[flang-commits] [flang] [InstCombine] Canonicalize `(X +/- Y) & Y` into `~X & Y` when Y is a power of 2 (PR #67915)
Yingwei Zheng via flang-commits
flang-commits at lists.llvm.org
Fri Oct 6 05:53:43 PDT 2023
https://github.com/dtcxzyw updated https://github.com/llvm/llvm-project/pull/67915
>From c4ce28c942c172e5646b5922f0b02b4169197840 Mon Sep 17 00:00:00 2001
From: Yingwei Zheng <dtcxzyw2333 at gmail.com>
Date: Sun, 1 Oct 2023 21:52:47 +0800
Subject: [PATCH 1/2] [InstCombine] Canonicalize `(X +/- Y) & Y` into `~X & Y`
when Y is a power of 2
---
.../InstCombine/InstCombineAndOrXor.cpp | 8 ++++
llvm/test/Transforms/InstCombine/and.ll | 44 +++++++++++++++++--
2 files changed, 48 insertions(+), 4 deletions(-)
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp b/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
index cbdab3e9c5fb91d..4322cc96f5a2b6c 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
@@ -2250,6 +2250,14 @@ Instruction *InstCombinerImpl::visitAnd(BinaryOperator &I) {
return SelectInst::Create(Cmp, ConstantInt::getNullValue(Ty), Y);
}
+ // Canonicalize:
+ // (X +/- Y) & Y --> ~X & Y when Y is a power of 2.
+ if (match(&I, m_c_And(m_Value(Y), m_OneUse(m_CombineOr(
+ m_c_Add(m_Value(X), m_Deferred(Y)),
+ m_Sub(m_Value(X), m_Deferred(Y)))))) &&
+ isKnownToBeAPowerOfTwo(Y, /*OrZero*/ true, /*Depth*/ 0, &I))
+ return BinaryOperator::CreateAnd(Builder.CreateNot(X), Y);
+
const APInt *C;
if (match(Op1, m_APInt(C))) {
const APInt *XorC;
diff --git a/llvm/test/Transforms/InstCombine/and.ll b/llvm/test/Transforms/InstCombine/and.ll
index 90f027010e2aea6..eb39ff9014ff3a4 100644
--- a/llvm/test/Transforms/InstCombine/and.ll
+++ b/llvm/test/Transforms/InstCombine/and.ll
@@ -1595,8 +1595,8 @@ define <2 x i8> @flip_masked_bit_uniform(<2 x i8> %A) {
define <2 x i8> @flip_masked_bit_undef(<2 x i8> %A) {
; CHECK-LABEL: @flip_masked_bit_undef(
-; CHECK-NEXT: [[B:%.*]] = add <2 x i8> [[A:%.*]], <i8 16, i8 undef>
-; CHECK-NEXT: [[C:%.*]] = and <2 x i8> [[B]], <i8 16, i8 undef>
+; CHECK-NEXT: [[TMP1:%.*]] = xor <2 x i8> [[A:%.*]], <i8 -1, i8 -1>
+; CHECK-NEXT: [[C:%.*]] = and <2 x i8> [[TMP1]], <i8 16, i8 undef>
; CHECK-NEXT: ret <2 x i8> [[C]]
;
%B = add <2 x i8> %A, <i8 16, i8 undef>
@@ -1606,8 +1606,8 @@ define <2 x i8> @flip_masked_bit_undef(<2 x i8> %A) {
define <2 x i8> @flip_masked_bit_nonuniform(<2 x i8> %A) {
; CHECK-LABEL: @flip_masked_bit_nonuniform(
-; CHECK-NEXT: [[B:%.*]] = add <2 x i8> [[A:%.*]], <i8 16, i8 4>
-; CHECK-NEXT: [[C:%.*]] = and <2 x i8> [[B]], <i8 16, i8 4>
+; CHECK-NEXT: [[TMP1:%.*]] = xor <2 x i8> [[A:%.*]], <i8 -1, i8 -1>
+; CHECK-NEXT: [[C:%.*]] = and <2 x i8> [[TMP1]], <i8 16, i8 4>
; CHECK-NEXT: ret <2 x i8> [[C]]
;
%B = add <2 x i8> %A, <i8 16, i8 4>
@@ -2546,3 +2546,39 @@ define i32 @and_zext_eq_zero(i32 %A, i32 %C) {
%5 = and i32 %2, %4
ret i32 %5
}
+
+define i32 @canonicalize_and_add_power2_or_zero(i32 %x, i32 %y) {
+; CHECK-LABEL: @canonicalize_and_add_power2_or_zero(
