Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
9 changes: 7 additions & 2 deletions llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -3469,7 +3469,8 @@ static bool isSafeToRemoveBitCeilSelect(ICmpInst::Predicate Pred, Value *Cond0,
// Note that the select is optimized away while the shift count is masked with
// 31. We handle some variations of the input operand like std::bit_ceil(X +
// 1).
static Instruction *foldBitCeil(SelectInst &SI, IRBuilderBase &Builder) {
static Instruction *foldBitCeil(SelectInst &SI, IRBuilderBase &Builder,
InstCombinerImpl &IC) {
Type *SelType = SI.getType();
unsigned BitWidth = SelType->getScalarSizeInBits();

Expand Down Expand Up @@ -3504,6 +3505,10 @@ static Instruction *foldBitCeil(SelectInst &SI, IRBuilderBase &Builder) {
// single hardware instruction as opposed to BitWidth - CTLZ, where BitWidth
// is an integer constant. Masking with BitWidth-1 comes free on some
// hardware as part of the shift instruction.

// Drop range attributes and re-infer them in the next iteration.
cast<Instruction>(Ctlz)->dropPoisonGeneratingAnnotations();
IC.addToWorklist(cast<Instruction>(Ctlz));
Value *Neg = Builder.CreateNeg(Ctlz);
Value *Masked =
Builder.CreateAnd(Neg, ConstantInt::get(SelType, BitWidth - 1));
Expand Down Expand Up @@ -4147,7 +4152,7 @@ Instruction *InstCombinerImpl::visitSelectInst(SelectInst &SI) {
if (sinkNotIntoOtherHandOfLogicalOp(SI))
return &SI;

if (Instruction *I = foldBitCeil(SI, Builder))
if (Instruction *I = foldBitCeil(SI, Builder, *this))
return I;

if (Instruction *I = foldSelectToCmp(SI))
Expand Down
17 changes: 17 additions & 0 deletions llvm/test/Transforms/InstCombine/bit_ceil.ll
Original file line number Diff line number Diff line change
Expand Up @@ -320,6 +320,23 @@ define i32 @pr91691_keep_nsw(i32 %0) {
ret i32 %7
}

define i32 @test_drop_range_attr(i32 %x) {
; CHECK-LABEL: @test_drop_range_attr(
; CHECK-NEXT: [[CTLZ:%.*]] = call range(i32 0, 33) i32 @llvm.ctlz.i32(i32 [[X:%.*]], i1 false)
; CHECK-NEXT: [[TMP1:%.*]] = sub nsw i32 0, [[CTLZ]]
; CHECK-NEXT: [[TMP2:%.*]] = and i32 [[TMP1]], 31
; CHECK-NEXT: [[SEL:%.*]] = shl nuw i32 1, [[TMP2]]
; CHECK-NEXT: ret i32 [[SEL]]
;
%ctlz = call range(i32 1, 33) i32 @llvm.ctlz.i32(i32 %x, i1 false)
%sub = sub i32 32, %ctlz
%shl = shl i32 1, %sub
%dec = add i32 %x, -1
%ult = icmp ult i32 %dec, -2
%sel = select i1 %ult, i32 %shl, i32 1
ret i32 %sel
}

declare i32 @llvm.ctlz.i32(i32, i1 immarg)
declare i64 @llvm.ctlz.i64(i64, i1 immarg)
declare <4 x i32> @llvm.ctlz.v4i32(<4 x i32>, i1)
Loading