[llvm] f88436c - [InstCombine] Fold signbit test of a pow2 or zero
Jun Zhang via llvm-commits
llvm-commits at lists.llvm.org
Mon Feb 27 23:53:07 PST 2023
Author: Jun Zhang
Date: 2023-02-28T15:52:13+08:00
New Revision: f88436c3f3b01a04aff4a129245a8a1b1124e7f1
URL: https://github.com/llvm/llvm-project/commit/f88436c3f3b01a04aff4a129245a8a1b1124e7f1
DIFF: https://github.com/llvm/llvm-project/commit/f88436c3f3b01a04aff4a129245a8a1b1124e7f1.diff
LOG: [InstCombine] Fold signbit test of a pow2 or zero
(X & X) < 0 --> X == MinSignedC
(X & X) > -1 --> X != MinSignedC
Alive2: https://alive2.llvm.org/ce/z/_J5q3S
Closes: https://github.com/llvm/llvm-project/issues/60957
Signed-off-by: Jun Zhang <jun at junz.org>
Differential Revision: https://reviews.llvm.org/D144777
Added:
Modified:
llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
llvm/test/Transforms/InstCombine/fold-signbit-test-power2.ll
llvm/test/Transforms/InstCombine/minmax-of-xor-x.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
index c8c24c75f655b..2300455a7934a 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -1832,6 +1832,15 @@ Instruction *InstCombinerImpl::foldICmpAndConstant(ICmpInst &Cmp,
auto NewPred = TrueIfNeg ? CmpInst::ICMP_EQ : CmpInst::ICMP_NE;
return new ICmpInst(NewPred, X, ConstantInt::getNullValue(X->getType()));
}
+ // (X & X) < 0 --> X == MinSignedC
+ // (X & X) > -1 --> X != MinSignedC
+ if (match(And, m_c_And(m_Neg(m_Value(X)), m_Deferred(X)))) {
+ Constant *MinSignedC = ConstantInt::get(
+ X->getType(),
+ APInt::getSignedMinValue(X->getType()->getScalarSizeInBits()));
+ auto NewPred = TrueIfNeg ? CmpInst::ICMP_EQ : CmpInst::ICMP_NE;
+ return new ICmpInst(NewPred, X, MinSignedC);
+ }
}
// TODO: These all require that Y is constant too, so refactor with the above.
diff --git a/llvm/test/Transforms/InstCombine/fold-signbit-test-power2.ll b/llvm/test/Transforms/InstCombine/fold-signbit-test-power2.ll
index 8c512092a3dd6..f5024664f58c3 100644
--- a/llvm/test/Transforms/InstCombine/fold-signbit-test-power2.ll
+++ b/llvm/test/Transforms/InstCombine/fold-signbit-test-power2.ll
@@ -1,56 +1,60 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=instcombine -S | FileCheck %s
-; icmp slt (and X, -X), 0 --> icmp eq (X, MinSignC)
-define i1 @pow2_or_zero1(i8 %x) {
-; CHECK-LABEL: @pow2_or_zero1(
-; CHECK-NEXT: [[NEG:%.*]] = sub i8 0, [[X:%.*]]
-; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[NEG]], [[X]]
-; CHECK-NEXT: [[CMP:%.*]] = icmp slt i8 [[POW2_OR_ZERO]], 0
+declare void @use(i8)
+declare void @use_i1(i1)
+declare void @use_i1_vec(<2 x i1>)
+
+; (X & -X) < 0 --> X == MinSignC
+; (X & X) > -1 --> X != MinSignC
+
+define i1 @pow2_or_zero_is_negative(i8 %x) {
