maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[InstCombine] Fold a shifty implementation of clamp-to-zero. 

Summary:
Fold
and(ashr(subNSW(Y, X), ScalarSizeInBits(Y)-1), X)
into
X s> Y ? X : 0

https://rise4fun.com/Alive/lFH

Fold shift into select enables more optimization,
e.g., vmax generation for ARM target.

Reviewers: lebedev.ri, efriedma, spatel, kparzysz, bcahoon

Reviewed By: lebedev.ri

Subscribers: xbolva00, andreadb, craig.topper, RKSimon, kristof.beyls, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67799

llvm-svn: 372676
This commit is contained in:
Huihui Zhang 2019-09-24 00:15:03 +00:00
parent adec1209e6
commit 8952199715
2 changed files with 36 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
llvm/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
View File

@ -1926,6 +1926,20 @@ Instruction *InstCombiner::visitAnd(BinaryOperator &I) {
A->getType()->isIntOrIntVectorTy(1))
return SelectInst::Create(A, Op0, Constant::getNullValue(I.getType()));
// and(ashr(subNSW(Y, X), ScalarSizeInBits(Y)-1), X) --> X s> Y ? X : 0.
{
Value *X, *Y;
const APInt *ShAmt;
Type *Ty = I.getType();
if (match(&I, m_c_And(m_OneUse(m_AShr(m_NSWSub(m_Value(Y), m_Value(X)),
m_APInt(ShAmt))),
m_Deferred(X))) &&
*ShAmt == Ty->getScalarSizeInBits() - 1) {
Value *NewICmpInst = Builder.CreateICmpSGT(X, Y);
return SelectInst::Create(NewICmpInst, X, ConstantInt::getNullValue(Ty));
}
}
return nullptr;
}

