Skip to contentSkip to conversation

perf: Fix POWER9 cpi_breakdown metricgroup

PATCH In review Paul A. Clarke 5 participants 14 messages May 7, 2020 – May 16, 2020 perf events

lore
Share & tools
lore
#0 lore raw

cover perf: Fix POWER9 cpi_breakdown metricgroup

From: "Paul A. Clarke" <[email protected]>

The recent patches posted by Ian Rogers motivated a deeper dive into the POWER9 perf metrics, which uncovered some additional issues:

- 'lsu_other_stall_cpi' doesn't work at all
- All of the "ICT" metrics are missing from the metricgroup

Paul A. Clarke (2):
perf: Fix POWER9 metric 'lsu_other_stall_cpi'
perf: Add missing metrics to POWER9 'cpi_breakdown'

 .../arch/powerpc/power9/metrics.json          | 143 ++++++++++--------
 tools/perf/util/expr.h                        |   2 +-
 2 files changed, 79 insertions(+), 66 deletions(-)
Signature · 1 line
2.18.2
#1 lore raw

PATCH 1/2 perf: Fix POWER9 metric 'lsu_other_stall_cpi'

From: "Paul A. Clarke" <[email protected]>

The metric definition is too long for the current value of EXPR_MAX_OTHER. Increase the value EXPR_MAX_OTHER sufficiently to allow 'lsu_other_stall_cpi' to build properly.

Before:
--

$ perf list | grep lsu_other
  lsu_other_stall_cpi
# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1
Cannot find metric or group `lsu_other_stall_cpi'

Usage: perf stat [<options>] [<command>]

-M, --metrics <metric/metric group list>
monitor specified metrics or metric groups (separated by ,)
--

After:
--

# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1

Performance counter stats for 'system wide':

       438,086,889      pm_cmplu_stall_lsu        #     1.74 lsu_other_stall_cpi

[...]
--

---
 tools/perf/util/expr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/expr.h +1 -1
index 87d627bb699b..a0991959cca4 100644
@@ -2,7 +2,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 20
+#define EXPR_MAX_OTHER 28
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct expr_parse_id {
Signature · 1 line
2.18.2
Acked-by Jiri Olsa on v1 1/2
#2 lore raw

Re: [PATCH 1/2] perf: Fix POWER9 metric 'lsu_other_stall_cpi'

Em Thu, May 07, 2020 at 11:28:57AM -0500, Paul A. Clarke escreveu:

Quoted 5 lines

From: "Paul A. Clarke" <[email protected]>

The metric definition is too long for the current value of EXPR_MAX_OTHER. Increase the value EXPR_MAX_OTHER sufficiently to allow 'lsu_other_stall_cpi' to build properly.

I already have a patch from Ian that bumps this further:

[acme@five perf]$ git log -p tools/perf/util/expr.h commit 26d3350db3e4668c1b1ff7f81c419afe71a2e8d9

Author: Ian Rogers <[email protected]>
Date:   Fri May 1 10:33:26 2020 -0700

perf expr: Increase max other

Large metrics such as Branch_Misprediction_Cost_SMT on x86 broadwell need more space.

Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Haiyan Song <[email protected]>
Cc Jin Yao <[email protected]>
Cc John Garry <[email protected]>
Cc Kajol Jain <[email protected]>
Cc Kan Liang <[email protected]>
Cc Leo Yan <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Paul Clarke <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Ravi Bangoria <[email protected]>
Cc Song Liu <[email protected]>
Cc Stephane Eranian <[email protected]>
tools/perf/util/expr.h +1 -1
index 87d627bb699b..40fc452b0f2b 100644
@@ -2,7 +2,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 20
+#define EXPR_MAX_OTHER 64
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct expr_parse_id {
Quoted 44 lines

Before:
--

$ perf list | grep lsu_other
  lsu_other_stall_cpi
# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1
Cannot find metric or group `lsu_other_stall_cpi'

Usage: perf stat [<options>] [<command>]

-M, --metrics <metric/metric group list>
monitor specified metrics or metric groups (separated by ,)
--

After:
--

# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1

Performance counter stats for 'system wide':

