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

[gvn] PRE needs to skip convergent intrinsics/calls. 

- As convergent intrinsics/calls could only be moved to
  control-equivalent blocks, or more precisely the same divergent
  branch, PRE needs to skip them.

Differential Revision: https://reviews.llvm.org/D90391
This commit is contained in:
Michael Liao 2020-10-30 10:55:04 -04:00
parent 3d31adaec4
commit c82403d025
2 changed files with 42 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Transforms/Scalar/GVN.cpp
View File

@ -2460,10 +2460,14 @@ bool GVN::performScalarPRE(Instruction *CurInst) {
if (isa<GetElementPtrInst>(CurInst))
return false;
// We don't currently value number ANY inline asm calls.
if (auto *CallB = dyn_cast<CallBase>(CurInst))
if (auto *CallB = dyn_cast<CallBase>(CurInst)) {
// We don't currently value number ANY inline asm calls.
if (CallB->isInlineAsm())
return false;
// Don't do PRE on convergent calls.
if (CallB->isConvergent())
return false;
}
uint32_t ValNo = VN.lookup(CurInst);

36
llvm/test/Transforms/GVN/pre-skip-convergent.ll Normal file
View File

@ -0,0 +1,36 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -gvn -o - %s | FileCheck %s
; RUN: opt -S -passes=gvn -o - %s | FileCheck %s
define i32 @foo(i1 %cond, i32* %q, i32* %p) {
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[V0:%.*]] = call i32 @llvm.convergent(i32 0)
; CHECK-NEXT: store i32 [[V0]], i32* [[Q:%.*]], align 4
; CHECK-NEXT: br i1 [[COND:%.*]], label [[PRE:%.*]], label [[MERGE:%.*]]
; CHECK: pre:
; CHECK-NEXT: [[T0:%.*]] = load i32, i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[MERGE]]
; CHECK: merge:
; CHECK-NEXT: [[M0:%.*]] = phi i32 [ [[T0]], [[PRE]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[R0:%.*]] = call i32 @llvm.convergent(i32 [[M0]])
; CHECK-NEXT: ret i32 [[R0]]
;
entry:
%v0 = call i32 @llvm.convergent(i32 0)
store i32 %v0, i32* %q
br i1 %cond, label %pre, label %merge
pre:
%t0 = load i32, i32* %p
br label %merge
merge:
%m0 = phi i32 [ %t0, %pre ], [ 0, %entry ]
%r0 = call i32 @llvm.convergent(i32 %m0)
ret i32 %r0
}
declare i32 @llvm.convergent(i32) #0
attributes #0 = { convergent nounwind readnone }