+; CHECK-LABEL: @pow2_or_zero_is_negative(
+; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8 [[X:%.*]], -128
+; CHECK-NEXT: [[CMP_2:%.*]] = icmp eq i8 [[X]], -128
+; CHECK-NEXT: call void @use_i1(i1 [[CMP_2]])
; CHECK-NEXT: ret i1 [[CMP]]
;
%neg = sub i8 0, %x
%pow2_or_zero = and i8 %x, %neg
%cmp = icmp slt i8 %pow2_or_zero, 0
+ %cmp.2 = icmp ugt i8 %pow2_or_zero, 127
+ call void @use_i1(i1 %cmp.2)
ret i1 %cmp
}
-; icmp slt (and -X, X), 0 --> icmp eq (X, MinSignC)
-define i1 @pow2_or_zero1_commute(i8 %A) {
-; CHECK-LABEL: @pow2_or_zero1_commute(
-; CHECK-NEXT: [[X:%.*]] = sdiv i8 42, [[A:%.*]]
-; CHECK-NEXT: [[NEG:%.*]] = sub nsw i8 0, [[X]]
-; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[X]], [[NEG]]
-; CHECK-NEXT: [[CMP:%.*]] = icmp slt i8 [[POW2_OR_ZERO]], 0
+define i1 @pow2_or_zero_is_negative_commute(i8 %A) {
+; CHECK-LABEL: @pow2_or_zero_is_negative_commute(
+; CHECK-NEXT: [[X:%.*]] = mul i8 [[A:%.*]], 42
+; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8 [[X]], -128
; CHECK-NEXT: ret i1 [[CMP]]
;
- %x = sdiv i8 42, %A ; thwart complexity-based canonicalization
+ %x = mul i8 42, %A ; thwart complexity-based canonicalization
%neg = sub i8 0, %x
%pow2_or_zero = and i8 %neg, %x
%cmp = icmp slt i8 %pow2_or_zero, 0
ret i1 %cmp
}
-define <2 x i1> @pow2_or_zero1_vec(<2 x i8> %x) {
-; CHECK-LABEL: @pow2_or_zero1_vec(
-; CHECK-NEXT: [[NEG:%.*]] = sub <2 x i8> zeroinitializer, [[X:%.*]]
-; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and <2 x i8> [[NEG]], [[X]]
-; CHECK-NEXT: [[CMP:%.*]] = icmp slt <2 x i8> [[POW2_OR_ZERO]], zeroinitializer
+define <2 x i1> @pow2_or_zero_is_negative_vec(<2 x i8> %x) {
+; CHECK-LABEL: @pow2_or_zero_is_negative_vec(
+; CHECK-NEXT: [[CMP:%.*]] = icmp eq <2 x i8> [[X:%.*]], <i8 -128, i8 -128>
+; CHECK-NEXT: [[CMP_2:%.*]] = icmp eq <2 x i8> [[X]], <i8 -128, i8 -128>
+; CHECK-NEXT: call void @use_i1_vec(<2 x i1> [[CMP_2]])
; CHECK-NEXT: ret <2 x i1> [[CMP]]
;
%neg = sub <2 x i8> <i8 0, i8 0>, %x
%pow2_or_zero = and <2 x i8> %x, %neg
%cmp = icmp slt <2 x i8> %pow2_or_zero, <i8 0, i8 0>
+ %cmp.2 = icmp ugt <2 x i8> %pow2_or_zero, <i8 127, i8 127>
+ call void @use_i1_vec(<2 x i1> %cmp.2)
ret <2 x i1> %cmp
}
-
-define <2 x i1> @pow2_or_zero1_vec_commute(<2 x i8> %A) {
-; CHECK-LABEL: @pow2_or_zero1_vec_commute(
+define <2 x i1> @pow2_or_zero_is_negative_vec_commute(<2 x i8> %A) {
+; CHECK-LABEL: @pow2_or_zero_is_negative_vec_commute(
; CHECK-NEXT: [[X:%.*]] = mul <2 x i8> [[A:%.*]], <i8 42, i8 42>
-; CHECK-NEXT: [[NEG:%.*]] = sub <2 x i8> zeroinitializer, [[X]]
-; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and <2 x i8> [[X]], [[NEG]]
-; CHECK-NEXT: [[CMP:%.*]] = icmp slt <2 x i8> [[POW2_OR_ZERO]], zeroinitializer