       438,086,889      pm_cmplu_stall_lsu        #     1.74 lsu_other_stall_cpi

[...]
--

---
 tools/perf/util/expr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/expr.h +1 -1
index 87d627bb699b..a0991959cca4 100644
@@ -2,7 +2,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 20
+#define EXPR_MAX_OTHER 28
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct expr_parse_id {
Signature · 1 line
2.18.2
Signature · 1 line
- Arnaldo
reviewer
#3 lore raw

Re: [PATCH 1/2] perf: Fix POWER9 metric 'lsu_other_stall_cpi'

Quoted 9 lines · Arnaldo Carvalho de Melo

Em Thu, May 07, 2020 at 11:28:57AM -0500, Paul A. Clarke escreveu:

Quoted 5 lines

From: "Paul A. Clarke" <[email protected]>

The metric definition is too long for the current value of EXPR_MAX_OTHER. Increase the value EXPR_MAX_OTHER sufficiently to allow 'lsu_other_stall_cpi' to build properly.

I already have a patch from Ian that bumps this further:

I sent out:
https://lore.kernel.org/lkml/[email protected]/
which removes this constant and moves the code to use a hashmap. Unfortunately, the hashmap comes from libbpf and so there is a dependency issue to resolve. Perhaps libapi can have a hashmap? I'm not sure who resolves these issues. A short-term fix is just to make the constant bigger.

Thanks,
Ian

Quoted 94 lines

[acme@five perf]$ git log -p tools/perf/util/expr.h commit 26d3350db3e4668c1b1ff7f81c419afe71a2e8d9

Author: Ian Rogers <[email protected]>
Date:   Fri May 1 10:33:26 2020 -0700

perf expr: Increase max other

Large metrics such as Branch_Misprediction_Cost_SMT on x86 broadwell need more space.

Cc Adrian Hunter <[email protected]>
Cc Alexander Shishkin <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Haiyan Song <[email protected]>
Cc Jin Yao <[email protected]>
Cc John Garry <[email protected]>
Cc Kajol Jain <[email protected]>
Cc Kan Liang <[email protected]>
Cc Leo Yan <[email protected]>
Cc Mark Rutland <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Paul Clarke <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Ravi Bangoria <[email protected]>
Cc Song Liu <[email protected]>
Cc Stephane Eranian <[email protected]>
tools/perf/util/expr.h +1 -1
index 87d627bb699b..40fc452b0f2b 100644
@@ -2,7 +2,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 20
+#define EXPR_MAX_OTHER 64
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct expr_parse_id {
Quoted 44 lines

Before:
--

$ perf list | grep lsu_other
  lsu_other_stall_cpi
# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1
Cannot find metric or group `lsu_other_stall_cpi'

Usage: perf stat [<options>] [<command>]

-M, --metrics <metric/metric group list>
monitor specified metrics or metric groups (separated by ,)
--

After:
--

# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1

Performance counter stats for 'system wide':

       438,086,889      pm_cmplu_stall_lsu        #     1.74 lsu_other_stall_cpi

[...]
--

---
 tools/perf/util/expr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/expr.h +1 -2
index 87d627bb699b..a0991959cca4 100644
@@ -2,7 +2,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 20
+#define EXPR_MAX_OTHER 28
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct expr_parse_id {
--
Quoted 2 lines

2.18.2

--

- Arnaldo

#4 lore raw

Re: [PATCH 1/2] perf: Fix POWER9 metric 'lsu_other_stall_cpi'

In reply to Paul A. Clarke
Quoted 39 lines · Paul A. Clarke

From: "Paul A. Clarke" <[email protected]>

The metric definition is too long for the current value of EXPR_MAX_OTHER. Increase the value EXPR_MAX_OTHER sufficiently to allow 'lsu_other_stall_cpi' to build properly.

Before:
--

$ perf list | grep lsu_other
  lsu_other_stall_cpi
# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1
Cannot find metric or group `lsu_other_stall_cpi'

Usage: perf stat [<options>] [<command>]

-M, --metrics <metric/metric group list>
monitor specified metrics or metric groups (separated by ,)
--

After:
--

# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1

Performance counter stats for 'system wide':

       438,086,889      pm_cmplu_stall_lsu        #     1.74 lsu_other_stall_cpi

[...]
--

---
 tools/perf/util/expr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/expr.h +0 -0
index 87d627bb699b..a0991959cca4 100644

tools/perf/util/expr.h line 5

Quoted 5 lines
tools/perf/util/expr.h +1 -1
@@ -2,7 +2,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
-#define EXPR_MAX_OTHER 20
+#define EXPR_MAX_OTHER 28

