Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TMA 5.01 Fixes #244

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

TMA 5.01 Fixes #244

wants to merge 3 commits into from

Conversation

calebbiggers
Copy link
Contributor

  • Fixes brief descriptions ending in periods
  • Fixes missing thresholds
  • Fixes incorrect visibility for GRR file

Copy link
Contributor

@edwarddavidbaker edwarddavidbaker left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Two metric thresholds on SKX and CLX look strange. Highlighted via create_perf_json.py failures. I assume it should be tma_code_stlb_hit > 5 but defer to Caleb regarding & p.

    {
        "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
        "MetricExpr": "max( 0 , tma_itlb_misses - tma_code_stlb_miss )",
        "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
        "MetricName": "tma_code_stlb_hit",
        "ScaleUnit": "100%",
        "MetricThreshold": "> 5 & p"
    },
    {
        "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
        "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
        "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
        "MetricName": "tma_code_stlb_miss",
        "ScaleUnit": "100%",
        "MetricThreshold": "> 5 & p"
    },

@1perrytaylor
Copy link
Contributor

Two metric thresholds on SKX and CLX look strange. Highlighted via create_perf_json.py failures. I assume it should be tma_code_stlb_hit > 5 but defer to Caleb regarding & p.

    {
        "BriefDescription": "This metric roughly estimates the fraction of cycles where the (first level) ITLB was missed by instructions fetches, that later on hit in second-level TLB (STLB)",
        "MetricExpr": "max( 0 , tma_itlb_misses - tma_code_stlb_miss )",
        "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
        "MetricName": "tma_code_stlb_hit",
        "ScaleUnit": "100%",
        "MetricThreshold": "> 5 & p"
    },
    {
        "BriefDescription": "This metric estimates the fraction of cycles where the Second-level TLB (STLB) was missed by instruction fetches, performing a hardware page walk",
        "MetricExpr": "ITLB_MISSES.WALK_ACTIVE / tma_info_thread_clks",
        "MetricGroup": "FetchLat;MemoryTLB;TopdownL4;tma_L4_group;tma_itlb_misses_group",
        "MetricName": "tma_code_stlb_miss",
        "ScaleUnit": "100%",
        "MetricThreshold": "> 5 & p"
    },

Thanks Ed. We are working on an update.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants