Skip to content

[PreISelIntrinsicLowering] Zext/trunc count parameter as necessary for memset_pattern16 emission #129239

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Mar 19, 2025
Merged

[PreISelIntrinsicLowering] Zext/trunc count parameter as necessary for memset_pattern16 emission #129239

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
d6f19cd
[PreISelIntrinsicLowering] Zext/trunc count parameter as necessary fo…
asb Feb 28, 2025
a2fdab8
Merge remote-tracking branch 'origin/main' into 2025q1-preiselintrins…
asb Mar 12, 2025
d528757
Merge remote-tracking branch 'origin/main' into 2025q1-preiselintrins…
asb Mar 12, 2025
9fa61c8
Merge remote-tracking branch 'origin/main' into 2025q1-preiselintrins…
asb Mar 19, 2025
1de9cef
Use TLI.getSizeTType and TLI.getAsSizeT helpers
asb Mar 19, 2025
7f92827
IntIdxTy -> SizeTTy
asb Mar 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 9 additions & 7 deletions llvm/lib/CodeGen/PreISelIntrinsicLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -394,11 +394,12 @@ bool PreISelIntrinsicLowering::expandMemIntrinsicUses(Function &F) const {
Module *M = Memset->getModule();
const DataLayout &DL = Memset->getDataLayout();

Type *DestPtrTy = Memset->getRawDest()->getType();
Type *IntIdxTy = DL.getIndexType(DestPtrTy);
StringRef FuncName = "memset_pattern16";
FunctionCallee MSP = getOrInsertLibFunc(
M, TLI, LibFunc_memset_pattern16, Builder.getVoidTy(),
Memset->getRawDest()->getType(), Builder.getPtrTy(),
Memset->getLength()->getType());
FunctionCallee MSP = getOrInsertLibFunc(M, TLI, LibFunc_memset_pattern16,
Builder.getVoidTy(), DestPtrTy,
Builder.getPtrTy(), IntIdxTy);
inferNonMandatoryLibFuncAttrs(M, FuncName, TLI);

// Otherwise we should form a memset_pattern16. PatternValue is known
Expand All @@ -415,9 +416,10 @@ bool PreISelIntrinsicLowering::expandMemIntrinsicUses(Function &F) const {
GV->setAlignment(Align(16));
Value *PatternPtr = GV;
Value *NumBytes = Builder.CreateMul(
Builder.getInt64(DL.getTypeSizeInBits(Memset->getValue()->getType()) /
8),
Memset->getLength());
ConstantInt::get(IntIdxTy,
DL.getTypeSizeInBits(Memset->getValue()->getType()) /
Copy link
Contributor

@nikic nikic Feb 28, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not directly related to your change, but shouldn't this be using getTypeAllocSize instead of getTypeSizeInBits / 8?

Copy link
Contributor Author

@asb asb Mar 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've directly committed that change, and merged in upstream changes to this PR.

8),
Builder.CreateZExtOrTrunc(Memset->getLength(), IntIdxTy));
CallInst *MemsetPattern16Call =
Builder.CreateCall(MSP, {Memset->getRawDest(), PatternPtr, NumBytes});
MemsetPattern16Call->setAAMetadata(Memset->getAAMetadata());
Expand Down
48 changes: 37 additions & 11 deletions llvm/test/Transforms/PreISelIntrinsicLowering/X86/memset-pattern.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,12 +3,14 @@