Hi Paul,
Ian already add one patch to increase EXPR_MAX_OTHER value to 68 which is Acked-by: Jiri

Link to the patch: https://lkml.org/lkml/2020/5/1/1023

Thanks,
Kajol Jain

Quoted 4 lines
tools/perf/util/expr.h +0 -0
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct expr_parse_id {
#5 lore raw

Re: [PATCH 1/2] perf: Fix POWER9 metric 'lsu_other_stall_cpi'

Quoted 45 lines · kajoljain
Quoted 42 lines · Paul A. Clarke

From: "Paul A. Clarke" <[email protected]>

The metric definition is too long for the current value of EXPR_MAX_OTHER. Increase the value EXPR_MAX_OTHER sufficiently to allow 'lsu_other_stall_cpi' to build properly.

Before:
--

$ perf list | grep lsu_other
  lsu_other_stall_cpi
# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1
Cannot find metric or group `lsu_other_stall_cpi'

Usage: perf stat [<options>] [<command>]

-M, --metrics <metric/metric group list>
monitor specified metrics or metric groups (separated by ,)
--

After:
--

# perf stat -a --metrics lsu_other_stall_cpi /bin/sleep 1

Performance counter stats for 'system wide':

       438,086,889      pm_cmplu_stall_lsu        #     1.74 lsu_other_stall_cpi

[...]
--

---
 tools/perf/util/expr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/expr.h +0 -0
index 87d627bb699b..a0991959cca4 100644
@@ -2,7 +2,7 @@
 #ifndef PARSE_CTX_H
 #define PARSE_CTX_H 1
 
Quoted 5 lines

tools/perf/util/expr.h line 5

Quoted 2 lines
tools/perf/util/expr.h +1 -1
-#define EXPR_MAX_OTHER 20
+#define EXPR_MAX_OTHER 28

Hi Paul,
Ian already add one patch to increase EXPR_MAX_OTHER value to 68 which is Acked-by: Jiri

Sorry its 64 not 68 and I missed earlier response from Arnaldo and Ian.

Thanks,
Kajol Jain

Quoted 10 lines

Link to the patch: https://lkml.org/lkml/2020/5/1/1023

Thanks,
Kajol Jain

Quoted 4 lines
tools/perf/util/expr.h +0 -0
 #define MAX_PARSE_ID EXPR_MAX_OTHER
 
 struct expr_parse_id {
#6 lore raw

PATCH 2/2 perf: Add missing metrics to POWER9 'cpi_breakdown'

In reply to Paul A. Clarke

From: "Paul A. Clarke" <[email protected]>

Add the following metrics to the POWER9 'cpi_breakdown' metricgroup:
- ict_noslot_br_mpred_cpi
- ict_noslot_br_mpred_icmiss_cpi
- ict_noslot_cyc_other_cpi
- ict_noslot_disp_held_cpi
- ict_noslot_disp_held_hb_full_cpi
- ict_noslot_disp_held_issq_cpi
- ict_noslot_disp_held_other_cpi
- ict_noslot_disp_held_sync_cpi
- ict_noslot_disp_held_tbegin_cpi
- ict_noslot_ic_l2_cpi
- ict_noslot_ic_l3_cpi
- ict_noslot_ic_l3miss_cpi
- ict_noslot_ic_miss_cpi

