R3_QPI0_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI0 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 AD Credits Empty", + "EventCode": "0x2a", + "EventName": "UNC_R3_QPI1_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the AD Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 HOM Messages", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 NDR Messages", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN0 SNP Messages", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_HOM", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 HOM Messages", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_NDR", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 NDR Messages", + "UMask": "0x40", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VN1 SNP Messages", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "QPI1 BL Credits Empty", + "EventCode": "0x2e", + "EventName": "UNC_R3_QPI1_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "No credits available to send to QPI1 on the BL Ring; VNA", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xcc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Even on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Counterclockwise and Odd on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Even on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AD Ring in Use; Clockwise and Odd on VRing 0", + "EventCode": "0x7", + "EventName": "UNC_R3_RING_AD_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AD ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xcc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Even on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Counterclockwise and Odd on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Even on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 AK Ring in Use; Clockwise and Odd on VRing 0", + "EventCode": "0x8", + "EventName": "UNC_R3_RING_AK_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the AK ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0xcc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Even on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Counterclockwise and Odd on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CCW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Counterclockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Even on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_VR0_EVEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Even ring polarity on Virtual Ring 0.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R3 BL Ring in Use; Clockwise and Odd on VRing 0", + "EventCode": "0x9", + "EventName": "UNC_R3_RING_BL_USED.CW_VR0_ODD", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the BL ring is being used at this ring stop. This includes when packets are passing by and when packets are being sunk, but does not include when packets are being sent from the ring stop.; Filters for the Clockwise and Odd ring polarity on Virtual Ring 0.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R2 IV Ring in Use; Any", + "EventCode": "0xA", + "EventName": "UNC_R3_RING_IV_USED.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters any polarity", + "UMask": "0xff", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R2 IV Ring in Use; Counterclockwise", + "EventCode": "0xa", + "EventName": "UNC_R3_RING_IV_USED.CCW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Counterclockwise polarity", + "UMask": "0xcc", + "Unit": "R3QPI" + }, + { + "BriefDescription": "R2 IV Ring in Use; Clockwise", + "EventCode": "0xa", + "EventName": "UNC_R3_RING_IV_USED.CW", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles that the IV ring is being used at this ring stop. This includes when packets are passing by and when packets are being sent, but does not include when packets are being sunk into the ring stop. The IV ring is unidirectional. Whether UP or DN is used is dependent on the system programming. Thereofore, one should generally set both the UP and DN bits for a given polarity (or both) at a given time.; Filters for Clockwise polarity", + "UMask": "0x33", + "Unit": "R3QPI" + }, + { + "BriefDescription": "AD Ingress Bypassed", + "EventCode": "0x12", + "EventName": "UNC_R3_RxR_AD_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the AD Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Bypassed", + "EventCode": "0x12", + "EventName": "UNC_R3_RxR_BYPASSED.AD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times when the Ingress was bypassed and an incoming transaction was bypassed directly across the BGF and into the qfclk domain.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; HOM", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; NDR", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Cycles Not Empty; SNP", + "EventCode": "0x10", + "EventName": "UNC_R3_RxR_CYCLES_NE.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of cycles when the QPI Ingress is not empty. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; DRS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.DRS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; HOM", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.HOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCB", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCB", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NCS", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NCS", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; NDR", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.NDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Allocations; SNP", + "EventCode": "0x11", + "EventName": "UNC_R3_RxR_INSERTS.SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of allocations into the QPI Ingress. This tracks one of the three rings that are used by the QPI agent. This can be used in conjunction with the QPI Ingress Occupancy Accumulator event in order to calculate average queue latency. Multiple ingress buffers can be tracked at a given time using multiple counters.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; DRS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.DRS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; DRS Ingress Queue", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; HOM", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.HOM", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; HOM Ingress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NCB", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NCB", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NCB Ingress Queue", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NCS", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NCS", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NCS Ingress Queue", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; NDR", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.NDR", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; NDR Ingress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Ingress Occupancy Accumulator; SNP", + "EventCode": "0x13", + "EventName": "UNC_R3_RxR_OCCUPANCY.SNP", + "PerPkg": "1", + "PublicDescription": "Accumulates the occupancy of a given QPI Ingress queue in each cycles. This tracks one of the three ring Ingress buffers. This can be used with the QPI Ingress Not Empty event to calculate average occupancy or the QPI Ingress Allocations event in order to calculate average queuing latency.; SNP Ingress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AK CCW", + "EventCode": "0x28", + "EventName": "UNC_R3_TxR_NACK_CCW.AD", + "PerPkg": "1", + "PublicDescription": "BL CounterClockwise Egress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; BL CW", + "EventCode": "0x28", + "EventName": "UNC_R3_TxR_NACK_CCW.AK", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; BL CCW", + "EventCode": "0x28", + "EventName": "UNC_R3_TxR_NACK_CCW.BL", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AD CW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK_CW.AD", + "PerPkg": "1", + "PublicDescription": "AD Clockwise Egress Queue", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AD CCW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK_CW.AK", + "PerPkg": "1", + "PublicDescription": "AD CounterClockwise Egress Queue", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Egress NACK; AK CW", + "EventCode": "0x26", + "EventName": "UNC_R3_TxR_NACK_CW.BL", + "PerPkg": "1", + "PublicDescription": "BL Clockwise Egress