| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 23 Mar 2023 12:20:28 -0700
From: Ian Rogers <irogers@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Zhengjun Xing <zhengjun.xing@...ux.intel.com>,
Kan Liang <kan.liang@...ux.intel.com>,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
Edward Baker <edward.baker@...el.com>,
Dan Williams <dan.j.williams@...el.com>,
perry.taylor@...el.com, caleb.biggers@...el.com,
samantha.alt@...el.com, weilin.wang@...el.com
Cc: Ian Rogers <irogers@...gle.com>
Subject: [PATCH v2 9/9] perf vendor events: Update metrics to detect optane
memory at runtime
By detecting whether optane memory is installed at runtime the number
of events can be reduced if it isn't. These changes come from this PR:
https://github.com/intel/perfmon/pull/63
Signed-off-by: Ian Rogers <irogers@...gle.com>
---
.../pmu-events/arch/x86/cascadelakex/clx-metrics.json | 10 +++++-----
.../perf/pmu-events/arch/x86/icelakex/icx-metrics.json | 10 +++++-----
.../arch/x86/sapphirerapids/spr-metrics.json | 10 +++++-----
3 files changed, 15 insertions(+), 15 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 4e993a3220e3..903f19ea1696 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -201,7 +201,7 @@
{
"BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
"MetricConstraint": "NO_GROUP_EVENTS",
- "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound",
+ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound if #has_optane > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound)",
"MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_dram_bound",
"MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -933,7 +933,7 @@
},
{
"BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]",
- "MetricExpr": "1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@...nt\\=0x0@",
+ "MetricExpr": "(1e9 * (UNC_M_PMM_RPQ_OCCUPANCY.ALL / UNC_M_PMM_RPQ_INSERTS) / imc_0@...nt\\=0x0@ if #has_optane > 0 else 0)",
"MetricGroup": "Mem;MemoryLat;Server;SoC",
"MetricName": "tma_info_mem_pmm_read_latency",
"PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
@@ -998,13 +998,13 @@
},
{
"BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
- "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time",
+ "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_optane > 0 else 0)",
"MetricGroup": "Mem;MemoryBW;Server;SoC",
"MetricName": "tma_info_pmm_read_bw"
},
{
"BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
- "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time",
+ "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_optane > 0 else 0)",
"MetricGroup": "Mem;MemoryBW;Server;SoC",
"MetricName": "tma_info_pmm_write_bw"
},
@@ -1310,7 +1310,7 @@
{
"BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a",
"MetricConstraint": "NO_GROUP_EVENTS",
- "MetricExpr": "((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0)",
+ "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_optane > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_optane > 0 else 0))) if #has_optane > 0 else 0)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_optane > 0 else 0)",
"MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_pmm_bound",
"MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
index 8109088a4df7..e5fba27dfe80 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
@@ -186,7 +186,7 @@
{
"BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
"MetricConstraint": "NO_GROUP_EVENTS",
- "MetricExpr": "CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound",
+ "MetricExpr": "(CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound - tma_pmm_bound if #has_optane > 0 else CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound)",
"MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_dram_bound",
"MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -918,7 +918,7 @@
},
{
"BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]",
- "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / cha_0@...nt\\=0x0@",
+ "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / cha_0@...nt\\=0x0@ if #has_optane > 0 else 0)",
"MetricGroup": "Mem;MemoryLat;Server;SoC",
"MetricName": "tma_info_mem_pmm_read_latency",
"PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
@@ -984,13 +984,13 @@
},
{
"BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
- "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time",
+ "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_optane > 0 else 0)",
"MetricGroup": "Mem;MemoryBW;Server;SoC",
"MetricName": "tma_info_pmm_read_bw"
},
{
"BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
- "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time",
+ "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_optane > 0 else 0)",
"MetricGroup": "Mem;MemoryBW;Server;SoC",
"MetricName": "tma_info_pmm_write_bw"
},
@@ -1298,7 +1298,7 @@
},
{
"BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a",
- "MetricExpr": "((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0)",
+ "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_optane > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_optane > 0 else 0))) if #has_optane > 0 else 0)) * (CYCLE_ACTIVITY.STALLS_L3_MISS / tma_info_clks + (CYCLE_ACTIVITY.STALLS_L1D_MISS - CYCLE_ACTIVITY.STALLS_L2_MISS) / tma_info_clks - tma_l2_bound) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_optane > 0 else 0)",
"MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_pmm_bound",
"MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index 149cc4c07fb5..d23fd6921a7f 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -185,7 +185,7 @@
{
"BriefDescription": "This metric estimates how often the CPU was stalled on accesses to external memory (DRAM) by loads",
"MetricConstraint": "NO_GROUP_EVENTS",
- "MetricExpr": "MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks - tma_pmm_bound",
+ "MetricExpr": "(MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks - tma_pmm_bound if #has_optane > 0 else MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks)",
"MetricGroup": "MemoryBound;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_dram_bound",
"MetricThreshold": "tma_dram_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
@@ -968,7 +968,7 @@
},
{
"BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]",
- "MetricExpr": "1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@...nt\\=0x1@",
+ "MetricExpr": "(1e9 * (UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM / UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM) / uncore_cha_0@...nt\\=0x1@ if #has_optane > 0 else 0)",
"MetricGroup": "Mem;MemoryLat;Server;SoC",
"MetricName": "tma_info_mem_pmm_read_latency",
"PublicDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches"
@@ -1034,13 +1034,13 @@
},
{
"BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
- "MetricExpr": "64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time",
+ "MetricExpr": "(64 * UNC_M_PMM_RPQ_INSERTS / 1e9 / duration_time if #has_optane > 0 else 0)",
"MetricGroup": "Mem;MemoryBW;Server;SoC",
"MetricName": "tma_info_pmm_read_bw"
},
{
"BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
- "MetricExpr": "64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time",
+ "MetricExpr": "(64 * UNC_M_PMM_WPQ_INSERTS / 1e9 / duration_time if #has_optane > 0 else 0)",
"MetricGroup": "Mem;MemoryBW;Server;SoC",
"MetricName": "tma_info_pmm_write_bw"
},
@@ -1406,7 +1406,7 @@
},
{
"BriefDescription": "This metric roughly estimates (based on idle latencies) how often the CPU was stalled on accesses to external 3D-Xpoint (Crystal Ridge, a.k.a",
- "MetricExpr": "((1 - (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))))) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0)",
+ "MetricExpr": "(((1 - ((19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS))) / (19 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + 10 * (MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) + MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS)) + (25 * (MEM_LOAD_RETIRED.LOCAL_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_optane > 0 else 0) + 33 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM * (1 + MEM_LOAD_RETIRED.FB_HIT / MEM_LOAD_RETIRED.L1_MISS) if #has_optane > 0 else 0))) if #has_optane > 0 else 0)) * (MEMORY_ACTIVITY.STALLS_L3_MISS / tma_info_clks) if 1e6 * (MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM + MEM_LOAD_RETIRED.LOCAL_PMM) > MEM_LOAD_RETIRED.L1_MISS else 0) if #has_optane > 0 else 0)",
"MetricGroup": "MemoryBound;Server;TmaL3mem;TopdownL3;tma_L3_group;tma_memory_bound_group",
"MetricName": "tma_pmm_bound",
"MetricThreshold": "tma_pmm_bound > 0.1 & (tma_memory_bound > 0.2 & tma_backend_bound > 0.2)",
--
2.40.0.348.gf938b09366-goog
Powered by blists - more mailing lists