---
 .../arch/powerpc/power9/metrics.json          | 143 ++++++++++--------
 1 file changed, 78 insertions(+), 65 deletions(-)
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +78 -65
index 811c2a8c1c9e..6169351a72c8 100644
@@ -207,6 +207,84 @@
         "MetricGroup": "cpi_breakdown",
         "MetricName": "fxu_stall_cpi"
     },
+    {
+        "BriefDescription": "Ict empty for this thread due to branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
+    },
+    {
+        "BriefDescription": "ICT other stalls",
+        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_cyc_other_cpi"
+    },
+    {
+        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_issq_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_other_cpi"
+    },
+    {
+        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_sync_cpi"
+    },
+    {
+        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l2_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3miss_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_miss_cpi"
+    },
     {
         "MetricExpr": "(PM_NTC_ISSUE_HELD_DARQ_FULL + PM_NTC_ISSUE_HELD_ARB + PM_NTC_ISSUE_HELD_OTHER)/PM_RUN_INST_CMPL",
         "MetricGroup": "cpi_breakdown",
@@ -1819,71 +1897,6 @@
         "MetricExpr": "PM_FXU_IDLE / PM_CYC",
         "MetricName": "fxu_all_idle"
     },
-    {
-        "BriefDescription": "Ict empty for this thread due to branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
-    },
-    {
-        "BriefDescription": "ICT other stalls",
-        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_cyc_other_cpi"
-    },
-    {
-        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_issq_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_other_cpi"
-    },
-    {
-        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_sync_cpi"
-    },
-    {
-        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l2_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3miss_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_miss_cpi"
-    },
     {
         "BriefDescription": "Rate of IERAT reloads from L2",
         "MetricExpr": "PM_IPTEG_FROM_L2 * 100 / PM_RUN_INST_CMPL",
Signature · 1 line
2.18.2
#7 lore raw

Re: [PATCH 2/2] perf: Add missing metrics to POWER9 'cpi_breakdown'

Em Thu, May 07, 2020 at 11:28:58AM -0500, Paul A. Clarke escreveu:

Quoted 16 lines

From: "Paul A. Clarke" <[email protected]>

Add the following metrics to the POWER9 'cpi_breakdown' metricgroup:
- ict_noslot_br_mpred_cpi
- ict_noslot_br_mpred_icmiss_cpi
- ict_noslot_cyc_other_cpi
- ict_noslot_disp_held_cpi
- ict_noslot_disp_held_hb_full_cpi
- ict_noslot_disp_held_issq_cpi
- ict_noslot_disp_held_other_cpi
- ict_noslot_disp_held_sync_cpi
- ict_noslot_disp_held_tbegin_cpi
- ict_noslot_ic_l2_cpi
- ict_noslot_ic_l3_cpi
- ict_noslot_ic_l3miss_cpi
- ict_noslot_ic_miss_cpi

Can folks provide Acked-by or Reviewed-by? Thanks,

- Arnaldo

Quoted 169 lines
---
 .../arch/powerpc/power9/metrics.json          | 143 ++++++++++--------
 1 file changed, 78 insertions(+), 65 deletions(-)
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +78 -65
index 811c2a8c1c9e..6169351a72c8 100644
@@ -207,6 +207,84 @@
         "MetricGroup": "cpi_breakdown",
         "MetricName": "fxu_stall_cpi"
     },
+    {
+        "BriefDescription": "Ict empty for this thread due to branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
+    },
+    {
+        "BriefDescription": "ICT other stalls",
+        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_cyc_other_cpi"
+    },
+    {
+        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_issq_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_other_cpi"
+    },
+    {
+        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_sync_cpi"
+    },
+    {
+        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l2_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3miss_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_miss_cpi"
+    },
     {
         "MetricExpr": "(PM_NTC_ISSUE_HELD_DARQ_FULL + PM_NTC_ISSUE_HELD_ARB + PM_NTC_ISSUE_HELD_OTHER)/PM_RUN_INST_CMPL",
         "MetricGroup": "cpi_breakdown",
@@ -1819,71 +1897,6 @@
         "MetricExpr": "PM_FXU_IDLE / PM_CYC",
         "MetricName": "fxu_all_idle"
     },
-    {
-        "BriefDescription": "Ict empty for this thread due to branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
-    },
-    {
-        "BriefDescription": "ICT other stalls",
-        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_cyc_other_cpi"
-    },
-    {
-        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_issq_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_other_cpi"
-    },
-    {
-        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_sync_cpi"
-    },
-    {
-        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l2_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3miss_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_miss_cpi"
-    },
     {
         "BriefDescription": "Rate of IERAT reloads from L2",
         "MetricExpr": "PM_IPTEG_FROM_L2 * 100 / PM_RUN_INST_CMPL",
Signature · 1 line
2.18.2
Signature · 1 line
- Arnaldo
Reviewed-by on v1 2/2
#8 lore raw

Re: [PATCH 2/2] perf: Add missing metrics to POWER9 'cpi_breakdown'

