Add in Neoverse N2 and V2 event and metric definitions

cmd/metrics/resources/events/aarch64/neoverse-n2-v2/fp_operation.json

@@ -0,0 +1,22 @@
+[
+    {
+        "ArchStdEvent": "FP_HP_SPEC",
+        "PublicDescription": "Counts speculatively executed half precision floating point operations."
+    },
+    {
+        "ArchStdEvent": "FP_SP_SPEC",
+        "PublicDescription": "Counts speculatively executed single precision floating point operations."
+    },
+    {
+        "ArchStdEvent": "FP_DP_SPEC",
+        "PublicDescription": "Counts speculatively executed double precision floating point operations."
+    },
+    {
+        "ArchStdEvent": "FP_SCALE_OPS_SPEC",
+        "PublicDescription": "Counts speculatively executed scalable single precision floating point operations."
+    },
+    {
+        "ArchStdEvent": "FP_FIXED_OPS_SPEC",
+        "PublicDescription": "Counts speculatively executed non-scalable single precision floating point operations."
+    }
+]

cmd/metrics/resources/events/aarch64/neoverse-n2-v2/general.json

@@ -0,0 +1,10 @@
+[
+    {
+        "ArchStdEvent": "CPU_CYCLES",
+        "PublicDescription": "Counts CPU clock cycles (not timer cycles). The clock measured by this event is defined as the physical clock driving the CPU logic."
+    },
+    {
+        "ArchStdEvent": "CNT_CYCLES",
+        "PublicDescription": "Increments at a constant frequency equal to the rate of increment of the System Counter, CNTPCT_EL0."
+    }
+]

cmd/metrics/resources/events/aarch64/neoverse-n2-v2/l1d_cache.json

@@ -0,0 +1,54 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL",
+        "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE",
+        "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) counts as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB",
+        "PublicDescription": "Counts write-backs of dirty data from the L1 data cache to the L2 cache. This occurs when either a dirty cache line is evicted from L1 data cache and allocated in the L2 cache or dirty data is written to the L2 and possibly to the next level of cache. This event counts both victim cache line evictions and cache write-backs from snoops or cache maintenance operations. The following cache operations are not counted:\n\n1. Invalidations which do not result in data being transferred out of the L1 (such as evictions of clean data),\n2. Full line writes which write to L2 without writing L1, such as write streaming mode."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_LMISS_RD",
+        "PublicDescription": "Counts cache line refills into the level 1 data cache from any memory read operations, that incurred additional latency."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_RD",
+        "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches counts as both a write access and read access."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR",
+        "PublicDescription": "Counts level 1 data cache accesses generated by store operations. This event also counts accesses caused by a DC ZVA (data cache zero, specified by virtual address) instruction. Near atomic operations that resolve in the CPUs caches count as a write access and read access."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
+        "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load instructions where the memory read operation misses in the level 1 data cache. This event only counts one event per cache line."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_WR",
+        "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed store instructions where the memory write operation misses in the level 1 data cache. This event only counts one event per cache line."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+        "PublicDescription": "Counts level 1 data cache refills where the cache line data came from caches inside the immediate cluster of the core."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+        "PublicDescription": "Counts level 1 data cache refills for which the cache line data came from outside the immediate cluster of the core, like an SLC in the system interconnect or DRAM."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+        "PublicDescription": "Counts dirty cache line evictions from the level 1 data cache caused by a new cache line allocation. This event does not count evictions caused by cache maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+        "PublicDescription": "Counts write-backs from the level 1 data cache that are a result of a coherency operation made by another CPU. Event count includes cache maintenance operations."
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+        "PublicDescription": "Counts each explicit invalidation of a cache line in the level 1 data cache caused by:\n\n- Cache Maintenance Operations (CMO) that operate by a virtual address.\n- Broadcast cache coherency operations from another CPU in the system.\n\nThis event does not count for the following conditions:\n\n1. A cache refill invalidates a cache line.\n2. A CMO which is executed on that CPU and invalidates a cache line specified by set/way.\n\nNote that CMOs that operate by set/way cannot be broadcast from one CPU to another."
+    }
+]

cmd/metrics/resources/events/aarch64/neoverse-n2-v2/l1i_cache.json

@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "L1I_CACHE_REFILL",
+        "PublicDescription": "Counts cache line refills in the level 1 instruction cache caused by a missed instruction fetch. Instruction fetches may include accessing multiple instructions, but the single cache line allocation is counted once."
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE",
+        "PublicDescription": "Counts instruction fetches which access the level 1 instruction cache. Instruction cache accesses caused by cache maintenance operations are not counted."
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE_LMISS",
+        "PublicDescription": "Counts cache line refills into the level 1 instruction cache, that incurred additional latency."
+    }
+]

