lkml.org 
[lkml]   [2022]   [Jul]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Date
SubjectRe: [PATCH v3 21/30] perf vendor events: Update Intel sandybridge
On Fri, Jul 29, 2022 at 4:36 PM Ian Rogers <irogers@google.com> wrote:
>
> On Fri, Jul 29, 2022 at 1:48 AM Sedat Dilek <sedat.dilek@gmail.com> wrote:
> >
> > On Fri, Jul 29, 2022 at 10:41 AM Sedat Dilek <sedat.dilek@gmail.com> wrote:
> > >
> > > On Thu, Jul 28, 2022 at 12:09 AM Ian Rogers <irogers@google.com> wrote:
> > > >
> > > > Update to v17, the metrics are based on TMA 4.4 full.
> > > >
> > > > Use script at:
> > > > https://github.com/intel/event-converter-for-linux-perf/blob/master/download_and_gen.py
> > > >
> > > > to download and generate the latest events and metrics. Manually copy
> > > > the sandybridge files into perf and update mapfile.csv.
> > > >
> > > > Tested on a non-sandybridge with 'perf test':
> > > > 10: PMU events :
> > > > 10.1: PMU event table sanity : Ok
> > > > 10.2: PMU event map aliases : Ok
> > > > 10.3: Parsing of PMU event table metrics : Ok
> > > > 10.4: Parsing of PMU event table metrics with fake PMUs : Ok
> > > >
> > >
> > > Hi Ian,
> > >
> > > thanks for v3 patchset.
> > >
> > > I used latest perf/core Git branch from Arnaldo's tree plus some
> > > custom patches (to fix binutils v2.38.90 and opennssl-v3 issues plus
> > > gnu11 tools patches) and build with LLVM-14.
> > >
> > > When I run on my Intel SandyBridge CPU...
> > >
> > > $ ~/bin/perf test
> > > ...
> > > 10: PMU events :
> > > 10.1: PMU event table sanity : Ok
> > > 10.2: PMU event map aliases : Ok
> > > 10.3: Parsing of PMU event table metrics : Ok
> > > 10.4: Parsing of PMU event table metrics with fake PMUs : Ok
> > > ...
> > >
> > > First time I ran perf with option test.
> > >
> > > Looks that good to you?
> > >
> >
> > Nice.
> >
> > $~/bin/perf test list
> > ...
> > 10: PMU events
> > 10:1: PMU event table sanity
> > 10:2: PMU event map aliases
> > 10:3: Parsing of PMU event table metrics
> > 10:4: Parsing of PMU event table metrics with fake PMUs
> > ...
> >
> > $ ~/bin/perf test 10
> > 10: PMU events :
> > 10.1: PMU event table sanity : Ok
> > 10.2: PMU event map aliases : Ok
> > 10.3: Parsing of PMU event table metrics : Ok
> > 10.4: Parsing of PMU event table metrics with fake PMUs : Ok
> >
> > New perf lessons learned.
>
> Thanks. There are also tests that iterate and run the events/metrics
> on your hardware:
>
> $ perf test list
> ...
> 93: perf all metricgroups test
> 94: perf all metrics test
> ...
> 96: perf all PMU test
> ...
>
> Test 10 is a unit test and tests 93, 94 and 96 (your numbers may vary)
> are more like integration tests.
>

Hi Ian,

thanks for the hints.

I tried like that:

$ ~/bin/perf test list 93 94 95
93: perf all metricgroups test
94: perf all metrics test
95: perf all PMU test

$ ~/bin/perf test 93 94 95
93: perf all metricgroups test : Ok
94: perf all metrics test : Ok
95: perf all PMU test : Ok

Looks good.

The tests FAILED when /proc/sys/kernel/perf_event_paranoid is not
appropriate set.

From my build_linux-llvm.sh:

317:echo "##### Starting Linux-kernel build ..."
318:echo "linux-perf: Adjust limited access to performance monitoring
and observability operations"
319:echo 0 | sudo tee /proc/sys/kernel/kptr_restrict
/proc/sys/kernel/perf_event_paranoid
...
321:echo 1 | sudo tee /proc/sys/kernel/kptr_restrict
/proc/sys/kernel/perf_event_paranoid
322:echo "linux-perf: Reset limited access to performance monitoring
and observability operations"

In Debian-kernels the default is 3 (Debian has some additional patches
for perf restrictions).

