[PATCH] D89085: [llvm] Update default cutoff threshold for machine function splitter.

[Snehasish Kumar via Phabricator via llvm-commits]

snehasish created this revision.
snehasish added a reviewer: tmsriram.
Herald added subscribers: llvm-commits, hiraditya.
Herald added a project: LLVM.
snehasish requested review of this revision.

Based on internal testing at Google we found that setting the profile
summary cutoff threshold to 999950 yields the best results in terms of
itlb and icache metrics (as observed on Intel CPUs).

*default* = Split out code if no profile count available for block
*size-%*  = The fraction of bytes split out of .text and .text.hot
*itlb*    = Misses per kilo instructions (MPKI) for itlb
*icache*  = Misses per kilo instructions (MPKI) for L1 <https://reviews.llvm.org/L1> icache

Search1

| cutoff  | size-%  | itlb     | icache  |
| ------- | ------- | -------- | ------- |
| default | 42.5861 | 0.0822151      | 2.46363 |
| 999999  | 44.9350 | 0.0767194      | 2.44416 |
| 999950  | 50.0660 | 0.075744 | 2.4091  |
| 999500  | 56.9158 | 0.082564 | 2.4188  |
| 995000  | 63.8625 | 0.0814927      | 2.42832 |
| 990000  | 71.7314 | 0.106906 | 2.57785 |
|

Search2

| cutoff  | size-% | itlb     | icache  |
| ------- | ------ | -------- | ------- |
| default | 2.8845 | 0.626712 | 4.73245 |
| 999999  | 3.3291 | 0.602309 | 4.70045 |
| 999950  | 3.8577 | 0.587842 | 4.71632 |
| 999500  | 4.4170 | 0.63577  | 4.68351 |
| 995000  | 5.1020 | 0.657969 | 4.82272 |
| 990000  | 5.7153 | 0.719122 | 5.39496 |


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D89085

Files:
  llvm/lib/CodeGen/MachineFunctionSplitter.cpp
  llvm/test/CodeGen/X86/machine-function-splitter.ll


Index: llvm/test/CodeGen/X86/machine-function-splitter.ll
===================================================================
--- llvm/test/CodeGen/X86/machine-function-splitter.ll
+++ llvm/test/CodeGen/X86/machine-function-splitter.ll
@@ -1,5 +1,5 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -split-machine-functions | FileCheck %s -check-prefix=MFS-DEFAULTS
-; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -split-machine-functions -mfs-count-threshold=2000 | FileCheck %s --dump-input=always -check-prefix=MFS-OPTS1
+; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -split-machine-functions -mfs-psi-cutoff=0 -mfs-count-threshold=2000 | FileCheck %s --dump-input=always -check-prefix=MFS-OPTS1
 ; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -split-machine-functions -mfs-psi-cutoff=950000 | FileCheck %s -check-prefix=MFS-OPTS2
 
 define void @foo1(i1 zeroext %0) nounwind !prof !14 !section_prefix !15 {
Index: llvm/lib/CodeGen/MachineFunctionSplitter.cpp
===================================================================
--- llvm/lib/CodeGen/MachineFunctionSplitter.cpp
+++ llvm/lib/CodeGen/MachineFunctionSplitter.cpp
@@ -43,7 +43,7 @@
     PercentileCutoff("mfs-psi-cutoff",
                      cl::desc("Percentile profile summary cutoff used to "
                               "determine cold blocks. Unused if set to zero."),
-                     cl::init(0), cl::Hidden);
+                     cl::init(999950), cl::Hidden);
 
 static cl::opt<unsigned> ColdCountThreshold(
     "mfs-count-threshold",


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D89085.297087.patch
Type: text/x-patch
Size: 1535 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20201009/7eb746d6/attachment.bin>