+; CHECK-NEXT: [[NY:%.*]] = sub i32 0, [[Y:%.*]]
+; CHECK-NEXT: [[P2:%.*]] = and i32 [[NY]], [[Y]]
+; CHECK-NEXT: call void @use32(i32 [[P2]])
+; CHECK-NEXT: [[TMP1:%.*]] = xor i32 [[X:%.*]], -1
+; CHECK-NEXT: [[AND:%.*]] = and i32 [[P2]], [[TMP1]]
+; CHECK-NEXT: ret i32 [[AND]]
+;
+ %ny = sub i32 0, %y
+ %p2 = and i32 %y, %ny
+ call void @use32(i32 %p2) ; keep p2
+
+ %val = add i32 %x, %p2
+ %and = and i32 %val, %p2
+ ret i32 %and
+}
+
+define i32 @canonicalize_and_sub_power2_or_zero(i32 %x, i32 %y) {
+; CHECK-LABEL: @canonicalize_and_sub_power2_or_zero(
+; CHECK-NEXT: [[NY:%.*]] = sub i32 0, [[Y:%.*]]
+; CHECK-NEXT: [[P2:%.*]] = and i32 [[NY]], [[Y]]
+; CHECK-NEXT: call void @use32(i32 [[P2]])
+; CHECK-NEXT: [[TMP1:%.*]] = xor i32 [[X:%.*]], -1
+; CHECK-NEXT: [[AND:%.*]] = and i32 [[P2]], [[TMP1]]
+; CHECK-NEXT: ret i32 [[AND]]
+;
+ %ny = sub i32 0, %y
+ %p2 = and i32 %y, %ny
+ call void @use32(i32 %p2) ; keep p2
+
+ %val = sub i32 %x, %p2
+ %and = and i32 %val, %p2
+ ret i32 %and
+}
>From b64ca5b5f743e6a935f4ea09154c3a08c6e65c47 Mon Sep 17 00:00:00 2001
From: Yingwei Zheng <dtcxzyw2333 at gmail.com>
Date: Fri, 6 Oct 2023 17:32:46 +0800
Subject: [PATCH 2/2] fixup! [InstCombine] Canonicalize `(X +/- Y) & Y` into
`~X & Y` when Y is a power of 2
Add additional tests.
---
llvm/test/Transforms/InstCombine/and.ll | 123 ++++++++++++++++++++++++
1 file changed, 123 insertions(+)
diff --git a/llvm/test/Transforms/InstCombine/and.ll b/llvm/test/Transforms/InstCombine/and.ll
index eb39ff9014ff3a4..989640ed41f2d2e 100644
--- a/llvm/test/Transforms/InstCombine/and.ll
+++ b/llvm/test/Transforms/InstCombine/and.ll
@@ -2582,3 +2582,126 @@ define i32 @canonicalize_and_sub_power2_or_zero(i32 %x, i32 %y) {
%and = and i32 %val, %p2
ret i32 %and
}
+
+define i32 @canonicalize_and_add_power2_or_zero_commuted1(i32 %x, i32 %y) {
+; CHECK-LABEL: @canonicalize_and_add_power2_or_zero_commuted1(
+; CHECK-NEXT: [[NY:%.*]] = sub i32 0, [[Y:%.*]]
+; CHECK-NEXT: [[P2:%.*]] = and i32 [[NY]], [[Y]]
+; CHECK-NEXT: call void @use32(i32 [[P2]])
+; CHECK-NEXT: [[TMP1:%.*]] = xor i32 [[X:%.*]], -1
+; CHECK-NEXT: [[AND:%.*]] = and i32 [[P2]], [[TMP1]]
+; CHECK-NEXT: ret i32 [[AND]]
+;
+ %ny = sub i32 0, %y
+ %p2 = and i32 %y, %ny
+ call void @use32(i32 %p2) ; keep p2
+
+ %val = add i32 %p2, %x
+ %and = and i32 %val, %p2
+ ret i32 %and
+}
+
+define i32 @canonicalize_and_add_power2_or_zero_commuted2(i32 %x, i32 %y) {
+; CHECK-LABEL: @canonicalize_and_add_power2_or_zero_commuted2(
+; CHECK-NEXT: [[NY:%.*]] = sub i32 0, [[Y:%.*]]
+; CHECK-NEXT: [[P2:%.*]] = and i32 [[NY]], [[Y]]
+; CHECK-NEXT: call void @use32(i32 [[P2]])
+; CHECK-NEXT: [[TMP1:%.*]] = xor i32 [[X:%.*]], -1
+; CHECK-NEXT: [[AND:%.*]] = and i32 [[P2]], [[TMP1]]
+; CHECK-NEXT: ret i32 [[AND]]
+;
+ %ny = sub i32 0, %y
+ %p2 = and i32 %y, %ny
+ call void @use32(i32 %p2) ; keep p2
+
+ %val = add i32 %x, %p2
+ %and = and i32 %p2, %val
+ ret i32 %and
+}
+