cmd/metrics/resources/events/aarch64/neoverse-n2-v2/l2_cache.json

@@ -0,0 +1,50 @@
+[
+    {
+        "ArchStdEvent": "L2D_CACHE",
+        "PublicDescription": "Counts accesses to the level 2 cache due to data accesses. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level data cache or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL",
+        "PublicDescription": "Counts cache line refills into the level 2 cache. Level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 data cache or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB",
+        "PublicDescription": "Counts write-backs of data from the L2 cache to outside the CPU. This includes snoops to the L2 (from other CPUs) which return data even if the snoops cause an invalidation. L2 cache line invalidations which do not write data outside the CPU and snoops which return data from an L1 cache are not counted. Data would not be written outside the cache when invalidating a clean cache line."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_ALLOCATE",
+        "PublicDescription": "Counts level 2 cache line allocates that do not fetch data from outside the level 2 data or unified cache."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD",
+        "PublicDescription": "Counts level 2 data cache accesses due to memory read operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR",
+        "PublicDescription": "Counts level 2 cache accesses due to memory write operations. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD",
+        "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR",
+        "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. Level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 data cache or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM",
+        "PublicDescription": "Counts evictions from the level 2 cache because of a line being allocated into the L2 cache."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN",
+        "PublicDescription": "Counts write-backs from the level 2 cache that are a result of either:\n\n1. Cache maintenance operations,\n\n2. Snoop responses or,\n\n3. Direct cache transfers to another CPU due to a forwarding snoop request."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL",
+        "PublicDescription": "Counts each explicit invalidation of a cache line in the level 2 cache by cache maintenance operations that operate by a virtual address, or by external coherency operations. This event does not count if either:\n\n1. A cache refill invalidates a cache line or,\n2. A Cache Maintenance Operation (CMO), which invalidates a cache line specified by set/way, is executed on that CPU.\n\nCMOs that operate by set/way cannot be broadcast from one CPU to another."
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_LMISS_RD",
+        "PublicDescription": "Counts cache line refills into the level 2 unified cache from any memory read operations that incurred additional latency."
+    }
+]

cmd/metrics/resources/events/aarch64/neoverse-n2-v2/l3_cache.json

@@ -0,0 +1,22 @@
+[
+    {
+        "ArchStdEvent": "L3D_CACHE_ALLOCATE",
+        "PublicDescription": "Counts level 3 cache line allocates that do not fetch data from outside the level 3 data or unified cache. For example, allocates due to streaming stores."
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_REFILL",
+        "PublicDescription": "Counts level 3 accesses that receive data from outside the L3 cache."
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE",
+        "PublicDescription": "Counts level 3 cache accesses. Level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_RD",
+        "PublicDescription": "Counts level 3 cache accesses caused by any memory read operation. Level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses."
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_LMISS_RD",
+        "PublicDescription": "Counts any cache line refill into the level 3 cache from memory read operations that incurred additional latency."
+    }
+]

cmd/metrics/resources/events/aarch64/neoverse-n2-v2/ll_cache.json

@@ -0,0 +1,10 @@
+[
+    {
+        "ArchStdEvent": "LL_CACHE_RD",
+        "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts for external last level cache  when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for the L3 cache. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources."
+    },
+    {
+        "ArchStdEvent": "LL_CACHE_MISS_RD",
+        "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts for external last level cache when the system register CPUECTLR.EXTLLC bit is set, otherwise it counts for L3 cache. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations."
+    }
+]