+; CHECK-NEXT: [[CMP:%.*]] = icmp eq <2 x i8> [[X]], <i8 -128, i8 -128>
; CHECK-NEXT: ret <2 x i1> [[CMP]]
;
%x = mul <2 x i8> <i8 42, i8 42>, %A ; thwart complexity-based canonicalization
@@ -60,27 +64,25 @@ define <2 x i1> @pow2_or_zero1_vec_commute(<2 x i8> %A) {
ret <2 x i1> %cmp
}
-; icmp sgt (and X, -X), -1 --> icmp ne (X, MinSignC)
-define i1 @pow2_or_zero2(i8 %x) {
-; CHECK-LABEL: @pow2_or_zero2(
-; CHECK-NEXT: [[NEG:%.*]] = sub i8 0, [[X:%.*]]
-; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[NEG]], [[X]]
-; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i8 [[POW2_OR_ZERO]], -1
+define i1 @pow2_or_zero_is_not_negative(i8 %x) {
+; CHECK-LABEL: @pow2_or_zero_is_not_negative(
+; CHECK-NEXT: [[CMP:%.*]] = icmp ne i8 [[X:%.*]], -128
+; CHECK-NEXT: [[CMP_2:%.*]] = icmp ne i8 [[X]], -128
+; CHECK-NEXT: call void @use_i1(i1 [[CMP_2]])
; CHECK-NEXT: ret i1 [[CMP]]
;
%neg = sub i8 0, %x
%pow2_or_zero = and i8 %x, %neg
%cmp = icmp sgt i8 %pow2_or_zero, -1
+ %cmp.2 = icmp ult i8 %pow2_or_zero, -128
+ call void @use_i1(i1 %cmp.2)
ret i1 %cmp
}
-; icmp sgt (and -X, X), -1 --> icmp ne (X, MinSignC)
-define i1 @pow2_or_zero2_commute(i8 %A) {
-; CHECK-LABEL: @pow2_or_zero2_commute(
+define i1 @pow2_or_zero_is_not_negative_commute(i8 %A) {
+; CHECK-LABEL: @pow2_or_zero_is_not_negative_commute(
; CHECK-NEXT: [[X:%.*]] = mul i8 [[A:%.*]], 42
-; CHECK-NEXT: [[NEG:%.*]] = sub i8 0, [[X]]
-; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[X]], [[NEG]]
-; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i8 [[POW2_OR_ZERO]], -1
+; CHECK-NEXT: [[CMP:%.*]] = icmp ne i8 [[X]], -128
; CHECK-NEXT: ret i1 [[CMP]]
;
%x = mul i8 42, %A ; thwart complexity-based canonicalization
@@ -90,25 +92,25 @@ define i1 @pow2_or_zero2_commute(i8 %A) {
ret i1 %cmp
}
-define <2 x i1> @pow2_or_zero2_vec(<2 x i8> %x) {
-; CHECK-LABEL: @pow2_or_zero2_vec(
-; CHECK-NEXT: [[NEG:%.*]] = sub <2 x i8> zeroinitializer, [[X:%.*]]
-; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and <2 x i8> [[NEG]], [[X]]
-; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <2 x i8> [[POW2_OR_ZERO]], <i8 -1, i8 -1>
+define <2 x i1> @pow2_or_zero_is_not_negative_vec(<2 x i8> %x) {
+; CHECK-LABEL: @pow2_or_zero_is_not_negative_vec(
+; CHECK-NEXT: [[CMP:%.*]] = icmp ne <2 x i8> [[X:%.*]], <i8 -128, i8 -128>
+; CHECK-NEXT: [[CMP_2:%.*]] = icmp ne <2 x i8> [[X]], <i8 -128, i8 -128>
+; CHECK-NEXT: call void @use_i1_vec(<2 x i1> [[CMP_2]])
; CHECK-NEXT: ret <2 x i1> [[CMP]]
;
%neg = sub <2 x i8> <i8 0, i8 0>, %x
%pow2_or_zero = and <2 x i8> %x, %neg
%cmp = icmp sgt <2 x i8> %pow2_or_zero, <i8 -1, i8 -1>
+ %cmp.2 = icmp ult <2 x i8> %pow2_or_zero, <i8 -128, i8 -128>
