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
12 changes: 12 additions & 0 deletions llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -582,6 +582,18 @@ static Instruction *foldCttzCtlz(IntrinsicInst &II, InstCombinerImpl &IC) {
IC.Builder.CreateBinaryIntrinsic(Intrinsic::ctlz, C, Op1);
return BinaryOperator::CreateSub(ConstCtlz, X);
}

// ctlz(~x & (x - 1)) -> bitwidth - cttz(x, false)
if (Op0->hasOneUse() &&
match(Op0,
m_c_And(m_Not(m_Value(X)), m_Add(m_Deferred(X), m_AllOnes())))) {
Type *Ty = II.getType();
unsigned BitWidth = Ty->getScalarSizeInBits();
auto *Cttz = IC.Builder.CreateIntrinsic(Intrinsic::cttz, Ty,
{X, IC.Builder.getFalse()});
auto *Bw = ConstantInt::get(Ty, APInt(BitWidth, BitWidth));
return IC.replaceInstUsesWith(II, IC.Builder.CreateSub(Bw, Cttz));
}
}

// cttz(Pow2) -> Log2(Pow2)
Expand Down
145 changes: 145 additions & 0 deletions llvm/test/Transforms/InstCombine/ctlz-cttz.ll
Original file line number Diff line number Diff line change
@@ -0,0 +1,145 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
; RUN: opt < %s -S -passes=instcombine | FileCheck %s

; ctpop(~i & (i - 1)) -> bitwidth - cttz(i, false)
define i8 @ctlz_to_sub_bw_cttz(i8 %a0) {
; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz(
; CHECK-SAME: i8 [[A0:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
; CHECK-NEXT: [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
; CHECK-NEXT: ret i8 [[CLZ]]
;
%dec = add i8 %a0, -1
%not = xor i8 %a0, -1
%and = and i8 %dec, %not
%clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
ret i8 %clz
}

define i8 @ctlz_to_sub_bw_cttz_poison(i8 %a0) {
; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_poison(
; CHECK-SAME: i8 [[A0:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
; CHECK-NEXT: [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
; CHECK-NEXT: ret i8 [[CLZ]]
;
%dec = add i8 %a0, -1
%not = xor i8 %a0, -1
%and = and i8 %dec, %not
%clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 true)
ret i8 %clz
}

define i8 @ctlz_to_sub_bw_cttz_different_add(i8 %a0) {
; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_different_add(
; CHECK-SAME: i8 [[A0:%.*]]) {
; CHECK-NEXT: [[DEC:%.*]] = add i8 [[A0]], 1
; CHECK-NEXT: [[NOT:%.*]] = xor i8 [[A0]], -1
; CHECK-NEXT: [[AND:%.*]] = and i8 [[DEC]], [[NOT]]
; CHECK-NEXT: [[CLZ:%.*]] = tail call range(i8 0, 9) i8 @llvm.ctlz.i8(i8 [[AND]], i1 false)
; CHECK-NEXT: ret i8 [[CLZ]]
;
%dec = add i8 %a0, 1
%not = xor i8 %a0, -1
%and = and i8 %dec, %not
%clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
ret i8 %clz
}

define i8 @ctlz_to_sub_bw_cttz_different_xor(i8 %a0) {
; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_different_xor(
; CHECK-SAME: i8 [[A0:%.*]]) {
; CHECK-NEXT: [[DEC:%.*]] = add i8 [[A0]], -1
; CHECK-NEXT: [[NOT:%.*]] = xor i8 [[A0]], 1
; CHECK-NEXT: [[AND:%.*]] = and i8 [[DEC]], [[NOT]]
; CHECK-NEXT: [[CLZ:%.*]] = tail call range(i8 0, 9) i8 @llvm.ctlz.i8(i8 [[AND]], i1 false)
; CHECK-NEXT: ret i8 [[CLZ]]
;
%dec = add i8 %a0, -1
%not = xor i8 %a0, 1
%and = and i8 %dec, %not
%clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
ret i8 %clz
}

declare void @use(i8)

