mirror of
https://github.com/llvm/llvm-project.git
synced 2025-04-30 01:56:06 +00:00

This change allows merging and trimming cold context profile in llvm-profgen to solve profile size bloat problem. Currently when the profile's total sample is below threshold(supported by a switch), it will be considered cold and merged into a base context-less profile, which will at least keep the profile quality as good as the baseline(non-cs). For example, two input profiles: [main @ foo @ bar]:60 [main @ bar]:50 Under threshold = 100, the two profiles will be merge into one with the base context, get result: [bar]:110 Added two switches: `--csprof-cold-thres=<value>`: Specified the total samples threshold for a context profile to be considered cold, with 100 being the default. Any cold context profiles will be merged into context-less base profile by default. `--csprof-keep-cold`: Force profile generation to keep cold context profiles instead of dropping them. By default, any cold context will not be written to output profile. Results: Though not yet evaluating it with the latest CSSPGO, our internal branch shows neutral on performance but significantly reduce the profile size. Detailed evaluation on llvm-profgen with CSSPGO will come later. Differential Revision: https://reviews.llvm.org/D94111
170 lines
6.6 KiB
Plaintext
170 lines
6.6 KiB
Plaintext
; Firstly test uncompression(--compress-recursion=0)
|
|
; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t --compress-recursion=0 --csprof-cold-thres=0
|
|
; RUN: FileCheck %s --input-file %t -check-prefix=CHECK-UNCOMPRESS
|
|
; RUN: llvm-profgen --perfscript=%S/Inputs/recursion-compression-pseudoprobe.perfscript --binary=%S/Inputs/recursion-compression-pseudoprobe.perfbin --output=%t --show-unwinder-output --csprof-cold-thres=0 | FileCheck %s --check-prefix=CHECK-UNWINDER
|
|
; RUN: FileCheck %s --input-file %t
|
|
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6 @ fa]:4:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 3: 1
|
|
; CHECK-UNCOMPRESS: 4: 1
|
|
; CHECK-UNCOMPRESS: 7: 1 fb:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 120515930909
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:6 @ fa:8 @ fa]:4:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 3: 1
|
|
; CHECK-UNCOMPRESS: 4: 1
|
|
; CHECK-UNCOMPRESS: 7: 1 fb:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 120515930909
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:6 @ fa]:4:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 3: 1
|
|
; CHECK-UNCOMPRESS: 5: 1
|
|
; CHECK-UNCOMPRESS: 8: 1 fa:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 120515930909
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6 @ fa:7 @ fb]:3:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 3: 1
|
|
; CHECK-UNCOMPRESS: 6: 1 fa:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 72617220756
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb]:3:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 3: 1
|
|
; CHECK-UNCOMPRESS: 6: 1 fa:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 72617220756
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb]:3:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 3: 1
|
|
; CHECK-UNCOMPRESS: 6: 1 fa:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 72617220756
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb]:3:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 2: 1
|
|
; CHECK-UNCOMPRESS: 5: 1 fb:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 72617220756
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb]:3:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 2: 1
|
|
; CHECK-UNCOMPRESS: 5: 1 fb:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 72617220756
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb]:3:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 2: 1
|
|
; CHECK-UNCOMPRESS: 5: 1 fb:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 72617220756