In reply to Paul A. Clarke
Quoted 17 lines · Paul A. Clarke

From: "Paul A. Clarke" <[email protected]>

Add the following metrics to the POWER9 'cpi_breakdown' metricgroup:
- ict_noslot_br_mpred_cpi
- ict_noslot_br_mpred_icmiss_cpi
- ict_noslot_cyc_other_cpi
- ict_noslot_disp_held_cpi
- ict_noslot_disp_held_hb_full_cpi
- ict_noslot_disp_held_issq_cpi
- ict_noslot_disp_held_other_cpi
- ict_noslot_disp_held_sync_cpi
- ict_noslot_disp_held_tbegin_cpi
- ict_noslot_ic_l2_cpi
- ict_noslot_ic_l3_cpi
- ict_noslot_ic_l3miss_cpi
- ict_noslot_ic_miss_cpi

Quoted 1 line

Thanks,
Kajol Jain

Quoted 166 lines
---
 .../arch/powerpc/power9/metrics.json          | 143 ++++++++++--------
 1 file changed, 78 insertions(+), 65 deletions(-)
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +78 -65
index 811c2a8c1c9e..6169351a72c8 100644
@@ -207,6 +207,84 @@
         "MetricGroup": "cpi_breakdown",
         "MetricName": "fxu_stall_cpi"
     },
+    {
+        "BriefDescription": "Ict empty for this thread due to branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
+    },
+    {
+        "BriefDescription": "ICT other stalls",
+        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_cyc_other_cpi"
+    },
+    {
+        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_issq_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_other_cpi"
+    },
+    {
+        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_sync_cpi"
+    },
+    {
+        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l2_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3miss_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_miss_cpi"
+    },
     {
         "MetricExpr": "(PM_NTC_ISSUE_HELD_DARQ_FULL + PM_NTC_ISSUE_HELD_ARB + PM_NTC_ISSUE_HELD_OTHER)/PM_RUN_INST_CMPL",
         "MetricGroup": "cpi_breakdown",
@@ -1819,71 +1897,6 @@
         "MetricExpr": "PM_FXU_IDLE / PM_CYC",
         "MetricName": "fxu_all_idle"
     },
-    {
-        "BriefDescription": "Ict empty for this thread due to branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
-    },
-    {
-        "BriefDescription": "ICT other stalls",
-        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_cyc_other_cpi"
-    },
-    {
-        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_issq_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_other_cpi"
-    },
-    {
-        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_sync_cpi"
-    },
-    {
-        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l2_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3miss_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_miss_cpi"
-    },
     {
         "BriefDescription": "Rate of IERAT reloads from L2",
         "MetricExpr": "PM_IPTEG_FROM_L2 * 100 / PM_RUN_INST_CMPL",
reviewer Tested-by
#9 lore raw

Re: [PATCH 2/2] perf: Add missing metrics to POWER9 'cpi_breakdown'

Quoted 18 lines · kajoljain
Quoted 17 lines · Paul A. Clarke

From: "Paul A. Clarke" <[email protected]>

Add the following metrics to the POWER9 'cpi_breakdown' metricgroup:
- ict_noslot_br_mpred_cpi
- ict_noslot_br_mpred_icmiss_cpi
- ict_noslot_cyc_other_cpi
- ict_noslot_disp_held_cpi
- ict_noslot_disp_held_hb_full_cpi
- ict_noslot_disp_held_issq_cpi
- ict_noslot_disp_held_other_cpi
- ict_noslot_disp_held_sync_cpi
- ict_noslot_disp_held_tbegin_cpi
- ict_noslot_ic_l2_cpi
- ict_noslot_ic_l3_cpi
- ict_noslot_ic_l3miss_cpi
- ict_noslot_ic_miss_cpi

