forked from OSchip/llvm-project
[DAGCombiner] Fix load-store forwarding of indexed loads.
Summary: Handle extra output from index loads in cases where we wish to forward a load value directly from a preceeding store. Fixes PR39571. Reviewers: peter.smith, rengolin Subscribers: javed.absar, hiraditya, arphaman, llvm-commits Differential Revision: https://reviews.llvm.org/D54265 llvm-svn: 346654
This commit is contained in:
parent
ac7c4f1db3
commit
a395e2df56
|
@ -12866,6 +12866,20 @@ SDValue DAGCombiner::ForwardStoreValueToDirectLoad(LoadSDNode *LD) {
|
|||
bool STCoversLD =
|
||||
(Offset >= 0) &&
|
||||
(Offset * 8 + LDMemType.getSizeInBits() <= STMemType.getSizeInBits());
|
||||
|
||||
auto ReplaceLd = [&](LoadSDNode *LD, SDValue Val, SDValue Chain) -> SDValue {
|
||||
if (LD->isIndexed()) {
|
||||
bool IsSub = (LD->getAddressingMode() == ISD::PRE_DEC ||
|
||||
LD->getAddressingMode() == ISD::POST_DEC);
|
||||
unsigned Opc = IsSub ? ISD::SUB : ISD::ADD;
|
||||
SDValue Idx = DAG.getNode(Opc, SDLoc(LD), LD->getOperand(1).getValueType(),
|
||||
LD->getOperand(1), LD->getOperand(2));
|
||||
SDValue Ops[] = {Val, Idx, Chain};
|
||||
return CombineTo(LD, Ops, 3);
|
||||
}
|
||||
return CombineTo(LD, Val, Chain);
|
||||
};
|
||||
|
||||
if (!STCoversLD)
|
||||
return SDValue();
|
||||
|
||||
|
@ -12873,7 +12887,7 @@ SDValue DAGCombiner::ForwardStoreValueToDirectLoad(LoadSDNode *LD) {
|
|||
if (Offset == 0 && LDType == STType && STMemType == LDMemType) {
|
||||
// Simple case: Direct non-truncating forwarding
|
||||
if (LDType.getSizeInBits() == LDMemType.getSizeInBits())
|
||||
return CombineTo(LD, ST->getValue(), Chain);
|
||||
return ReplaceLd(LD, ST->getValue(), Chain);
|
||||
// Can we model the truncate and extension with an and mask?
|
||||
if (STType.isInteger() && LDMemType.isInteger() && !STType.isVector() &&
|
||||
!LDMemType.isVector() && LD->getExtensionType() != ISD::SEXTLOAD) {
|
||||
|
@ -12883,7 +12897,7 @@ SDValue DAGCombiner::ForwardStoreValueToDirectLoad(LoadSDNode *LD) {
|
|||
STMemType.getSizeInBits()),
|
||||
SDLoc(ST), STType);
|
||||
auto Val = DAG.getNode(ISD::AND, SDLoc(LD), LDType, ST->getValue(), Mask);
|
||||
return CombineTo(LD, Val, Chain);
|
||||
return ReplaceLd(LD, Val, Chain);
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -12908,7 +12922,7 @@ SDValue DAGCombiner::ForwardStoreValueToDirectLoad(LoadSDNode *LD) {
|
|||
}
|
||||
if (!extendLoadedValueToExtension(LD, Val))
|
||||
continue;
|
||||
return CombineTo(LD, Val, Chain);
|
||||
return ReplaceLd(LD, Val, Chain);
|
||||
} while (false);
|
||||
|
||||
// On failure, cleanup dead nodes we may have created.
|
||||
|
|
|
@ -0,0 +1,33 @@
|
|||
; RUN: llc < %s -mtriple armv4t-unknown-linux-gnueabi -mattr=+strict-align
|
||||
|
||||
; Avoid crash from forwarding indexed-loads back to store.
|
||||
%struct.anon = type { %struct.ma*, %struct.mb }
|
||||
%struct.ma = type { i8 }
|
||||
%struct.mb = type { i8, i8 }
|
||||
%struct.anon.0 = type { %struct.anon.1 }
|
||||
%struct.anon.1 = type { %struct.ds }
|
||||
%struct.ds = type <{ i8, %union.ie }>
|
||||
%union.ie = type { %struct.ib }
|
||||
%struct.ib = type { i8, i8, i16 }
|
||||
|
||||
@a = common dso_local local_unnamed_addr global %struct.anon* null, align 4
|
||||
@b = common dso_local local_unnamed_addr global %struct.anon.0 zeroinitializer, align 1
|
||||
|
||||
; Function Attrs: norecurse nounwind
|
||||
define dso_local void @func() local_unnamed_addr {
|
||||
entry:
|
||||
%0 = load %struct.anon*, %struct.anon** @a, align 4
|
||||
%ad = getelementptr inbounds %struct.anon, %struct.anon* %0, i32 0, i32 0
|
||||
%1 = load %struct.ma*, %struct.ma** %ad, align 4
|
||||
%c.sroa.0.0..sroa_idx = getelementptr inbounds %struct.ma, %struct.ma* %1, i32 0, i32 0
|
||||
%c.sroa.0.0.copyload = load i8, i8* %c.sroa.0.0..sroa_idx, align 1
|
||||
%cb = getelementptr inbounds %struct.anon, %struct.anon* %0, i32 0, i32 1
|
||||
%band = getelementptr inbounds %struct.anon, %struct.anon* %0, i32 0, i32 1, i32 1
|
||||
store i8 %c.sroa.0.0.copyload, i8* %band, align 4
|
||||
store i8 6, i8* getelementptr inbounds (%struct.anon.0, %struct.anon.0* @b, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0), align 1
|
||||
store i8 2, i8* getelementptr inbounds (%struct.anon.0, %struct.anon.0* @b, i32 0, i32 0, i32 0, i32 1, i32 0, i32 1), align 1
|
||||
%2 = bitcast %struct.mb* %cb to i32*
|
||||
%3 = load i32, i32* bitcast (i8* getelementptr inbounds (%struct.anon.0, %struct.anon.0* @b, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0) to i32*), align 1
|
||||
store i32 %3, i32* %2, align 1
|
||||
ret void
|
||||
}
|
Loading…
Reference in New Issue