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6 @ fa:7 @ fb:6 @ fa]:2:1
|
|
; CHECK-UNCOMPRESS: 1: 1
|
|
; CHECK-UNCOMPRESS: 3: 1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 120515930909
|
|
; CHECK-UNCOMPRESS: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:5 @ fb:5 @ fb:5 @ fb]:1:0
|
|
; CHECK-UNCOMPRESS: 5: 1 fb:1
|
|
; CHECK-UNCOMPRESS: !CFGChecksum: 72617220756
|
|
|
|
|
|
; CHECK: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb]:13:4
|
|
; CHECK: 1: 4
|
|
; CHECK: 2: 3
|
|
; CHECK: 3: 1
|
|
; CEHCK: 5: 4 fb:4
|
|
; CHECK: 6: 1 fa:1
|
|
; CHECK !CFGChecksum: 72617220756
|
|
; CHECK: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6 @ fa]:6:2
|
|
; CHECK: 1: 2
|
|
; CHECK: 3: 2
|
|
; CHECK: 4: 1
|
|
; CHECK: 7: 1 fb:1
|
|
; CHECK: !CFGChecksum: 120515930909
|
|
; CHECK: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa]:4:1
|
|
; CHECK: 1: 1
|
|
; CHECK: 3: 1
|
|
; CHECK: 4: 1
|
|
; CHECK: 7: 1 fb:1
|
|
; CHECK: !CFGChecksum: 120515930909
|
|
; CHECK: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa]:4:1
|
|
; CHECK: 1: 1
|
|
; CHECK: 3: 1
|
|
; CHECK: 5: 1
|
|
; CHECK: 8: 1 fa:1
|
|
; CHECK: !CFGChecksum: 120515930909
|
|
; CHECK: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6 @ fa:7 @ fb]:3:1
|
|
; CHECK: 1: 1
|
|
; CHECK: 3: 1
|
|
; CHECK: 6: 1 fa:1
|
|
; CHECK: !CFGChecksum: 72617220756
|
|
; CHECK: [main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb]:3:1
|
|
; CHECK: 1: 1
|
|
; CHECK: 3: 1
|
|
; CHECK: 6: 1 fa:1
|
|
; CHECK: !CFGChecksum: 72617220756
|
|
|
|
|
|
; CHECK-UNWINDER: Binary(recursion-compression-pseudoprobe.perfbin)'s Range Counter:
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5
|
|
; CHECK-UNWINDER: (7a0, 7a7): 1
|
|
; CHECK-UNWINDER: (7a0, 7ab): 3
|
|
; CHECK-UNWINDER: (7b2, 7b5): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6
|
|
; CHECK-UNWINDER: (7c0, 7d4): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8
|
|
; CHECK-UNWINDER: (7c0, 7cd): 1
|
|
; CHECK-UNWINDER: (7db, 7e0): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa:7
|
|
; CHECK-UNWINDER: (7a0, 7a7): 1
|
|
; CHECK-UNWINDER: (7b2, 7b5): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6
|
|
; CHECK-UNWINDER: (7c0, 7cd): 2
|
|
; CHECK-UNWINDER: (7db, 7e0): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6 @ fa:7
|
|
; CHECK-UNWINDER: (7a0, 7a7): 1
|
|
; CHECK-UNWINDER: (7b2, 7b5): 1
|
|
|
|
; CHECK-UNWINDER: Binary(recursion-compression-pseudoprobe.perfbin)'s Branch Counter:
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5
|
|
; CHECK-UNWINDER: (7a7, 7b2): 1
|
|
; CHECK-UNWINDER: (7ab, 7a0): 4
|
|
; CHECK-UNWINDER: (7b5, 7c0): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6
|
|
; CHECK-UNWINDER: (7d4, 7c0): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8
|
|
; CHECK-UNWINDER: (7cd, 7db): 1
|
|
; CHECK-UNWINDER: (7e0, 7a0): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa:7
|
|
; CHECK-UNWINDER: (7a7, 7b2): 1
|
|
; CHECK-UNWINDER: (7b5, 7c0): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6
|
|
; CHECK-UNWINDER: (7cd, 7db): 2
|
|
; CHECK-UNWINDER: (7e0, 7a0): 1
|
|
; CHECK-UNWINDER: main:2 @ foo:5 @ fa:8 @ fa:7 @ fb:5 @ fb:6 @ fa:8 @ fa:7 @ fb:6 @ fa:7
|
|
; CHECK-UNWINDER: (7a7, 7b2): 1
|
|
; CHECK-UNWINDER: (7b5, 7c0): 1
|
|
|
|
|
|
; clang -O3 -fexperimental-new-pass-manager -fuse-ld=lld -fpseudo-probe-for-profiling
|
|
; -fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -Xclang -mdisable-tail-calls
|
|
; -g test.c -o a.out
|
|
|
|
#include <stdio.h>
|
|
|
|
int fb(int n) {
|
|
if(n > 10) return fb(n / 2);
|
|
return fa(n - 1);
|
|
}
|
|
|
|
int fa(int n) {
|
|
if(n < 2) return n;
|
|
if(n % 2) return fb(n - 1);
|
|
return fa(n - 1);
|
|
}
|
|
|
|
void foo() {
|
|
int s, i = 0;
|
|
while (i++ < 10000)
|
|
s += fa(i);
|
|
printf("sum is %d\n", s);
|
|
}
|
|
|
|
int main() {
|
|
foo();
|
|
return 0;
|
|
}
|