mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 12:41:49 +01:00
[SROA] Take advantage of separate alignments for memcpy source and destination
Summary: This change is part of step five in the series of changes to remove alignment argument from memcpy/memmove/memset in favour of alignment attributes. In particular, this changes the SROA pass to cease using the old getAlignment() & setAlignment() APIs of MemoryIntrinsic in favour of getting source & dest specific alignments through the new API. This allows us to enhance visitMemTransferInst to be more aggressive setting the alignment in memcpy calls that it creates, as well as to only change the alignment of a memcpy/memmove argument that it replaces. Steps: Step 1) Remove alignment parameter and create alignment parameter attributes for memcpy/memmove/memset. ( rL322965, rC322964, rL322963 ) Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. ( rL323597 ) Step 3) Update Clang to use the new IRBuilder API. ( rC323617 ) Step 4) Update Polly to use the new IRBuilder API. ( rL323618 ) Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use [get|set]DestAlignment() and [get|set]SourceAlignment() instead. ( rL323886, rL323891, rL324148, rL324273, rL324278, rL324384, rL324395, rL324402, rL324626, rL324642, rL324653, rL324654, rL324773, rL324774, rL324781, rL324784, rL324955, rL324960, rL325816 ) Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reference http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html Reviewers: chandlerc, bollu, efriedma Reviewed By: efriedma Subscribers: efriedma, eraman, llvm-commits Differential Revision: https://reviews.llvm.org/D42974 llvm-svn: 327398
This commit is contained in:
Daniel Neilson
parent
1b9cd38265
commit
e6d5325391
@ -2698,7 +2698,7 @@ private:
|
||||
assert(!IsSplit);
|
||||
assert(NewBeginOffset == BeginOffset);
|
||||
II.setDest(getNewAllocaSlicePtr(IRB, OldPtr->getType()));
|
||||
II.setAlignment(getSliceAlign());
|
||||
II.setDestAlignment(getSliceAlign());
|
||||
|
||||
deleteIfTriviallyDead(OldPtr);
|
||||
return false;
|
||||
@ -2819,13 +2819,13 @@ private:
|
||||
// update both source and dest of a single call.
|
||||
if (!IsSplittable) {
|
||||
Value *AdjustedPtr = getNewAllocaSlicePtr(IRB, OldPtr->getType());
|
||||
if (IsDest)
|
||||
if (IsDest) {
|
||||
II.setDest(AdjustedPtr);
|
||||
else
|
||||
II.setDestAlignment(SliceAlign);
|
||||
}
|
||||
else {
|
||||
II.setSource(AdjustedPtr);
|
||||
|
||||
if (II.getAlignment() > SliceAlign) {
|
||||
II.setAlignment(MinAlign(II.getAlignment(), SliceAlign));
|
||||
II.setSourceAlignment(SliceAlign);
|
||||
}
|
||||
|
||||
DEBUG(dbgs() << " to: " << II << "\n");
|
||||
@ -2878,8 +2878,10 @@ private:
|
||||
// Compute the relative offset for the other pointer within the transfer.
|
||||
unsigned IntPtrWidth = DL.getPointerSizeInBits(OtherAS);
|
||||
APInt OtherOffset(IntPtrWidth, NewBeginOffset - BeginOffset);
|
||||
unsigned OtherAlign = MinAlign(II.getAlignment() ? II.getAlignment() : 1,
|
||||
OtherOffset.zextOrTrunc(64).getZExtValue());
|
||||
unsigned OtherAlign =
|
||||
IsDest ? II.getSourceAlignment() : II.getDestAlignment();
|
||||
OtherAlign = MinAlign(OtherAlign ? OtherAlign : 1,
|
||||
OtherOffset.zextOrTrunc(64).getZExtValue());
|
||||
|
||||
if (EmitMemCpy) {
|
||||
// Compute the other pointer, folding as much as possible to produce
|
||||
@ -2891,9 +2893,22 @@ private:
|
||||
Type *SizeTy = II.getLength()->getType();
|
||||
Constant *Size = ConstantInt::get(SizeTy, NewEndOffset - NewBeginOffset);
|
||||
|
||||
CallInst *New = IRB.CreateMemCpy(
|
||||
IsDest ? OurPtr : OtherPtr, IsDest ? OtherPtr : OurPtr, Size,
|
||||
MinAlign(SliceAlign, OtherAlign), II.isVolatile());
|
||||
Value *DestPtr, *SrcPtr;
|
||||
unsigned DestAlign, SrcAlign;
|
||||
// Note: IsDest is true iff we're copying into the new alloca slice
|
||||
if (IsDest) {
|
||||
DestPtr = OurPtr;
|
||||
DestAlign = SliceAlign;
|
||||
SrcPtr = OtherPtr;
|
||||
SrcAlign = OtherAlign;
|
||||
} else {
|
||||
DestPtr = OtherPtr;
|
||||
DestAlign = OtherAlign;
|
||||
SrcPtr = OurPtr;
|
||||
SrcAlign = SliceAlign;
|
||||
}
|
||||
CallInst *New = IRB.CreateMemCpy(DestPtr, DestAlign, SrcPtr, SrcAlign,
|
||||
Size, II.isVolatile());