+ call void @use_i1_vec(<2 x i1> %cmp.2)
ret <2 x i1> %cmp
}
-define <2 x i1> @pow2_or_zero2_vec_commute(<2 x i8> %A) {
-; CHECK-LABEL: @pow2_or_zero2_vec_commute(
+define <2 x i1> @pow2_or_zero_is_not_negative_vec_commute(<2 x i8> %A) {
+; CHECK-LABEL: @pow2_or_zero_is_not_negative_vec_commute(
; CHECK-NEXT: [[X:%.*]] = mul <2 x i8> [[A:%.*]], <i8 42, i8 42>
-; CHECK-NEXT: [[NEG:%.*]] = sub <2 x i8> zeroinitializer, [[X]]
-; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and <2 x i8> [[X]], [[NEG]]
-; CHECK-NEXT: [[CMP:%.*]] = icmp sgt <2 x i8> [[POW2_OR_ZERO]], <i8 -1, i8 -1>
+; CHECK-NEXT: [[CMP:%.*]] = icmp ne <2 x i8> [[X]], <i8 -128, i8 -128>
; CHECK-NEXT: ret <2 x i1> [[CMP]]
;
%x = mul <2 x i8> <i8 42, i8 42>, %A ; thwart complexity-based canonicalization
@@ -117,3 +119,20 @@ define <2 x i1> @pow2_or_zero2_vec_commute(<2 x i8> %A) {
%cmp = icmp sgt <2 x i8> %pow2_or_zero, <i8 -1, i8 -1>
ret <2 x i1> %cmp
}
+
+define i1 @pow2_or_zero_is_negative_extra_use(i8 %x) {
+; CHECK-LABEL: @pow2_or_zero_is_negative_extra_use(
+; CHECK-NEXT: [[NEG:%.*]] = sub i8 0, [[X:%.*]]
+; CHECK-NEXT: call void @use(i8 [[NEG]])
+; CHECK-NEXT: [[POW2_OR_ZERO:%.*]] = and i8 [[NEG]], [[X]]
+; CHECK-NEXT: call void @use(i8 [[POW2_OR_ZERO]])
+; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8 [[X]], -128
+; CHECK-NEXT: ret i1 [[CMP]]
+;
+ %neg = sub i8 0, %x
+ call void @use(i8 %neg)
+ %pow2_or_zero = and i8 %x, %neg
+ call void @use(i8 %pow2_or_zero)
+ %cmp = icmp slt i8 %pow2_or_zero, 0
+ ret i1 %cmp
+}
diff --git a/llvm/test/Transforms/InstCombine/minmax-of-xor-x.ll b/llvm/test/Transforms/InstCombine/minmax-of-xor-x.ll
index ff3093cd183eb..daf58a3b52000 100644
--- a/llvm/test/Transforms/InstCombine/minmax-of-xor-x.ll
+++ b/llvm/test/Transforms/InstCombine/minmax-of-xor-x.ll
@@ -134,12 +134,13 @@ define <2 x i8> @smin_xor_pow2_unk(<2 x i8> %x, <2 x i8> %y) {
define i8 @smax_xor_pow2_neg(i8 %x, i8 %y) {
; CHECK-LABEL: @smax_xor_pow2_neg(
-; CHECK-NEXT: [[NY:%.*]] = sub i8 0, [[Y:%.*]]
-; CHECK-NEXT: [[YP2:%.*]] = and i8 [[NY]], [[Y]]
-; CHECK-NEXT: [[CMP:%.*]] = icmp slt i8 [[YP2]], 0
+; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8 [[Y:%.*]], -128
; CHECK-NEXT: br i1 [[CMP]], label [[NEG:%.*]], label [[POS:%.*]]
; CHECK: neg:
-; CHECK-NEXT: [[R:%.*]] = and i8 [[X:%.*]], 127
+; CHECK-NEXT: [[NY:%.*]] = sub i8 0, [[Y]]
+; CHECK-NEXT: [[YP2:%.*]] = and i8 [[NY]], [[Y]]
+; CHECK-NEXT: [[X_XOR:%.*]] = xor i8 [[YP2]], [[X:%.*]]
+; CHECK-NEXT: [[R:%.*]] = call i8 @llvm.smax.i8(i8 [[X]], i8 [[X_XOR]])
; CHECK-NEXT: ret i8 [[R]]
; CHECK: pos:
; CHECK-NEXT: call void @barrier()
More information about the llvm-commits
mailing list