;.
; CHECK: @.memset_pattern = private unnamed_addr constant [2 x i64] [i64 -6148895925951734307, i64 -6148895925951734307], align 16
; CHECK: @.memset_pattern.1 = private unnamed_addr constant [2 x i64] [i64 4614256656552045848, i64 4614256656552045848], align 16
; CHECK: @.memset_pattern.2 = private unnamed_addr constant [8 x i16] [i16 -21555, i16 -21555, i16 -21555, i16 -21555, i16 -21555, i16 -21555, i16 -21555, i16 -21555], align 16
; CHECK: @.memset_pattern.3 = private unnamed_addr constant i128 -113427455635030943652277463699152839203, align 16
; CHECK: @.memset_pattern.4 = private unnamed_addr constant i128 -113427455635030943652277463699152839203, align 16
; CHECK: @.memset_pattern.1 = private unnamed_addr constant [2 x i64] [i64 -6148895925951734307, i64 -6148895925951734307], align 16
; CHECK: @.memset_pattern.2 = private unnamed_addr constant [2 x i64] [i64 -6148895925951734307, i64 -6148895925951734307], align 16
; CHECK: @.memset_pattern.3 = private unnamed_addr constant [2 x i64] [i64 4614256656552045848, i64 4614256656552045848], align 16
; CHECK: @.memset_pattern.4 = private unnamed_addr constant [8 x i16] [i16 -21555, i16 -21555, i16 -21555, i16 -21555, i16 -21555, i16 -21555, i16 -21555, i16 -21555], align 16
; CHECK: @.memset_pattern.5 = private unnamed_addr constant i128 -113427455635030943652277463699152839203, align 16
; CHECK: @.memset_pattern.6 = private unnamed_addr constant i128 -113427455635030943652277463699152839203, align 16
; CHECK: @.memset_pattern.7 = private unnamed_addr constant i128 -113427455635030943652277463699152839203, align 16
; CHECK: @.memset_pattern.8 = private unnamed_addr constant i128 -113427455635030943652277463699152839203, align 16
;.
define void @memset_pattern_i128_1_dynvalue(ptr %a, i128 %value) nounwind {
; CHECK-LABEL: define void @memset_pattern_i128_1_dynvalue(
Expand All @@ -31,7 +33,7 @@ define void @memset_pattern_i128_1_dynvalue(ptr %a, i128 %value) nounwind {
define void @memset_pattern_i128_1(ptr %a, i128 %value) nounwind {
; CHECK-LABEL: define void @memset_pattern_i128_1(
; CHECK-SAME: ptr [[A:%.*]], i128 [[VALUE:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.3, i64 16)
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.5, i64 16)
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i128 u0xaaaaaaaabbbbbbbbccccccccdddddddd, i64 1, i1 false)
Expand Down Expand Up @@ -59,7 +61,7 @@ define void @memset_pattern_i128_1_nz_as(ptr addrspace(1) %a, i128 %value) nounw
define void @memset_pattern_i128_1_align_attr(ptr align(16) %a, i128 %value) nounwind {
; CHECK-LABEL: define void @memset_pattern_i128_1_align_attr(
; CHECK-SAME: ptr align 16 [[A:%.*]], i128 [[VALUE:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: call void @memset_pattern16(ptr align 16 [[A]], ptr @.memset_pattern.4, i64 16)
; CHECK-NEXT: call void @memset_pattern16(ptr align 16 [[A]], ptr @.memset_pattern.6, i64 16)
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr align(16) %a, i128 u0xaaaaaaaabbbbbbbbccccccccdddddddd, i64 1, i1 false)
Expand All @@ -69,7 +71,7 @@ define void @memset_pattern_i128_1_align_attr(ptr align(16) %a, i128 %value) nou
define void @memset_pattern_i128_16(ptr %a) nounwind {
; CHECK-LABEL: define void @memset_pattern_i128_16(
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.5, i64 256)
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.7, i64 256)
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i128 u0xaaaaaaaabbbbbbbbccccccccdddddddd, i64 16, i1 false)
Expand All @@ -80,7 +82,7 @@ define void @memset_pattern_i128_x(ptr %a, i64 %x) nounwind {
; CHECK-LABEL: define void @memset_pattern_i128_x(
; CHECK-SAME: ptr [[A:%.*]], i64 [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 16, [[X]]
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.6, i64 [[TMP1]])
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.8, i64 [[TMP1]])
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i128 u0xaaaaaaaabbbbbbbbccccccccdddddddd, i64 %x, i1 false)
Expand Down Expand Up @@ -110,7 +112,7 @@ define void @memset_pattern_i16_x(ptr %a, i64 %x) nounwind {
; CHECK-LABEL: define void @memset_pattern_i16_x(
; CHECK-SAME: ptr [[A:%.*]], i64 [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 2, [[X]]
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.2, i64 [[TMP1]])
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.4, i64 [[TMP1]])
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i16 u0xabcd, i64 %x, i1 false)
Expand All @@ -121,7 +123,7 @@ define void @memset_pattern_i64_x(ptr %a, i64 %x) nounwind {
; CHECK-LABEL: define void @memset_pattern_i64_x(
; CHECK-SAME: ptr [[A:%.*]], i64 [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = mul i64 8, [[X]]
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern, i64 [[TMP1]])
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.2, i64 [[TMP1]])
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i64 u0xaaaabbbbccccdddd, i64 %x, i1 false)
Expand All @@ -132,13 +134,37 @@ define void @memset_pattern_i64_x(ptr %a, i64 %x) nounwind {
define void @memset_pattern_i64_128_tbaa(ptr %a) nounwind {
; CHECK-LABEL: define void @memset_pattern_i64_128_tbaa(
; CHECK-SAME: ptr [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.1, i64 1024), !tbaa [[TBAA0:![0-9]+]]
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.3, i64 1024), !tbaa [[TBAA0:![0-9]+]]
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i64 u0x400921fb54442d18, i64 128, i1 false), !tbaa !5
ret void
}

define void @memset_pattern_i64_narrow_idx(ptr %a, i32 %x) nounwind {
; CHECK-LABEL: define void @memset_pattern_i64_narrow_idx(
; CHECK-SAME: ptr [[A:%.*]], i32 [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[X]] to i64
; CHECK-NEXT: [[TMP2:%.*]] = mul i64 8, [[TMP1]]
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.1, i64 [[TMP2]])
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i64 u0xaaaabbbbccccdddd, i32 %x, i1 false)
ret void
}

define void @memset_pattern_i64_wide_idx(ptr %a, i128 %x) nounwind {
; CHECK-LABEL: define void @memset_pattern_i64_wide_idx(
; CHECK-SAME: ptr [[A:%.*]], i128 [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = trunc i128 [[X]] to i64
; CHECK-NEXT: [[TMP2:%.*]] = mul i64 8, [[TMP1]]
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern, i64 [[TMP2]])
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i64 u0xaaaabbbbccccdddd, i128 %x, i1 false)
ret void
}

!5 = !{!6, !6, i64 0}
!6 = !{!"double", !7, i64 0}
!7 = !{!"omnipotent char", !8, i64 0}
Expand Down
Loading