|
||||
if (AATags)
|
||||
New->setAAMetadata(AATags);
|
||||
DEBUG(dbgs() << " to: " << *New << "\n");
|
||||
|
||||
@ -65,7 +65,7 @@ L2:
|
||||
ret i64 %Z
|
||||
}
|
||||
|
||||
define void @test3(i8* %dst, i8* %src) {
|
||||
define void @test3(i8* %dst, i8* align 8 %src) {
|
||||
; CHECK-LABEL: @test3(
|
||||
|
||||
entry:
|
||||
@ -80,9 +80,9 @@ entry:
|
||||
; CHECK-NEXT: %[[test3_a7:.*]] = alloca [85 x i8]
|
||||
|
||||
%b = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 0
|
||||
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 300, i1 false), !tbaa !0
|
||||
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* align 8 %src, i32 300, i1 false), !tbaa !0
|
||||
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a1]], i64 0, i64 0
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %src, i32 42, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 8 %src, i32 42, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 42
|
||||
; CHECK-NEXT: %[[test3_r1:.*]] = load i8, i8* %[[gep]], {{.*}}, !tbaa [[TAG_0]]
|
||||
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 43
|
||||
@ -90,18 +90,18 @@ entry:
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 99, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 142
|
||||
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [16 x i8], [16 x i8]* %[[test3_a3]], i64 0, i64 0
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 16, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 2 %[[gep_src]], i32 16, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 158
|
||||
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [42 x i8], [42 x i8]* %[[test3_a4]], i64 0, i64 0
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 42, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 2 %[[gep_src]], i32 42, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 200
|
||||
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 0
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 8 %[[gep_src]], i32 7, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds i8, i8* %src, i64 207
|
||||
; CHECK-NEXT: %[[test3_r2:.*]] = load i8, i8* %[[gep]], {{.*}}, !tbaa [[TAG_0]]
|
||||
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 208
|
||||
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 0
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 7, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 8 %[[gep_src]], i32 7, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
; CHECK-NEXT: %[[gep_src:.*]] = getelementptr inbounds i8, i8* %src, i64 215
|
||||
; CHECK-NEXT: %[[gep_dst:.*]] = getelementptr inbounds [85 x i8], [85 x i8]* %[[test3_a7]], i64 0, i64 0
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[gep_dst]], i8* align 1 %[[gep_src]], i32 85, {{.*}}), !tbaa [[TAG_0:!.*]]
|
||||
@ -778,7 +778,7 @@ define void @test18(i8* %src, i8* %dst, i32 %size) {
|
||||
; CHECK-NEXT: %[[srccast1:.*]] = bitcast i8* %[[srcgep1]] to i32*
|
||||
; CHECK-NEXT: %[[srcload:.*]] = load i32, i32* %[[srccast1]], {{.*}}, !tbaa [[TAG_0]]
|
||||
; CHECK-NEXT: %[[agep1:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %[[agep1]], i8* %src, i32 %size, {{.*}}), !tbaa [[TAG_3]]
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 %[[agep1]], i8* %src, i32 %size, {{.*}}), !tbaa [[TAG_3]]
|
||||
; CHECK-NEXT: %[[agep2:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0
|
||||
; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 %[[agep2]], i8 42, i32 %size, {{.*}}), !tbaa [[TAG_5]]
|
||||
; CHECK-NEXT: %[[dstcast1:.*]] = bitcast i8* %dst to i32*
|
||||
@ -787,7 +787,7 @@ define void @test18(i8* %src, i8* %dst, i32 %size) {
|
||||
; CHECK-NEXT: %[[dstcast2:.*]] = bitcast i8* %[[dstgep1]] to i32*
|
||||
; CHECK-NEXT: store i32 %[[srcload]], i32* %[[dstcast2]], {{.*}}, !tbaa [[TAG_9]]
|
||||
; CHECK-NEXT: %[[agep3:.*]] = getelementptr inbounds [34 x i8], [34 x i8]* %[[a]], i64 0, i64 0
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %[[agep3]], i32 %size, {{.*}}), !tbaa [[TAG_11]]
|
||||
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* align 1 %[[agep3]], i32 %size, {{.*}}), !tbaa [[TAG_11]]
|
||||
; CHECK-NEXT: ret void
|
||||
|
||||
entry:
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user