},
{
"PEBS": "1",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x41",
},
{
"PEBS": "1",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x42",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+ "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
"EventCode": "0x87",
"Counter": "0,1,2,3",
"UMask": "0x1",
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"SampleAfterValue": "100003",
"L1_Hit_Indication": "1",
"CounterHTOff": "0,1,2,3"
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"Counter": "0,1,2,3",
"EventName": "ILD_STALL.LCP",
- "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+ "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"SampleAfterValue": "100003",
"CounterHTOff": "0,1,2,3"
},
"PEBS": "1",
"Counter": "0,1,2,3",
"EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
- "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"SampleAfterValue": "100003",
"L1_Hit_Indication": "1",
"CounterHTOff": "0,1,2,3"
"BriefDescription": "Stalls caused by changing prefix length of the instruction.",
"Counter": "0,1,2,3",
"EventName": "ILD_STALL.LCP",
- "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+ "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
"SampleAfterValue": "2000003",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
},
{
"PEBS": "1",
- "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x41",
},
{
"PEBS": "1",
- "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x42",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
+ "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventName": "OFFCORE_RESPONSE.ANY_PF_L2.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts any Read request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Demand code reads and prefetch code read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Demand cacheable data write requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.UC_CODE_READS.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts UC code reads (valid only for Outstanding response type) that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type). that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
"EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING",
"MSRIndex": "0x1a6",
"SampleAfterValue": "100007",
- "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0. ",
+ "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
"Offcore": "1"
},
{
},
{
"PEBS": "1",
- "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x41",
},
{
"PEBS": "1",
- "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+ "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
"EventCode": "0xD0",
"Counter": "0,1,2,3",
"UMask": "0x42",
"CounterHTOff": "0,1,2,3,4,5,6,7"
},
{
- "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
+ "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store. See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
"EventCode": "0x03",
"Counter": "0,1,2,3",
"UMask": "0x2",
"EventCode": "0x5C",
"EventName": "UNC_CHA_SNOOP_RESP.RSP_WBWB",
"PerPkg": "1",
- "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to it's home. This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured. This reponse will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.",
+ "PublicDescription": "Counts when a transaction with the opcode type Rsp*WB Snoop Response was received which indicates which indicates the data was written back to it's home. This is returned when a non-RFO request hits a cacheline in the Modified state. The Cache can either downgrade the cacheline to a S (Shared) or I (Invalid) state depending on how the system has been configured. This response will also be sent when a cache requests E (Exclusive) ownership of a cache line without receiving data, because the cache must acquire ownership.",
"UMask": "0x10",
"Unit": "CHA"
},
"EventCode": "0x57",
"EventName": "UNC_M2M_PREFCAM_INSERTS",
"PerPkg": "1",
- "PublicDescription": "Counts when the M2M (Mesh to Memory) recieves a prefetch request and inserts it into its outstanding prefetch queue. Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory",
+ "PublicDescription": "Counts when the M2M (Mesh to Memory) receives a prefetch request and inserts it into its outstanding prefetch queue. Explanatory Side Note: the prefect queue is made from CAM: Content Addressable Memory",
"Unit": "M2M"
},
{
"EventCode": "0x31",
"EventName": "UNC_UPI_RxL_BYPASSED.SLOT0",
"PerPkg": "1",
- "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.",
+ "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot0 RxQ buffer (Receive Queue) and passed directly to 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.",
"UMask": "0x1",
"Unit": "UPI LL"
},
"EventCode": "0x31",
"EventName": "UNC_UPI_RxL_BYPASSED.SLOT1",
"PerPkg": "1",
- "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer (Receive Queue) and passed 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 transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.",
+ "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot1 RxQ buffer (Receive Queue) and passed 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.",
"UMask": "0x2",
"Unit": "UPI LL"
},
{
- "BriefDescription": "FLITs received which bypassed the Slot0 Recieve Buffer",
+ "BriefDescription": "FLITs received which bypassed the Slot0 Receive Buffer",
"Counter": "0,1,2,3",
"EventCode": "0x31",
"EventName": "UNC_UPI_RxL_BYPASSED.SLOT2",
"PerPkg": "1",
- "PublicDescription": "Counts incoming FLITs (FLow control unITs) whcih bypassed the slot2 RxQ buffer (Receive Queue) and passed directly to the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of FLITs transfered, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.",
+ "PublicDescription": "Counts incoming FLITs (FLow control unITs) which bypassed the slot2 RxQ buffer (Receive Queue) and passed directly to 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.",
"UMask": "0x4",
"Unit": "UPI LL"
},
projects / platform / kernel / linux-rpi.git / commitdiff