RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-29 14:20:29 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[LoopSink] Add preheader to alias set

Browse Source 
This patch fixes PR39695.

The original LoopSink only considers memory alias in loop body. But PR39695 shows that instructions following sink candidate in preheader should also be checked. This is a conservative patch, it simply adds whole preheader block to alias set. It may lose some optimization opportunity, but I think that is very rare because: 1 in the most common case st/ld to the same address, the load should already be optimized away. 2 usually preheader is not very large. 

Differential Revision: https://reviews.llvm.org/D54659

llvm-svn: 347325
This commit is contained in:
Guozhi Wei 2018-11-20 16:49:07 +00:00
parent 18470cf8db
commit 07981cc027
2 changed files with 38 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
lib/Transforms/Scalar/LoopSink.cpp
View File

@ -280,6 +280,7 @@ static bool sinkLoopInvariantInstructions(Loop &L, AAResults &AA, LoopInfo &LI,
// Compute alias set.
for (BasicBlock *BB : L.blocks())
CurAST.add(*BB);
CurAST.add(*Preheader);
// Sort loop's basic blocks by frequency
SmallVector<BasicBlock *, 10> ColdLoopBBs;

37
test/Transforms/LICM/loopsink-pr39695.ll Normal file
View File

@ -0,0 +1,37 @@
; RUN: opt -S -loop-sink < %s | FileCheck %s
; The load instruction should not be sunk into following loop.
; CHECK: @foo
; CHECK-NEXT: entry
; CHECK-NEXT: %ptr = load i8*, i8** %pp, align 8
; CHECK-NEXT: store i8* null, i8** %pp, align 8
define i32 @foo(i32 %n, i8** %pp) !prof !0 {
entry:
%ptr = load i8*, i8** %pp, align 8
store i8* null, i8** %pp, align 8
br label %for.cond
for.cond: ; preds = %for.body, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%cmp = icmp ult i32 %i.0, %n
br i1 %cmp, label %for.body, label %for.end, !prof !1
for.body: ; preds = %for.cond
%0 = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i8, i8* %ptr, i64 %0
%1 = load i8, i8* %arrayidx, align 1
%or19 = call i8 @llvm.bitreverse.i8(i8 %1)
%v = sext i8 %or19 to i32
%inc = add i32 %i.0, %v
br label %for.cond
for.end: ; preds = %for.cond
ret i32 %i.0
}
declare i8 @llvm.bitreverse.i8(i8) #0
attributes #0 = { nounwind readnone speculatable }
!0 = !{!"function_entry_count", i64 1}
!1 = !{!"branch_weights", i32 1, i32 2000}