Queue", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; DRS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; HOM Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCB Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NCS Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; NDR Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Acquisition Failed on DRS; SNP Message Class", + "EventCode": "0x37", + "EventName": "UNC_R3_VN0_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a DRS VN0 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN0 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; DRS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; HOM Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCB Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NCS Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; NDR Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN0 Credit Used; SNP Message Class", + "EventCode": "0x36", + "EventName": "UNC_R3_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; DRS Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; HOM Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCB Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NCS Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; NDR Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Acquisition Failed on DRS; SNP Message Class", + "EventCode": "0x39", + "EventName": "UNC_R3_VN1_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a request failed to acquire a VN1 credit. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This therefore counts the number of times when a request failed to acquire either a VNA or VN1 credit and is delayed. This should generally be a rare situation.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; DRS Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.DRS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; HOM Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.HOM", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCB Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NCS Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Non-Coherent Standard (NCS). NCS is commonly used for ?", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; NDR Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.NDR", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VN1 Credit Used; SNP Message Class", + "EventCode": "0x38", + "EventName": "UNC_R3_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "Number of times a VN1 credit was used on the DRS message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.AD", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA credit Acquisitions; HOM Message Class", + "EventCode": "0x33", + "EventName": "UNC_R3_VNA_CREDITS_ACQUIRED.BL", + "PerPkg": "1", + "PublicDescription": "Number of QPI VNA Credit acquisitions. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average lifetime of a credit holder. VNA credits are used by all message classes in order to communicate across QPI. If a packet is unable to acquire credits, it will then attempt to use credits from the VN0 pool. Note that a single packet may require multiple flit buffers (i.e. when data is being transferred). Therefore, this event will increment by the number of credits acquired in each cycle. Filtering based on message class is not provided. One can count the number of packets transferred in a given message class using an qfclk event.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; DRS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Data Response (DRS). DRS is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using DRS.", + "UMask": "0x8", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; HOM Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.HOM", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for the Home (HOM) message class. HOM is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCB Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Broadcast (NCB). NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x10", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NCS Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Non-Coherent Standard (NCS).", + "UMask": "0x20", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; NDR Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.NDR", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; NDR packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "R3QPI" + }, + { + "BriefDescription": "VNA Credit Reject; SNP Message Class", + "EventCode": "0x34", + "EventName": "UNC_R3_VNA_CREDITS_REJECT.SNP", + "PerPkg": "1", + "PublicDescription": "Number of attempted VNA credit acquisitions that were rejected because the VNA credit pool was full (or almost full). It is possible to filter this event by message class. Some packets use more than one flit buffer, and therefore must acquire multiple credits. Therefore, one could get a reject even if the VNA credits were not fully used up. The VNA pool is generally used to provide the bulk of the QPI bandwidth (as opposed to the VN0 pool which is used to guarantee forward progress). VNA credits can run out if the flit buffer on the receiving side starts to queue up substantially. This can happen if the rest of the uncore is unable to drain the requests fast enough.; Filter for Snoop (SNP) message class. SNP is used for outgoing snoops. Note that snoop responses flow on the HOM message class.", + "UMask": "0x2", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Cycles with no VNA credits available", + "EventCode": "0x31", + "EventName": "UNC_R3_VNA_CREDIT_CYCLES_OUT", + "PerPkg": "1", + "PublicDescription": "Number of QPI uclk cycles when the transmitted has no VNA credits available and therefore cannot send any requests on this channel. Note that this does not mean that no flits can be transmitted, as those holding VN0 credits will still (potentially) be able to transmit. Generally it is the goal of the uncore that VNA credits should not run out, as this can substantially throttle back useful QPI bandwidth.", + "Unit": "R3QPI" + }, + { + "BriefDescription": "Cycles with 1 or more VNA credits in use", + "EventCode": "0x32", + "EventName": "UNC_R3_VNA_CREDIT_CYCLES_USED", + "PerPkg": "1", + "PublicDescription": "Number of QPI uclk cycles with one or more VNA credits in use. This event can be used in conjunction with the VNA In-Use Accumulator to calculate the average number of used VNA credits.", + "Unit": "R3QPI" + }, + { + "EventName": "UNC_U_CLOCKTICKS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "VLW Received", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Virtual Logical Wire (legacy) message were received from Uncore. Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_DISABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Filter Match", + "EventCode": "0x41", + "EventName": "UNC_U_FILTER_MATCH.U2C_ENABLE", + "PerPkg": "1", + "PublicDescription": "Filter match per thread (w/ or w/o Filter Enable). Specify the thread to filter on using NCUPMONCTRLGLCTR.ThreadID.", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "IDI Lock/SplitLock Cycles", + "EventCode": "0x44", + "EventName": "UNC_U_LOCK_CYCLES", + "PerPkg": "1", + "PublicDescription": "Number of times an IDI Lock/SplitLock sequence was started", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack; Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "PHOLD cycles. Filter from source CoreID.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Correctable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.CMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Livelock", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LIVELOCK", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; LTError", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.LTERROR", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T0", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T0", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Monitor T1", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.MONITOR_T1", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; Filter by core", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Other", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.OTHER", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores; PREQ, PSMI, P2U, Thermal, PCUSMI, PMI", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Trap", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.TRAP", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "Monitor Sent to T0; Uncorrectable Machine Check", + "EventCode": "0x43", + "EventName": "UNC_U_U2C_EVENTS.UMC", + "PerPkg": "1", + "PublicDescription": "Events coming from Uncore can be sent to one or all cores", + "UMask": "0x20", + "Unit": "UBOX" } ] |