maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Memory intrinsic value profile optimization: Avoid divide by 0 

Summary:
Skip memops if the total value profiled count is 0, we can't correctly
scale up the counts and there is no point anyway.

Reviewers: davidxl

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D32624

llvm-svn: 301645
This commit is contained in:
Teresa Johnson 2017-04-28 14:30:54 +00:00
parent 7ae9419dc0
commit 51177295c4
2 changed files with 23 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
View File

@ -872,6 +872,10 @@ bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
if (ActualCount < MemOPCountThreshold)
return false;
// Skip if the total value profiled count is 0, in which case we can't
// scale up the counts properly (and there is no profitable transformation).
if (TotalCount == 0)
return false;
TotalCount = ActualCount;
if (MemOPScaleCount)

19
llvm/test/Transforms/PGOProfile/memop_size_opt_zero.ll Normal file
View File

@ -0,0 +1,19 @@
; Test to ensure the pgo memop optimization pass doesn't try to scale
; up a value profile with a 0 count, which would lead to divide by 0.
; RUN: opt < %s -passes=pgo-memop-opt -pgo-memop-count-threshold=1 -S | FileCheck %s --check-prefix=MEMOP_OPT
; RUN: opt < %s -pgo-memop-opt -pgo-memop-count-threshold=1 -S | FileCheck %s --check-prefix=MEMOP_OPT
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
define void @foo(i8* %dst, i8* %src, i64 %conv) !prof !0 {
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof !1
ret void
}
; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof !1
!0 = !{!"function_entry_count", i64 1}
!1 = !{!"VP", i32 1, i64 0, i64 1, i64 0, i64 2, i64 0, i64 3, i64 0, i64 9, i64 0, i64 4, i64 0, i64 5, i64 0, i64 6, i64 0, i64 7, i64 0, i64 8, i64 0}
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1)