mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-12-11 13:37:07 +00:00
51d4708437
PGO profile is usually more precise than sample profile. However, PGO profile needs to be collected from loadtest and loadtest may not be representative enough to the production workload. Sample profile collected from production can be used as a supplement -- for functions cold in loadtest but warm/hot in production, we can scale up the related function in PGO profile if the function is warm or hot in sample profile. The implementation contains changes in compiler side and llvm-profdata side. Given an instr profile and a sample profile, for a function cold in PGO profile but warm/hot in sample profile, llvm-profdata will either mark all the counters in the profile to be -1 or scale up the max count in the function to be above hot threshold, depending on the zero counter ratio in the profile. The assumption is if there are too many counters being zero in the function profile, the profile is more likely to cause harm than good, then llvm-profdata will mark all the counters to be -1 indicating the function is hot but the profile is unaccountable. In compiler side, if a function profile with all -1 counters is seen, the function entry count will be set to be above hot threshold but its internal profile will be dropped. In the long run, it may be useful to let compiler support using PGO profile and sample profile at the same time, but that requires more careful design and more substantial changes to make two profiles work seamlessly. The patch here serves as a simple intermediate solution. Differential Revision: https://reviews.llvm.org/D81981
38 lines
1.2 KiB
LLVM
38 lines
1.2 KiB
LLVM
; Supplement instr profile suppl-profile.proftext with sample profile
|
|
; sample-profile.proftext.
|
|
; RUN: llvm-profdata merge -instr -suppl-min-size-threshold=0 \
|
|
; RUN: -supplement-instr-with-sample=%p/Inputs/sample-profile.proftext \
|
|
; RUN: %S/Inputs/suppl-profile.proftext -o %t.profdata
|
|
; RUN: opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s
|
|
; RUN: opt < %s -passes=pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-linux-gnu"
|
|
|
|
; Check test_simple_for has a non-zero entry count and doesn't have any other
|
|
; prof metadata.
|
|
; CHECK: @test_simple_for(i32 %n) {{.*}} !prof ![[ENTRY_COUNT:[0-9]+]]
|
|
; CHECK-NOT: !prof !
|
|
; CHECK: ![[ENTRY_COUNT]] = !{!"function_entry_count", i64 540}
|
|
define i32 @test_simple_for(i32 %n) {
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond:
|
|
%i = phi i32 [ 0, %entry ], [ %inc1, %for.inc ]
|
|
%sum = phi i32 [ 1, %entry ], [ %inc, %for.inc ]
|
|
%cmp = icmp slt i32 %i, %n
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.body:
|
|
%inc = add nsw i32 %sum, 1
|
|
br label %for.inc
|
|
|
|
for.inc:
|
|
%inc1 = add nsw i32 %i, 1
|
|
br label %for.cond
|
|
|
|
for.end:
|
|
ret i32 %sum
|
|
}
|