Skip to content

[PreISelIntrinsicLowering] Reuse previously generated GlobalVariable for memset_pattern16 when possible #144677

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 1 commit into from
Jun 23, 2025
Merged

[PreISelIntrinsicLowering] Reuse previously generated GlobalVariable for memset_pattern16 when possible #144677

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
32 changes: 22 additions & 10 deletions llvm/lib/CodeGen/PreISelIntrinsicLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,9 @@ struct PreISelIntrinsicLowering {

static bool shouldExpandMemIntrinsicWithSize(Value *Size,
const TargetTransformInfo &TTI);
bool expandMemIntrinsicUses(Function &F) const;
bool
expandMemIntrinsicUses(Function &F,
DenseMap<Constant *, GlobalVariable *> &CMap) const;
bool lowerIntrinsics(Module &M) const;
};

Expand Down Expand Up @@ -287,7 +289,8 @@ static Constant *getMemSetPattern16Value(MemSetPatternInst *Inst,

// TODO: Handle atomic memcpy and memcpy.inline
// TODO: Pass ScalarEvolution
bool PreISelIntrinsicLowering::expandMemIntrinsicUses(Function &F) const {
bool PreISelIntrinsicLowering::expandMemIntrinsicUses(
Function &F, DenseMap<Constant *, GlobalVariable *> &CMap) const {
Intrinsic::ID ID = F.getIntrinsicID();
bool Changed = false;

Expand Down Expand Up @@ -404,13 +407,20 @@ bool PreISelIntrinsicLowering::expandMemIntrinsicUses(Function &F) const {
// global.
assert(Memset->getRawDest()->getType()->getPointerAddressSpace() == 0 &&
"Should have skipped if non-zero AS");
GlobalVariable *GV = new GlobalVariable(
*M, PatternValue->getType(), /*isConstant=*/true,
GlobalValue::PrivateLinkage, PatternValue, ".memset_pattern");
GV->setUnnamedAddr(
GlobalValue::UnnamedAddr::Global); // Ok to merge these.
// TODO: Consider relaxing alignment requirement.
GV->setAlignment(Align(16));
GlobalVariable *GV;
auto It = CMap.find(PatternValue);
if (It != CMap.end()) {
GV = It->second;
} else {
GV = new GlobalVariable(
*M, PatternValue->getType(), /*isConstant=*/true,
GlobalValue::PrivateLinkage, PatternValue, ".memset_pattern");
GV->setUnnamedAddr(
GlobalValue::UnnamedAddr::Global); // Ok to merge these.
// TODO: Consider relaxing alignment requirement.
GV->setAlignment(Align(16));
CMap[PatternValue] = GV;
}
Value *PatternPtr = GV;
Value *NumBytes = Builder.CreateMul(
TLI.getAsSizeT(DL.getTypeAllocSize(Memset->getValue()->getType()),
Expand Down Expand Up @@ -439,6 +449,8 @@ bool PreISelIntrinsicLowering::expandMemIntrinsicUses(Function &F) const {
}

bool PreISelIntrinsicLowering::lowerIntrinsics(Module &M) const {
// Map unique constants to globals.
DenseMap<Constant *, GlobalVariable *> CMap;
bool Changed = false;
for (Function &F : M) {
switch (F.getIntrinsicID()) {
Expand All @@ -450,7 +462,7 @@ bool PreISelIntrinsicLowering::lowerIntrinsics(Module &M) const {
case Intrinsic::memset:
case Intrinsic::memset_inline:
case Intrinsic::experimental_memset_pattern:
Changed |= expandMemIntrinsicUses(F);
Changed |= expandMemIntrinsicUses(F, CMap);
break;
case Intrinsic::load_relative:
Changed |= lowerLoadRelative(F);
Expand Down
34 changes: 14 additions & 20 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 @@ -4,16 +4,10 @@
;.
; CHECK: @G = global i32 5
; CHECK: @.memset_pattern = private unnamed_addr constant [2 x ptr] [ptr @G, ptr @G], align 16
; CHECK: @.memset_pattern.1 = private unnamed_addr constant [2 x ptr] [ptr @G, ptr @G], 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 -6148895925951734307, i64 -6148895925951734307], align 16
; CHECK: @.memset_pattern.4 = private unnamed_addr constant [2 x i64] [i64 -6148895925951734307, i64 -6148895925951734307], align 16
; CHECK: @.memset_pattern.5 = private unnamed_addr constant [2 x i64] [i64 4614256656552045848, i64 4614256656552045848], align 16
; CHECK: @.memset_pattern.6 = 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.7 = private unnamed_addr constant i128 -113427455635030943652277463699152839203, align 16
; CHECK: @.memset_pattern.8 = private unnamed_addr constant i128 -113427455635030943652277463699152839203, align 16
; CHECK: @.memset_pattern.9 = private unnamed_addr constant i128 -113427455635030943652277463699152839203, align 16
; CHECK: @.memset_pattern.10 = 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 4614256656552045848, i64 4614256656552045848], align 16
; CHECK: @.memset_pattern.3 = 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.4 = 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 @@ -36,7 +30,7 @@ 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.7, i64 16)
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.4, 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 @@ -64,7 +58,7 @@ 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.8, i64 16)
; CHECK-NEXT: call void @memset_pattern16(ptr align 16 [[A]], ptr @.memset_pattern.4, 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 @@ -74,7 +68,7 @@ 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.9, i64 256)
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.4, i64 256)
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i128 u0xaaaaaaaabbbbbbbbccccccccdddddddd, i64 16, i1 false)
Expand All @@ -85,7 +79,7 @@ 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.10, 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, i128 u0xaaaaaaaabbbbbbbbccccccccdddddddd, i64 %x, i1 false)
Expand Down Expand Up @@ -115,7 +109,7 @@ 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.6, i64 [[TMP1]])
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.3, i64 [[TMP1]])
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i16 u0xabcd, i64 %x, i1 false)
Expand All @@ -126,7 +120,7 @@ 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.4, i64 [[TMP1]])
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.1, i64 [[TMP1]])
; CHECK-NEXT: ret void
;
tail call void @llvm.experimental.memset.pattern(ptr %a, i64 u0xaaaabbbbccccdddd, i64 %x, i1 false)
Expand All @@ -137,7 +131,7 @@ 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.5, i64 1024), !tbaa [[TBAA0:![0-9]+]]
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.2, 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
Expand All @@ -154,7 +148,7 @@ define void @memset_pattern_i64_narrow_idx(ptr %a, i32 %x) nounwind {
; 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.3, i64 [[TMP2]])
; 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)
Expand All @@ -166,7 +160,7 @@ define void @memset_pattern_i64_wide_idx(ptr %a, i128 %x) nounwind {
; 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.2, i64 [[TMP2]])
; 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, i128 %x, i1 false)
Expand All @@ -189,7 +183,7 @@ define void @memset_pattern_i64_x_fromptr(ptr %a, i64 %x) nounwind {
; CHECK-LABEL: define void @memset_pattern_i64_x_fromptr(
; CHECK-SAME: ptr [[A:%.*]], i64 [[X:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP2:%.*]] = mul i64 8, [[X]]
; CHECK-NEXT: call void @memset_pattern16(ptr [[A]], ptr @.memset_pattern.1, i64 [[TMP2]])
; 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, ptr @G, i64 %x, i1 false)
Expand Down
Loading