Quoted 3 lines
Quoted 1 line

Tested with:
https://lore.kernel.org/lkml/[email protected]/

Thanks,
Ian

Quoted 168 lines

Thanks,
Kajol Jain

Quoted 166 lines
---
 .../arch/powerpc/power9/metrics.json          | 143 ++++++++++--------
 1 file changed, 78 insertions(+), 65 deletions(-)
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +78 -65
index 811c2a8c1c9e..6169351a72c8 100644
@@ -207,6 +207,84 @@
         "MetricGroup": "cpi_breakdown",
         "MetricName": "fxu_stall_cpi"
     },
+    {
+        "BriefDescription": "Ict empty for this thread due to branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
+    },
+    {
+        "BriefDescription": "ICT other stalls",
+        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_cyc_other_cpi"
+    },
+    {
+        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_issq_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_other_cpi"
+    },
+    {
+        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_sync_cpi"
+    },
+    {
+        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l2_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3miss_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_miss_cpi"
+    },
     {
         "MetricExpr": "(PM_NTC_ISSUE_HELD_DARQ_FULL + PM_NTC_ISSUE_HELD_ARB + PM_NTC_ISSUE_HELD_OTHER)/PM_RUN_INST_CMPL",
         "MetricGroup": "cpi_breakdown",
@@ -1819,71 +1897,6 @@
         "MetricExpr": "PM_FXU_IDLE / PM_CYC",
         "MetricName": "fxu_all_idle"
     },
-    {
-        "BriefDescription": "Ict empty for this thread due to branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
-    },
-    {
-        "BriefDescription": "ICT other stalls",
-        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_cyc_other_cpi"
-    },
-    {
-        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_issq_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_other_cpi"
-    },
-    {
-        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_sync_cpi"
-    },
-    {
-        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l2_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3miss_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_miss_cpi"
-    },
     {
         "BriefDescription": "Rate of IERAT reloads from L2",
         "MetricExpr": "PM_IPTEG_FROM_L2 * 100 / PM_RUN_INST_CMPL",
#10 lore raw

Re: [PATCH 2/2] perf: Add missing metrics to POWER9 'cpi_breakdown'

Em Sat, May 09, 2020 at 11:26:56PM -0700, Ian Rogers escreveu:

Quoted 19 lines · kajoljain
Quoted 18 lines · Paul A. Clarke
Quoted 17 lines

From: "Paul A. Clarke" <[email protected]>

Add the following metrics to the POWER9 'cpi_breakdown' metricgroup:
- ict_noslot_br_mpred_cpi
- ict_noslot_br_mpred_icmiss_cpi
- ict_noslot_cyc_other_cpi
- ict_noslot_disp_held_cpi
- ict_noslot_disp_held_hb_full_cpi
- ict_noslot_disp_held_issq_cpi
- ict_noslot_disp_held_other_cpi
- ict_noslot_disp_held_sync_cpi
- ict_noslot_disp_held_tbegin_cpi
- ict_noslot_ic_l2_cpi
- ict_noslot_ic_l3_cpi
- ict_noslot_ic_l3miss_cpi
- ict_noslot_ic_miss_cpi