54
llvm/test/Transforms/InstCombine/sub-ashr-and-to-icmp-select.ll
View File

@ -12,9 +12,8 @@
define i8 @sub_ashr_and_i8(i8 %x, i8 %y) {
; CHECK-LABEL: @sub_ashr_and_i8(
; CHECK-NEXT: [[SUB:%.*]] = sub nsw i8 [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr i8 [[SUB]], 7
; CHECK-NEXT: [[AND:%.*]] = and i8 [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i8 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select i1 [[TMP1]], i8 [[X]], i8 0
; CHECK-NEXT: ret i8 [[AND]]
;
%sub = sub nsw i8 %y, %x
@ -25,9 +24,8 @@ define i8 @sub_ashr_and_i8(i8 %x, i8 %y) {
define i16 @sub_ashr_and_i16(i16 %x, i16 %y) {
; CHECK-LABEL: @sub_ashr_and_i16(
; CHECK-NEXT: [[SUB:%.*]] = sub nsw i16 [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr i16 [[SUB]], 15
; CHECK-NEXT: [[AND:%.*]] = and i16 [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i16 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select i1 [[TMP1]], i16 [[X]], i16 0
; CHECK-NEXT: ret i16 [[AND]]
;
@ -39,9 +37,8 @@ define i16 @sub_ashr_and_i16(i16 %x, i16 %y) {
define i32 @sub_ashr_and_i32(i32 %x, i32 %y) {
; CHECK-LABEL: @sub_ashr_and_i32(
; CHECK-NEXT: [[SUB:%.*]] = sub nsw i32 [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr i32 [[SUB]], 31
; CHECK-NEXT: [[AND:%.*]] = and i32 [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 0
; CHECK-NEXT: ret i32 [[AND]]
;
%sub = sub nsw i32 %y, %x
@ -52,9 +49,8 @@ define i32 @sub_ashr_and_i32(i32 %x, i32 %y) {
define i64 @sub_ashr_and_i64(i64 %x, i64 %y) {
; CHECK-LABEL: @sub_ashr_and_i64(
; CHECK-NEXT: [[SUB:%.*]] = sub nsw i64 [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr i64 [[SUB]], 63
; CHECK-NEXT: [[AND:%.*]] = and i64 [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i64 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select i1 [[TMP1]], i64 [[X]], i64 0
; CHECK-NEXT: ret i64 [[AND]]
;
%sub = sub nsw i64 %y, %x
@ -67,9 +63,8 @@ define i64 @sub_ashr_and_i64(i64 %x, i64 %y) {
define i32 @sub_ashr_and_i32_nuw_nsw(i32 %x, i32 %y) {
; CHECK-LABEL: @sub_ashr_and_i32_nuw_nsw(
; CHECK-NEXT: [[SUB:%.*]] = sub nuw nsw i32 [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr i32 [[SUB]], 31
; CHECK-NEXT: [[AND:%.*]] = and i32 [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 0
; CHECK-NEXT: ret i32 [[AND]]
;
%sub = sub nuw nsw i32 %y, %x
@ -82,9 +77,8 @@ define i32 @sub_ashr_and_i32_nuw_nsw(i32 %x, i32 %y) {
define i32 @sub_ashr_and_i32_commute(i32 %x, i32 %y) {
; CHECK-LABEL: @sub_ashr_and_i32_commute(
; CHECK-NEXT: [[SUB:%.*]] = sub nsw i32 [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr i32 [[SUB]], 31
; CHECK-NEXT: [[AND:%.*]] = and i32 [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 0
; CHECK-NEXT: ret i32 [[AND]]
;
%sub = sub nsw i32 %y, %x
@ -97,9 +91,8 @@ define i32 @sub_ashr_and_i32_commute(i32 %x, i32 %y) {
define <4 x i32> @sub_ashr_and_i32_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @sub_ashr_and_i32_vec(
; CHECK-NEXT: [[SUB:%.*]] = sub nsw <4 x i32> [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr <4 x i32> [[SUB]], <i32 31, i32 31, i32 31, i32 31>
; CHECK-NEXT: [[AND:%.*]] = and <4 x i32> [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt <4 x i32> [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select <4 x i1> [[TMP1]], <4 x i32> [[X]], <4 x i32> zeroinitializer
; CHECK-NEXT: ret <4 x i32> [[AND]]
;
%sub = sub nsw <4 x i32> %y, %x
@ -110,9 +103,8 @@ define <4 x i32> @sub_ashr_and_i32_vec(<4 x i32> %x, <4 x i32> %y) {
define <4 x i32> @sub_ashr_and_i32_vec_nuw_nsw(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @sub_ashr_and_i32_vec_nuw_nsw(
; CHECK-NEXT: [[SUB:%.*]] = sub nuw nsw <4 x i32> [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr <4 x i32> [[SUB]], <i32 31, i32 31, i32 31, i32 31>
; CHECK-NEXT: [[AND:%.*]] = and <4 x i32> [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt <4 x i32> [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select <4 x i1> [[TMP1]], <4 x i32> [[X]], <4 x i32> zeroinitializer
; CHECK-NEXT: ret <4 x i32> [[AND]]
;
%sub = sub nuw nsw <4 x i32> %y, %x
@ -123,9 +115,8 @@ define <4 x i32> @sub_ashr_and_i32_vec_nuw_nsw(<4 x i32> %x, <4 x i32> %y) {
define <4 x i32> @sub_ashr_and_i32_vec_commute(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @sub_ashr_and_i32_vec_commute(
; CHECK-NEXT: [[SUB:%.*]] = sub nsw <4 x i32> [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr <4 x i32> [[SUB]], <i32 31, i32 31, i32 31, i32 31>
; CHECK-NEXT: [[AND:%.*]] = and <4 x i32> [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt <4 x i32> [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select <4 x i1> [[TMP1]], <4 x i32> [[X]], <4 x i32> zeroinitializer
; CHECK-NEXT: ret <4 x i32> [[AND]]
;
%sub = sub nsw <4 x i32> %y, %x
@ -140,8 +131,8 @@ define i32 @sub_ashr_and_i32_extra_use_sub(i32 %x, i32 %y, i32* %p) {
; CHECK-LABEL: @sub_ashr_and_i32_extra_use_sub(
; CHECK-NEXT: [[SUB:%.*]] = sub nsw i32 [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: store i32 [[SUB]], i32* [[P:%.*]], align 4
; CHECK-NEXT: [[SHR:%.*]] = ashr i32 [[SUB]], 31
; CHECK-NEXT: [[AND:%.*]] = and i32 [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[Y]], [[X]]
; CHECK-NEXT: [[AND:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 0
; CHECK-NEXT: ret i32 [[AND]]
;
%sub = sub nsw i32 %y, %x
@ -153,9 +144,8 @@ define i32 @sub_ashr_and_i32_extra_use_sub(i32 %x, i32 %y, i32* %p) {
define i32 @sub_ashr_and_i32_extra_use_and(i32 %x, i32 %y, i32* %p) {
; CHECK-LABEL: @sub_ashr_and_i32_extra_use_and(
; CHECK-NEXT: [[SUB:%.*]] = sub nsw i32 [[Y:%.*]], [[X:%.*]]
; CHECK-NEXT: [[SHR:%.*]] = ashr i32 [[SUB]], 31
; CHECK-NEXT: [[AND:%.*]] = and i32 [[SHR]], [[X]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[X:%.*]], [[Y:%.*]]
; CHECK-NEXT: [[AND:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 0
; CHECK-NEXT: store i32 [[AND]], i32* [[P:%.*]], align 4
; CHECK-NEXT: ret i32 [[AND]]
;