Best regards,
-Sedat-

> > >
> > > > Signed-off-by: Ian Rogers <irogers@google.com>
> > > > ---
> > > > tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
> > > > tools/perf/pmu-events/arch/x86/sandybridge/cache.json | 2 +-
> > > > .../arch/x86/sandybridge/floating-point.json | 2 +-
> > > > .../pmu-events/arch/x86/sandybridge/frontend.json | 4 ++--
> > > > .../perf/pmu-events/arch/x86/sandybridge/memory.json | 2 +-
> > > > tools/perf/pmu-events/arch/x86/sandybridge/other.json | 2 +-
> > > > .../pmu-events/arch/x86/sandybridge/pipeline.json | 10 +++++-----
> > > > .../pmu-events/arch/x86/sandybridge/snb-metrics.json | 11 +++++++++--
> > > > .../pmu-events/arch/x86/sandybridge/uncore-other.json | 2 +-
> > > > .../arch/x86/sandybridge/virtual-memory.json | 2 +-
> > > > 10 files changed, 23 insertions(+), 16 deletions(-)
> > > >
> > > > diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
> > > > index 2f9419ee2d29..0b56c4a8a3a8 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/mapfile.csv
> > > > +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
> > > > @@ -19,12 +19,12 @@ GenuineIntel-6-(57|85),v9,knightslanding,core
> > > > GenuineIntel-6-AA,v1.00,meteorlake,core
> > > > GenuineIntel-6-1[AEF],v3,nehalemep,core
> > > > GenuineIntel-6-2E,v3,nehalemex,core
> > > > +GenuineIntel-6-2A,v17,sandybridge,core
> > > > GenuineIntel-6-[4589]E,v24,skylake,core
> > > > GenuineIntel-6-A[56],v24,skylake,core
> > > > GenuineIntel-6-37,v13,silvermont,core
> > > > GenuineIntel-6-4D,v13,silvermont,core
> > > > GenuineIntel-6-4C,v13,silvermont,core
> > > > -GenuineIntel-6-2A,v15,sandybridge,core
> > > > GenuineIntel-6-2C,v2,westmereep-dp,core
> > > > GenuineIntel-6-25,v2,westmereep-sp,core
> > > > GenuineIntel-6-2F,v2,westmereex,core
> > > > diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json
> > > > index 92a7269eb444..a1d622352131 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json
> > > > +++ b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json
> > > > @@ -1876,4 +1876,4 @@
> > > > "SampleAfterValue": "100003",
> > > > "UMask": "0x10"
> > > > }
> > > > -]
> > > > \ No newline at end of file
> > > > +]
> > > > diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json
> > > > index 713878fd062b..eb2ff2cfdf6b 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json
> > > > +++ b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json
> > > > @@ -135,4 +135,4 @@
> > > > "SampleAfterValue": "2000003",
> > > > "UMask": "0x1"
> > > > }
> > > > -]
> > > > \ No newline at end of file
> > > > +]
> > > > diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
> > > > index fa22f9463b66..e2c82e43a2de 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
> > > > +++ b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
> > > > @@ -176,7 +176,7 @@
> > > > "CounterMask": "1",
> > > > "EventCode": "0x79",
> > > > "EventName": "IDQ.MS_CYCLES",
> > > > - "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance. See the Intel 64 and IA-32 Architectures Optimization Reference Manual for more information.",
> > > > + "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops. Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder. Using other instructions, if possible, will usually improve performance. See the Intel(R) 64 and IA-32 Architectures Optimization Reference Manual for more information.",
> > > > "SampleAfterValue": "2000003",
> > > > "UMask": "0x30"
> > > > },
> > > > @@ -311,4 +311,4 @@
> > > > "SampleAfterValue": "2000003",
> > > > "UMask": "0x1"
> > > > }
> > > > -]
> > > > \ No newline at end of file
> > > > +]
> > > > diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json
> > > > index 931892d34076..3c283ca309f3 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json
> > > > +++ b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json
> > > > @@ -442,4 +442,4 @@
> > > > "SampleAfterValue": "100003",
> > > > "UMask": "0x1"
> > > > }
> > > > -]
> > > > \ No newline at end of file
> > > > +]
> > > > diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/other.json b/tools/perf/pmu-events/arch/x86/sandybridge/other.json
> > > > index e251f535ec09..2f873ab14156 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/sandybridge/other.json
> > > > +++ b/tools/perf/pmu-events/arch/x86/sandybridge/other.json
> > > > @@ -55,4 +55,4 @@
> > > > "SampleAfterValue": "2000003",
> > > > "UMask": "0x1"
> > > > }
> > > > -]
> > > > \ No newline at end of file
> > > > +]
> > > > diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json
> > > > index b9a3f194a00a..2c3b6c92aa6b 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json
> > > > +++ b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json
> > > > @@ -609,7 +609,7 @@
> > > > "UMask": "0x3"
> > > > },
> > > > {