define i8 @ctlz_to_sub_bw_cttz_multi_use_dec(i8 %a0) {
; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_multi_use_dec(
; CHECK-SAME: i8 [[A0:%.*]]) {
; CHECK-NEXT: [[DEC:%.*]] = add i8 [[A0]], -1
; CHECK-NEXT: call void @use(i8 [[DEC]])
; CHECK-NEXT: [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
; CHECK-NEXT: [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
; CHECK-NEXT: ret i8 [[CLZ]]
;
%dec = add i8 %a0, -1
call void @use(i8 %dec)
%not = xor i8 %a0, -1
%and = and i8 %dec, %not
%clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
ret i8 %clz
}

define i8 @ctlz_to_sub_bw_cttz_multi_use_not(i8 %a0) {
; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_multi_use_not(
; CHECK-SAME: i8 [[A0:%.*]]) {
; CHECK-NEXT: [[NOT:%.*]] = xor i8 [[A0]], -1
; CHECK-NEXT: call void @use(i8 [[NOT]])
; CHECK-NEXT: [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
; CHECK-NEXT: [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
; CHECK-NEXT: ret i8 [[CLZ]]
;
%dec = add i8 %a0, -1
%not = xor i8 %a0, -1
call void @use(i8 %not)
%and = and i8 %dec, %not
%clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
ret i8 %clz
}

define i8 @ctlz_to_sub_bw_cttz_multi_use_and(i8 %a0) {
; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_multi_use_and(
; CHECK-SAME: i8 [[A0:%.*]]) {
; CHECK-NEXT: [[DEC:%.*]] = add i8 [[A0]], -1
; CHECK-NEXT: [[NOT:%.*]] = xor i8 [[A0]], -1
; CHECK-NEXT: [[AND:%.*]] = and i8 [[DEC]], [[NOT]]
; CHECK-NEXT: call void @use(i8 [[AND]])
; CHECK-NEXT: [[CLZ:%.*]] = tail call range(i8 0, 9) i8 @llvm.ctlz.i8(i8 [[AND]], i1 false)
; CHECK-NEXT: ret i8 [[CLZ]]
;
%dec = add i8 %a0, -1
%not = xor i8 %a0, -1
%and = and i8 %dec, %not
call void @use(i8 %and)
%clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
ret i8 %clz
}

define i8 @ctlz_to_sub_bw_cttz_commute_and(i8 %a0) {
; CHECK-LABEL: define i8 @ctlz_to_sub_bw_cttz_commute_and(
; CHECK-SAME: i8 [[A0:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call range(i8 0, 9) i8 @llvm.cttz.i8(i8 [[A0]], i1 false)
; CHECK-NEXT: [[CLZ:%.*]] = sub nuw nsw i8 8, [[TMP1]]
; CHECK-NEXT: ret i8 [[CLZ]]
;
%dec = add i8 %a0, -1
%not = xor i8 %a0, -1
%and = and i8 %not, %dec
%clz = tail call i8 @llvm.ctlz.i8(i8 %and, i1 false)
ret i8 %clz
}

define <2 x i8> @ctlz_to_sub_bw_cttz_vec_splat(<2 x i8> %a0) {
; CHECK-LABEL: define <2 x i8> @ctlz_to_sub_bw_cttz_vec_splat(
; CHECK-SAME: <2 x i8> [[A0:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call range(i8 0, 9) <2 x i8> @llvm.cttz.v2i8(<2 x i8> [[A0]], i1 false)
; CHECK-NEXT: [[CLZ:%.*]] = sub nuw nsw <2 x i8> splat (i8 8), [[TMP1]]
; CHECK-NEXT: ret <2 x i8> [[CLZ]]
;
%dec = add <2 x i8> %a0, <i8 -1, i8 -1>
%not = xor <2 x i8> %a0, <i8 -1, i8 -1>
%and = and <2 x i8> %dec, %not
%clz = tail call <2 x i8>@llvm.ctlz.v2i8(<2 x i8> %and, i1 false)
ret <2 x i8> %clz
}