Quoted 7 lines
Quoted 3 lines
Quoted 1 line

Tested with:
https://lore.kernel.org/lkml/[email protected]/

Thanks, looking up that series now,

- Arnaldo

Quoted 171 lines

Thanks,
Ian

Quoted 168 lines

Thanks,
Kajol Jain

Quoted 166 lines
---
 .../arch/powerpc/power9/metrics.json          | 143 ++++++++++--------
 1 file changed, 78 insertions(+), 65 deletions(-)
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +78 -65
index 811c2a8c1c9e..6169351a72c8 100644
@@ -207,6 +207,84 @@
         "MetricGroup": "cpi_breakdown",
         "MetricName": "fxu_stall_cpi"
     },
+    {
+        "BriefDescription": "Ict empty for this thread due to branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
+        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
+    },
+    {
+        "BriefDescription": "ICT other stalls",
+        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_cyc_other_cpi"
+    },
+    {
+        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_issq_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_other_cpi"
+    },
+    {
+        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_sync_cpi"
+    },
+    {
+        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
+        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
+    },
+    {
+        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
+        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l2_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_l3miss_cpi"
+    },
+    {
+        "BriefDescription": "Ict empty for this thread due to Icache Miss",
+        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
+        "MetricGroup": "cpi_breakdown",
+        "MetricName": "ict_noslot_ic_miss_cpi"
+    },
     {
         "MetricExpr": "(PM_NTC_ISSUE_HELD_DARQ_FULL + PM_NTC_ISSUE_HELD_ARB + PM_NTC_ISSUE_HELD_OTHER)/PM_RUN_INST_CMPL",
         "MetricGroup": "cpi_breakdown",
@@ -1819,71 +1897,6 @@
         "MetricExpr": "PM_FXU_IDLE / PM_CYC",
         "MetricName": "fxu_all_idle"
     },
-    {
-        "BriefDescription": "Ict empty for this thread due to branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss and branch mispred",
-        "MetricExpr": "PM_ICT_NOSLOT_BR_MPRED_ICMISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_br_mpred_icmiss_cpi"
-    },
-    {
-        "BriefDescription": "ICT other stalls",
-        "MetricExpr": "(PM_ICT_NOSLOT_CYC - PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_BR_MPRED_ICMISS - PM_ICT_NOSLOT_BR_MPRED - PM_ICT_NOSLOT_DISP_HELD)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_cyc_other_cpi"
-    },
-    {
-        "BriefDescription": "Cycles in which the NTC instruciton is held at dispatch for any reason",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_HB_FULL/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_hb_full_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to dispatch hold on this thread due to Issue q full, BRQ full, XVCF Full, Count cache, Link, Tar full",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_ISSQ/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_issq_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_DISP_HELD_OTHER_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_DISP_HELD - PM_ICT_NOSLOT_DISP_HELD_HB_FULL - PM_ICT_NOSLOT_DISP_HELD_SYNC - PM_ICT_NOSLOT_DISP_HELD_TBEGIN - PM_ICT_NOSLOT_DISP_HELD_ISSQ)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_other_cpi"
-    },
-    {
-        "BriefDescription": "Dispatch held due to a synchronizing instruction at dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_SYNC/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_sync_cpi"
-    },
-    {
-        "BriefDescription": "the NTC instruction is being held at dispatch because it is a tbegin instruction and there is an older tbegin in the pipeline that must complete before the younger tbegin can dispatch",
-        "MetricExpr": "PM_ICT_NOSLOT_DISP_HELD_TBEGIN/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_disp_held_tbegin_cpi"
-    },
-    {
-        "BriefDescription": "ICT_NOSLOT_IC_L2_CPI",
-        "MetricExpr": "(PM_ICT_NOSLOT_IC_MISS - PM_ICT_NOSLOT_IC_L3 - PM_ICT_NOSLOT_IC_L3MISS)/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l2_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from the local L3",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to icache misses that were sourced from beyond the local L3. The source could be local/remote/distant memory or another core's cache",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_L3MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_l3miss_cpi"
-    },
-    {
-        "BriefDescription": "Ict empty for this thread due to Icache Miss",
-        "MetricExpr": "PM_ICT_NOSLOT_IC_MISS/PM_RUN_INST_CMPL",
-        "MetricName": "ict_noslot_ic_miss_cpi"
-    },
     {
         "BriefDescription": "Rate of IERAT reloads from L2",
         "MetricExpr": "PM_IPTEG_FROM_L2 * 100 / PM_RUN_INST_CMPL",
Signature · 1 line
- Arnaldo
#11 lore raw

Re: [PATCH 2/2] perf: Add missing metrics to POWER9 'cpi_breakdown'

In reply to Paul A. Clarke
Quoted 27 lines · Paul A. Clarke

From: "Paul A. Clarke" <[email protected]>

Add the following metrics to the POWER9 'cpi_breakdown' metricgroup:
- ict_noslot_br_mpred_cpi
- ict_noslot_br_mpred_icmiss_cpi
- ict_noslot_cyc_other_cpi
- ict_noslot_disp_held_cpi
- ict_noslot_disp_held_hb_full_cpi
- ict_noslot_disp_held_issq_cpi
- ict_noslot_disp_held_other_cpi
- ict_noslot_disp_held_sync_cpi
- ict_noslot_disp_held_tbegin_cpi
- ict_noslot_ic_l2_cpi
- ict_noslot_ic_l3_cpi
- ict_noslot_ic_l3miss_cpi
- ict_noslot_ic_miss_cpi

---
 .../arch/powerpc/power9/metrics.json          | 143 ++++++++++--------
 1 file changed, 78 insertions(+), 65 deletions(-)
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +0 -0
index 811c2a8c1c9e..6169351a72c8 100644

tools/perf/pmu-events/arch/powerpc/power9/metrics.json line 211

Quoted 5 lines
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +2 -0
@@ -207,6 +207,84 @@
         "MetricGroup": "cpi_breakdown",
         "MetricName": "fxu_stall_cpi"
     },
+    {
+        "BriefDescription": "Ict empty for this thread due to branch mispred",

I think you're just moving this, not adding it. But ICT is an acronym, so it should be spelled ICT not Ict.