> > > > - "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
> > > > + "BriefDescription": "Number of occurrences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
> > > > "Counter": "0,1,2,3",
> > > > "CounterHTOff": "0,1,2,3,4,5,6,7",
> > > > "CounterMask": "1",
> > > > @@ -652,7 +652,7 @@
> > > > "CounterHTOff": "0,1,2,3,4,5,6,7",
> > > > "EventCode": "0x03",
> > > > "EventName": "LD_BLOCKS.STORE_FORWARD",
> > > > - "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
> > > > + "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load. The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store. See the table of not supported store forwards in the Intel(R) 64 and IA-32 Architectures Optimization Reference Manual. The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
> > > > "SampleAfterValue": "100003",
> > > > "UMask": "0x2"
> > > > },
> > > > @@ -778,7 +778,7 @@
> > > > "CounterMask": "1",
> > > > "EventCode": "0x59",
> > > > "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES",
> > > > - "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel 64 and IA-32 Architectures Optimization Reference Manual.",
> > > > + "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel(R) 64 and IA-32 Architectures Optimization Reference Manual.",
> > > > "SampleAfterValue": "2000003",
> > > > "UMask": "0x20"
> > > > },
> > > > @@ -797,7 +797,7 @@
> > > > "CounterHTOff": "0,1,2,3,4,5,6,7",
> > > > "EventCode": "0x59",
> > > > "EventName": "PARTIAL_RAT_STALLS.SLOW_LEA_WINDOW",
> > > > - "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.",
> > > > + "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel(R) 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.",
> > > > "SampleAfterValue": "2000003",
> > > > "UMask": "0x40"
> > > > },
> > > > @@ -1209,4 +1209,4 @@
> > > > "SampleAfterValue": "2000003",
> > > > "UMask": "0x1"
> > > > }
> > > > -]
> > > > \ No newline at end of file
> > > > +]
> > > > diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
> > > > index c8e7050d9c26..ae7ed267b2a2 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
> > > > +++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
> > > > @@ -124,7 +124,7 @@
> > > > "MetricName": "FLOPc_SMT"
> > > > },
> > > > {
> > > > - "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
> > > > + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
> > > > "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
> > > > "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
> > > > "MetricName": "ILP"
> > > > @@ -141,6 +141,12 @@
> > > > "MetricGroup": "Summary;TmaL1",
> > > > "MetricName": "Instructions"
> > > > },
> > > > + {
> > > > + "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
> > > > + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
> > > > + "MetricGroup": "Pipeline;Ret",
> > > > + "MetricName": "Retire"
> > > > + },
> > > > {
> > > > "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
> > > > "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
> > > > @@ -163,7 +169,8 @@
> > > > "BriefDescription": "Giga Floating Point Operations Per Second",
> > > > "MetricExpr": "( ( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE ) / 1000000000 ) / duration_time",
> > > > "MetricGroup": "Cor;Flops;HPC",
> > > > - "MetricName": "GFLOPs"
> > > > + "MetricName": "GFLOPs",
> > > > + "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine."
> > > > },
> > > > {
> > > > "BriefDescription": "Average Frequency Utilization relative nominal frequency",
> > > > diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/uncore-other.json b/tools/perf/pmu-events/arch/x86/sandybridge/uncore-other.json
> > > > index 6278068908cf..88f1e326205f 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/sandybridge/uncore-other.json
> > > > +++ b/tools/perf/pmu-events/arch/x86/sandybridge/uncore-other.json
> > > > @@ -82,10 +82,10 @@
> > > > {
> > > > "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
> > > > "Counter": "Fixed",
> > > > + "EventCode": "0xff",
> > > > "EventName": "UNC_CLOCK.SOCKET",
> > > > "PerPkg": "1",
> > > > "PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
> > > > - "UMask": "0x01",
> > > > "Unit": "ARB"
> > > > }
> > > > ]
> > > > diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json
> > > > index 4dd136d00a10..98362abba1a7 100644
> > > > --- a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json
> > > > +++ b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json
> > > > @@ -146,4 +146,4 @@
> > > > "SampleAfterValue": "100007",
> > > > "UMask": "0x20"
> > > > }
> > > > -]
> > > > \ No newline at end of file
> > > > +]
> > > > --
> > > > 2.37.1.359.gd136c6c3e2-goog
> > > >

\
 
 \ /
  Last update: 2022-07-30 20:45    [W:0.053 / U:0.680 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site