cmd/metrics/resources/events/aarch64/neoverse-n2-v2/memory.json

@@ -0,0 +1,46 @@
+[
+    {
+        "ArchStdEvent": "MEM_ACCESS",
+        "PublicDescription": "Counts memory accesses issued by the CPU load store unit, where those accesses are issued due to load or store operations. This event counts memory accesses no matter whether the data is received from any level of cache hierarchy or external memory. If memory accesses are broken up into smaller transactions than what were specified in the load or store instructions, then the event counts those smaller memory transactions."
+    },
+    {
+        "ArchStdEvent": "MEMORY_ERROR",
+        "PublicDescription": "Counts any detected correctable or uncorrectable physical memory errors (ECC or parity) in protected CPUs RAMs. On the core, this event counts errors in the caches (including data and tag rams). Any detected memory error (from either a speculative and abandoned access, or an architecturally executed access) is counted. Note that errors are only detected when the actual protected memory is accessed by an operation."
+    },
+    {
+        "ArchStdEvent": "REMOTE_ACCESS",
+        "PublicDescription": "Counts accesses to another chip, which is implemented as a different CMN mesh in the system. If the CHI bus response back to the core indicates that the data source is from another chip (mesh), then the counter is updated. If no data is returned, even if the system snoops another chip/mesh, then the counter is not updated."
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+        "PublicDescription": "Counts memory accesses issued by the CPU due to load operations. The event counts any memory load access, no matter whether the data is received from any level of cache hierarchy or external memory. The event also counts atomic load operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions."
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+        "PublicDescription": "Counts memory accesses issued by the CPU due to store operations. The event counts any memory store access, no matter whether the data is located in any level of cache or external memory. The event also counts atomic load and store operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions."
+    },
+    {
+        "ArchStdEvent": "LDST_ALIGN_LAT",
+        "PublicDescription": "Counts the number of memory read and write accesses in a cycle that incurred additional latency, due to the alignment of the address and the size of data being accessed, which results in store crossing a single cache line."
+    },
+    {
+        "ArchStdEvent": "LD_ALIGN_LAT",
+        "PublicDescription": "Counts the number of memory read accesses in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed, which results in load crossing a single cache line."
+    },
+    {
+        "ArchStdEvent": "ST_ALIGN_LAT",
+        "PublicDescription": "Counts the number of memory write access in a cycle that incurred additional latency, due to the alignment of the address and size of data being accessed incurred additional latency."
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED",
+        "PublicDescription": "Counts the number of memory read and write accesses counted by MEM_ACCESS that are tag checked by the Memory Tagging Extension (MTE). This event is implemented as the sum of MEM_ACCESS_CHECKED_RD and MEM_ACCESS_CHECKED_WR"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_RD",
+        "PublicDescription": "Counts the number of memory read accesses in a cycle that are tag checked by the Memory Tagging Extension (MTE)."
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_WR",
+        "PublicDescription": "Counts the number of memory write accesses in a cycle that is tag checked by the Memory Tagging Extension (MTE)."
+    }
+]

cmd/metrics/resources/events/aarch64/neoverse-n2-v2/retired.json

@@ -0,0 +1,30 @@
+[
+    {
+        "ArchStdEvent": "SW_INCR",
+        "PublicDescription": "Counts software writes to the PMSWINC_EL0 (software PMU increment) register. The PMSWINC_EL0 register is a manually updated counter for use by application software.\n\nThis event could be used to measure any user program event, such as accesses to a particular data structure (by writing to the PMSWINC_EL0 register each time the data structure is accessed).\n\nTo use the PMSWINC_EL0 register and event, developers must insert instructions that write to the PMSWINC_EL0 register into the source code.\n\nSince the SW_INCR event records writes to the PMSWINC_EL0 register, there is no need to do a read/increment/write sequence to the PMSWINC_EL0 register."
+    },
+    {
+        "ArchStdEvent": "INST_RETIRED",
+        "PublicDescription": "Counts instructions that have been architecturally executed."
+    },
+    {
+        "ArchStdEvent": "CID_WRITE_RETIRED",
+        "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR_EL1 register, which usually contain the kernel PID and can be output with hardware trace."
+    },
+    {
+        "ArchStdEvent": "TTBR_WRITE_RETIRED",
+        "PublicDescription": "Counts architectural writes to TTBR0/1_EL1. If virtualization host extensions are enabled (by setting the HCR_EL2.E2H bit to 1), then accesses to TTBR0/1_EL1 that are redirected to TTBR0/1_EL2, or accesses to TTBR0/1_EL12, are counted. TTBRn registers are typically updated when the kernel is swapping user-space threads or applications."
+    },
+    {
+        "ArchStdEvent": "BR_RETIRED",
+        "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted. Note that exception generating instructions, exception return instructions and context synchronization instructions are not counted."
+    },
+    {
+        "ArchStdEvent": "BR_MIS_PRED_RETIRED",
+        "PublicDescription": "Counts branches counted by BR_RETIRED which were mispredicted and caused a pipeline flush."
+    },
+    {
+        "ArchStdEvent": "OP_RETIRED",
+        "PublicDescription": "Counts micro-operations that are architecturally executed. This is a count of number of micro-operations retired from the commit queue in a single cycle."
+    }
+]