It might be worth expanding it too?

cheers

#12 lore raw

Re: [PATCH 2/2] perf: Add missing metrics to POWER9 'cpi_breakdown'

Quoted 35 lines · Michael Ellerman
Quoted 25 lines · Paul A. Clarke

Add the following metrics to the POWER9 'cpi_breakdown' metricgroup:
- ict_noslot_br_mpred_cpi
- ict_noslot_br_mpred_icmiss_cpi
- ict_noslot_cyc_other_cpi
- ict_noslot_disp_held_cpi
- ict_noslot_disp_held_hb_full_cpi
- ict_noslot_disp_held_issq_cpi
- ict_noslot_disp_held_other_cpi
- ict_noslot_disp_held_sync_cpi
- ict_noslot_disp_held_tbegin_cpi
- ict_noslot_ic_l2_cpi
- ict_noslot_ic_l3_cpi
- ict_noslot_ic_l3miss_cpi
- ict_noslot_ic_miss_cpi

---
 .../arch/powerpc/power9/metrics.json          | 143 ++++++++++--------
 1 file changed, 78 insertions(+), 65 deletions(-)
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +0 -0
index 811c2a8c1c9e..6169351a72c8 100644

tools/perf/pmu-events/arch/powerpc/power9/metrics.json line 211

Quoted 5 lines
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +2 -0
@@ -207,6 +207,84 @@
         "MetricGroup": "cpi_breakdown",
         "MetricName": "fxu_stall_cpi"
     },
+    {
+        "BriefDescription": "Ict empty for this thread due to branch mispred",

I think you're just moving this, not adding it. But ICT is an acronym, so it should be spelled ICT not Ict.

Quoted 1 line

It might be worth expanding it too?

This was 98% produced through automated means, translating an existing XML file to perf's JSON format.

I've gotten the upstream XML file changed to include the "ICT" metrics in the "cpi_breakdown" group already, and can request the changes you suggest also be incorporated.

For the time being, can we move forward with the patch as-is?

PC

#13 lore raw

Re: [PATCH 2/2] perf: Add missing metrics to POWER9 'cpi_breakdown'

Quoted 38 lines · Paul A. Clarke
Quoted 35 lines · Michael Ellerman
Quoted 25 lines · Paul A. Clarke

Add the following metrics to the POWER9 'cpi_breakdown' metricgroup:
- ict_noslot_br_mpred_cpi
- ict_noslot_br_mpred_icmiss_cpi
- ict_noslot_cyc_other_cpi
- ict_noslot_disp_held_cpi
- ict_noslot_disp_held_hb_full_cpi
- ict_noslot_disp_held_issq_cpi
- ict_noslot_disp_held_other_cpi
- ict_noslot_disp_held_sync_cpi
- ict_noslot_disp_held_tbegin_cpi
- ict_noslot_ic_l2_cpi
- ict_noslot_ic_l3_cpi
- ict_noslot_ic_l3miss_cpi
- ict_noslot_ic_miss_cpi

---
 .../arch/powerpc/power9/metrics.json          | 143 ++++++++++--------
 1 file changed, 78 insertions(+), 65 deletions(-)
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +0 -0
index 811c2a8c1c9e..6169351a72c8 100644

tools/perf/pmu-events/arch/powerpc/power9/metrics.json line 211

Quoted 5 lines
tools/perf/pmu-events/arch/powerpc/power9/metrics.json +2 -0
@@ -207,6 +207,84 @@
         "MetricGroup": "cpi_breakdown",
         "MetricName": "fxu_stall_cpi"
     },
+    {
+        "BriefDescription": "Ict empty for this thread due to branch mispred",

I think you're just moving this, not adding it. But ICT is an acronym, so it should be spelled ICT not Ict.

Quoted 1 line

It might be worth expanding it too?

Quoted 8 lines

This was 98% produced through automated means, translating an existing XML file to perf's JSON format.

I've gotten the upstream XML file changed to include the "ICT" metrics in the "cpi_breakdown" group already, and can request the changes you suggest also be incorporated.

For the time being, can we move forward with the patch as-is?

Fine by me.

cheers