[X86] Keep dependencies when constructing loads in combineStore

Summary:
Preserve chain dependecies between old and new loads constructed to
prevent loads from reordering below later stores.

Fixes PR34088.

Reviewers: craig.topper, spatel, RKSimon, efriedma

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D36528

llvm-svn: 310604
This commit is contained in:
Nirav Dave 2017-08-10 15:12:32 +00:00
parent 6470011e9c
commit 926e2d39bf
4 changed files with 61 additions and 11 deletions

View File

@ -1222,8 +1222,9 @@ public:
/// If an existing load has uses of its chain, create a token factor node with
/// that chain and the new memory node's chain and update users of the old
/// chain to the token factor. This ensures that the new memory node will have
/// the same relative memory dependency position as the old load.
void makeEquivalentMemoryOrdering(LoadSDNode *Old, SDValue New);
/// the same relative memory dependency position as the old load. Returns the
/// new merged load chain.
SDValue makeEquivalentMemoryOrdering(LoadSDNode *Old, SDValue New);
/// Topological-sort the AllNodes list and a
/// assign a unique node id for each node in the DAG based on their

View File

@ -7339,22 +7339,23 @@ void SelectionDAG::TransferDbgValues(SDValue From, SDValue To) {
AddDbgValue(I, ToNode, false);
}
void SelectionDAG::makeEquivalentMemoryOrdering(LoadSDNode *OldLoad,
SDValue NewMemOp) {
SDValue SelectionDAG::makeEquivalentMemoryOrdering(LoadSDNode *OldLoad,
SDValue NewMemOp) {
assert(isa<MemSDNode>(NewMemOp.getNode()) && "Expected a memop node");
if (!OldLoad->hasAnyUseOfValue(1))
return;
// The new memory operation must have the same position as the old load in
// terms of memory dependency. Create a TokenFactor for the old load and new
// memory operation and update uses of the old load's output chain to use that
// TokenFactor.
SDValue OldChain = SDValue(OldLoad, 1);
SDValue NewChain = SDValue(NewMemOp.getNode(), 1);
if (!OldLoad->hasAnyUseOfValue(1))
return NewChain;
SDValue TokenFactor =
getNode(ISD::TokenFactor, SDLoc(OldLoad), MVT::Other, OldChain, NewChain);
ReplaceAllUsesOfValueWith(OldChain, TokenFactor);
UpdateNodeOperands(TokenFactor.getNode(), OldChain, NewChain);
return TokenFactor;
}
//===----------------------------------------------------------------------===//

View File

@ -33349,7 +33349,8 @@ static SDValue combineStore(SDNode *N, SelectionDAG &DAG,
SDValue NewLd = DAG.getLoad(LdVT, LdDL, Ld->getChain(), Ld->getBasePtr(),
Ld->getPointerInfo(), Ld->getAlignment(),
Ld->getMemOperand()->getFlags());
SDValue NewChain = NewLd.getValue(1);
// Make sure new load is placed in same chain order.
SDValue NewChain = DAG.makeEquivalentMemoryOrdering(Ld, NewLd);
if (TokenFactorIndex >= 0) {
Ops.push_back(NewChain);
NewChain = DAG.getNode(ISD::TokenFactor, LdDL, MVT::Other, Ops);
@ -33370,11 +33371,12 @@ static SDValue combineStore(SDNode *N, SelectionDAG &DAG,
Ld->getPointerInfo().getWithOffset(4),
MinAlign(Ld->getAlignment(), 4),
Ld->getMemOperand()->getFlags());
// Make sure new loads are placed in same chain order.
SDValue NewChain = DAG.makeEquivalentMemoryOrdering(Ld, LoLd);
NewChain = DAG.makeEquivalentMemoryOrdering(Ld, HiLd);
SDValue NewChain = LoLd.getValue(1);
if (TokenFactorIndex >= 0) {
Ops.push_back(LoLd);
Ops.push_back(HiLd);
Ops.push_back(NewChain);
NewChain = DAG.getNode(ISD::TokenFactor, LdDL, MVT::Other, Ops);
}

View File

@ -0,0 +1,46 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown -mcpu=pentium4 | FileCheck %s
%struct.Foo = type { i32, %struct.Bar }
%struct.Bar = type { i32, %struct.Buffer, i32 }
%struct.Buffer = type { i8*, i32 }
; This test checks that the load of store %2 is not dropped.
;
define i32 @pr34088() local_unnamed_addr {
; CHECK-LABEL: pr34088:
; CHECK: # BB#0: # %entry
; CHECK-NEXT: pushl %ebp
; CHECK-NEXT: .Lcfi0:
; CHECK-NEXT: .cfi_def_cfa_offset 8
; CHECK-NEXT: .Lcfi1:
; CHECK-NEXT: .cfi_offset %ebp, -8
; CHECK-NEXT: movl %esp, %ebp
; CHECK-NEXT: .Lcfi2:
; CHECK-NEXT: .cfi_def_cfa_register %ebp
; CHECK-NEXT: andl $-16, %esp
; CHECK-NEXT: subl $32, %esp
; CHECK-NEXT: xorps %xmm0, %xmm0
; CHECK-NEXT: movaps {{.*#+}} xmm1 = [205,205,205,205,205,205,205,205,205,205,205,205,205,205,205,205]
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: movaps %xmm0, (%esp)
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT: movaps %xmm1, (%esp)
; CHECK-NEXT: movl $-842150451, {{[0-9]+}}(%esp) # imm = 0xCDCDCDCD
; CHECK-NEXT: movsd %xmm0, {{[0-9]+}}(%esp)
; CHECK-NEXT: movl %ebp, %esp
; CHECK-NEXT: popl %ebp
; CHECK-NEXT: retl
entry:
%foo = alloca %struct.Foo, align 4
%0 = bitcast %struct.Foo* %foo to i8*
call void @llvm.memset.p0i8.i32(i8* nonnull %0, i8 0, i32 20, i32 4, i1 false)
%buffer1 = getelementptr inbounds %struct.Foo, %struct.Foo* %foo, i32 0, i32 1, i32 1
%1 = bitcast %struct.Buffer* %buffer1 to i64*
%2 = load i64, i64* %1, align 4
call void @llvm.memset.p0i8.i32(i8* nonnull %0, i8 -51, i32 20, i32 4, i1 false)
store i64 %2, i64* %1, align 4
ret i32 0
}
declare void @llvm.memset.p0i8.i32(i8* nocapture writeonly, i8, i32, i32, i1)