+define i32 @canonicalize_and_add_power2_or_zero_commuted3(i32 %x, i32 %y) {
+; CHECK-LABEL: @canonicalize_and_add_power2_or_zero_commuted3(
+; CHECK-NEXT: [[NY:%.*]] = sub i32 0, [[Y:%.*]]
+; CHECK-NEXT: [[P2:%.*]] = and i32 [[NY]], [[Y]]
+; CHECK-NEXT: call void @use32(i32 [[P2]])
+; CHECK-NEXT: [[TMP1:%.*]] = xor i32 [[X:%.*]], -1
+; CHECK-NEXT: [[AND:%.*]] = and i32 [[P2]], [[TMP1]]
+; CHECK-NEXT: ret i32 [[AND]]
+;
+ %ny = sub i32 0, %y
+ %p2 = and i32 %y, %ny
+ call void @use32(i32 %p2) ; keep p2
+
+ %val = add i32 %p2, %x
+ %and = and i32 %p2, %val
+ ret i32 %and
+}
+
+define i32 @canonicalize_and_sub_power2_or_zero_commuted_nofold(i32 %x, i32 %y) {
+; CHECK-LABEL: @canonicalize_and_sub_power2_or_zero_commuted_nofold(
+; CHECK-NEXT: [[NY:%.*]] = sub i32 0, [[Y:%.*]]
+; CHECK-NEXT: [[P2:%.*]] = and i32 [[NY]], [[Y]]
+; CHECK-NEXT: call void @use32(i32 [[P2]])
+; CHECK-NEXT: [[VAL:%.*]] = sub i32 [[P2]], [[X:%.*]]
+; CHECK-NEXT: [[AND:%.*]] = and i32 [[VAL]], [[P2]]
+; CHECK-NEXT: ret i32 [[AND]]
+;
+ %ny = sub i32 0, %y
+ %p2 = and i32 %y, %ny
+ call void @use32(i32 %p2) ; keep p2
+
+ %val = sub i32 %p2, %x
+ %and = and i32 %val, %p2
+ ret i32 %and
+}
+
+define i32 @canonicalize_and_add_non_power2_or_zero_nofold(i32 %x, i32 %y) {
+; CHECK-LABEL: @canonicalize_and_add_non_power2_or_zero_nofold(
+; CHECK-NEXT: [[VAL:%.*]] = add i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT: [[AND:%.*]] = and i32 [[VAL]], [[Y]]
+; CHECK-NEXT: ret i32 [[AND]]
+;
+ %val = add i32 %x, %y
+ %and = and i32 %val, %y
+ ret i32 %and
+}
+
+define i32 @canonicalize_and_add_power2_or_zero_multiuse_nofold(i32 %x, i32 %y) {
+; CHECK-LABEL: @canonicalize_and_add_power2_or_zero_multiuse_nofold(
+; CHECK-NEXT: [[NY:%.*]] = sub i32 0, [[Y:%.*]]
+; CHECK-NEXT: [[P2:%.*]] = and i32 [[NY]], [[Y]]
+; CHECK-NEXT: call void @use32(i32 [[P2]])
+; CHECK-NEXT: [[VAL:%.*]] = add i32 [[P2]], [[X:%.*]]
+; CHECK-NEXT: call void @use32(i32 [[VAL]])
+; CHECK-NEXT: [[AND:%.*]] = and i32 [[VAL]], [[P2]]
+; CHECK-NEXT: ret i32 [[AND]]
+;
+ %ny = sub i32 0, %y
+ %p2 = and i32 %y, %ny
+ call void @use32(i32 %p2) ; keep p2
+
+ %val = add i32 %x, %p2
+ call void @use32(i32 %val)
+ %and = and i32 %val, %p2
+ ret i32 %and
+}
+
+define i32 @canonicalize_and_sub_power2_or_zero_multiuse_nofold(i32 %x, i32 %y) {
+; CHECK-LABEL: @canonicalize_and_sub_power2_or_zero_multiuse_nofold(
+; CHECK-NEXT: [[NY:%.*]] = sub i32 0, [[Y:%.*]]
+; CHECK-NEXT: [[P2:%.*]] = and i32 [[NY]], [[Y]]
+; CHECK-NEXT: call void @use32(i32 [[P2]])
+; CHECK-NEXT: [[VAL:%.*]] = sub i32 [[X:%.*]], [[P2]]
+; CHECK-NEXT: call void @use32(i32 [[VAL]])
+; CHECK-NEXT: [[AND:%.*]] = and i32 [[VAL]], [[P2]]
+; CHECK-NEXT: ret i32 [[AND]]
+;
+ %ny = sub i32 0, %y
+ %p2 = and i32 %y, %ny
+ call void @use32(i32 %p2) ; keep p2
+
+ %val = sub i32 %x, %p2
+ call void @use32(i32 %val)
+ %and = and i32 %val, %p2
+ ret i32 %and
+}
More information about the flang-commits
mailing list