RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2024-12-29 16:04:33 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix for PR20059 (instcombine reorders shufflevector after instruction that may trap)

Browse Source 
In PR20059 ( http://llvm.org/pr20059 ), instcombine eliminates shuffles that are necessary before performing an operation that can trap (srem).

This patch calls isSafeToSpeculativelyExecute() and bails out of the optimization in SimplifyVectorOp() if needed.

Differential Revision: http://reviews.llvm.org/D4424



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@212629 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel 2014-07-09 16:34:54 +00:00
parent 6a6556695e
commit 296cb7b128
2 changed files with 38 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lib/Transforms/InstCombine/InstructionCombining.cpp
View File

@ -42,6 +42,7 @@
#include "llvm/Analysis/ConstantFolding.h" #include "llvm/Analysis/ConstantFolding.h"
#include "llvm/Analysis/InstructionSimplify.h" #include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/MemoryBuiltins.h" #include "llvm/Analysis/MemoryBuiltins.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/CFG.h" #include "llvm/IR/CFG.h"
#include "llvm/IR/DataLayout.h" #include "llvm/IR/DataLayout.h"
#include "llvm/IR/GetElementPtrTypeIterator.h" #include "llvm/IR/GetElementPtrTypeIterator.h"
@ -1195,6 +1196,11 @@ static Value *CreateBinOpAsGiven(BinaryOperator &Inst, Value *LHS, Value *RHS,
Value *InstCombiner::SimplifyVectorOp(BinaryOperator &Inst) { Value *InstCombiner::SimplifyVectorOp(BinaryOperator &Inst) {
if (!Inst.getType()->isVectorTy()) return nullptr; if (!Inst.getType()->isVectorTy()) return nullptr;
// It may not be safe to reorder shuffles and things like div, urem, etc.
// because we may trap when executing those ops on unknown vector elements.
// See PR20059.
if (!isSafeToSpeculativelyExecute(&Inst)) return nullptr;
unsigned VWidth = cast<VectorType>(Inst.getType())->getNumElements(); unsigned VWidth = cast<VectorType>(Inst.getType())->getNumElements();
Value *LHS = Inst.getOperand(0), *RHS = Inst.getOperand(1); Value *LHS = Inst.getOperand(0), *RHS = Inst.getOperand(1);
assert(cast<VectorType>(LHS->getType())->getNumElements() == VWidth); assert(cast<VectorType>(LHS->getType())->getNumElements() == VWidth);

32
test/Transforms/InstCombine/pr20059.ll Normal file
View File

@ -0,0 +1,32 @@
; RUN: opt -S -instcombine < %s | FileCheck %s
; In PR20059 ( http://llvm.org/pr20059 ), shufflevector operations are reordered/removed
; for an srem operation. This is not a valid optimization because it may cause a trap
; on div-by-zero.
; CHECK-LABEL: @do_not_reorder
; CHECK: %splat1 = shufflevector <4 x i32> %p1, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %splat2 = shufflevector <4 x i32> %p2, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %retval = srem <4 x i32> %splat1, %splat2
define <4 x i32> @do_not_reorder(<4 x i32> %p1, <4 x i32> %p2) {
%splat1 = shufflevector <4 x i32> %p1, <4 x i32> undef, <4 x i32> zeroinitializer
%splat2 = shufflevector <4 x i32> %p2, <4 x i32> undef, <4 x i32> zeroinitializer
%retval = srem <4 x i32> %splat1, %splat2
ret <4 x i32> %retval
}
; RUN: opt -S -instcombine < %s | FileCheck %s
; In PR20059 ( http://llvm.org/pr20059 ), shufflevector operations are reordered/removed
; for an srem operation. This is not a valid optimization because it may cause a trap
; on div-by-zero.
; CHECK-LABEL: @do_not_reorder
; CHECK: %splat1 = shufflevector <4 x i32> %p1, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %splat2 = shufflevector <4 x i32> %p2, <4 x i32> undef, <4 x i32> zeroinitializer
; CHECK-NEXT: %retval = srem <4 x i32> %splat1, %splat2
define <4 x i32> @do_not_reorder(<4 x i32> %p1, <4 x i32> %p2) {
%splat1 = shufflevector <4 x i32> %p1, <4 x i32> undef, <4 x i32> zeroinitializer
%splat2 = shufflevector <4 x i32> %p2, <4 x i32> undef, <4 x i32> zeroinitializer
%retval = srem <4 x i32> %splat1, %splat2
ret <4 x i32> %retval
}