[PATCH] D112042: [llvm-profgen] Skip duplication factor outside of body sample computation

Tue Oct 19 10:00:46 PDT 2021

wenlei added subscribers: hoy, wlei.
wenlei added a comment.

Good to know. Just to clarify, you meant that the removal of duplication factor doesn’t show perf impact, right? You didn’t actually try to see if fixing the bloated total samples (as proposed in the patch) has perf impact?

Asking because I think the fix here would affect sample loader inlining for AutoFDO since it looks at total samples for inline decision. It may not have perf impact still depending on workloads. For our HHVM workload, one cold function was incorrectly accounted as the top 5 hot functions in profile due to this bug. But I’m surprised that this bug survived in the tools used by both of us through the years.. 😊

Thanks,
Wenlei

From: Rong Xu <xur at google.com>
Date: Tuesday, October 19, 2021 at 9:44 AM
To: Wenlei He <reviews+D112042 <https://reviews.llvm.org/D112042>+public+c17afeb67dc591e4 at reviews.llvm.org>
Cc: Wenlei He <wenlei at fb.com>, Hongtao Yu <hoy at fb.com>, Lei Wang <wlei at fb.com>, davidxl at google.com <davidxl at google.com>, rajeshwarv at google.com <rajeshwarv at google.com>, llvm-commits at lists.llvm.org <llvm-commits at lists.llvm.org>, lxfind at gmail.com <lxfind at gmail.com>, Modi Mo <modimo at fb.com>, bhuvanendra.kumarn at amd.com <bhuvanendra.kumarn at amd.com>, yanliang.mu at intel.com <yanliang.mu at intel.com>, dougpuob at gmail.com <dougpuob at gmail.com>, michael.hliao at gmail.com <michael.hliao at gmail.com>, florian_hahn at apple.com <florian_hahn at apple.com>, david.green at arm.com <david.green at arm.com>, simon.moll at emea.nec.com <simon.moll at emea.nec.com>
Subject: Re: [PATCH] D112042 <https://reviews.llvm.org/D112042>: [llvm-profgen] Skip duplication factor outside of body sample computation

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D112042/new/

https://reviews.llvm.org/D112042