[InstCombine] Optimize always overflowing signed saturating add/sub

Based on the overflow direction information added in D62463, we can
now fold always overflowing signed saturating add/sub to signed min/max.

Differential Revision: https://reviews.llvm.org/D62544

llvm-svn: 362006
This commit is contained in:
Nikita Popov 2019-05-29 18:37:13 +00:00
parent 5feead5752
commit 5382803b04
2 changed files with 16 additions and 24 deletions

View File

@ -13,6 +13,7 @@
#include "InstCombineInternal.h"
#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/APSInt.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/None.h"
#include "llvm/ADT/Optional.h"
@ -2053,6 +2054,7 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
case Intrinsic::usub_sat:
case Intrinsic::ssub_sat: {
SaturatingInst *SI = cast<SaturatingInst>(II);
Type *Ty = SI->getType();
Value *Arg0 = SI->getLHS();
Value *Arg1 = SI->getRHS();
@ -2067,14 +2069,16 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
return BinaryOperator::CreateNSW(SI->getBinaryOp(), Arg0, Arg1);
else
return BinaryOperator::CreateNUW(SI->getBinaryOp(), Arg0, Arg1);
case OverflowResult::AlwaysOverflowsLow:
if (SI->isSigned()) break; // TODO: Support signed.
return replaceInstUsesWith(*SI,
ConstantInt::getNullValue(II->getType()));
case OverflowResult::AlwaysOverflowsHigh:
if (SI->isSigned()) break; // TODO: Support signed.
return replaceInstUsesWith(*SI,
ConstantInt::getAllOnesValue(II->getType()));
case OverflowResult::AlwaysOverflowsLow: {
unsigned BitWidth = Ty->getScalarSizeInBits();
APInt Min = APSInt::getMinValue(BitWidth, !SI->isSigned());
return replaceInstUsesWith(*SI, ConstantInt::get(Ty, Min));
}
case OverflowResult::AlwaysOverflowsHigh: {
unsigned BitWidth = Ty->getScalarSizeInBits();
APInt Max = APSInt::getMaxValue(BitWidth, !SI->isSigned());
return replaceInstUsesWith(*SI, ConstantInt::get(Ty, Max));
}
}
// ssub.sat(X, C) -> sadd.sat(X, -C) if C != MIN

View File

@ -341,10 +341,7 @@ define <2 x i8> @test_vector_sadd_neg_neg(<2 x i8> %a) {
define i8 @test_scalar_sadd_always_overflows_low(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_always_overflows_low(
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i8 [[A:%.*]], -120
; CHECK-NEXT: [[MIN:%.*]] = select i1 [[CMP]], i8 [[A]], i8 -120
; CHECK-NEXT: [[R:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[MIN]], i8 -10)
; CHECK-NEXT: ret i8 [[R]]
; CHECK-NEXT: ret i8 -128
;
%cmp = icmp slt i8 %a, -120
%min = select i1 %cmp, i8 %a, i8 -120
@ -354,10 +351,7 @@ define i8 @test_scalar_sadd_always_overflows_low(i8 %a) {
define i8 @test_scalar_sadd_always_overflows_high(i8 %a) {
; CHECK-LABEL: @test_scalar_sadd_always_overflows_high(
; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i8 [[A:%.*]], 120
; CHECK-NEXT: [[MAX:%.*]] = select i1 [[CMP]], i8 [[A]], i8 120
; CHECK-NEXT: [[R:%.*]] = call i8 @llvm.sadd.sat.i8(i8 [[MAX]], i8 10)
; CHECK-NEXT: ret i8 [[R]]
; CHECK-NEXT: ret i8 127
;
%cmp = icmp sgt i8 %a, 120
%max = select i1 %cmp, i8 %a, i8 120
@ -829,10 +823,7 @@ define <2 x i8> @test_vector_ssub_neg_nneg(<2 x i8> %a) {
define i8 @test_scalar_ssub_always_overflows_low(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_always_overflows_low(
; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i8 [[A:%.*]], 120
; CHECK-NEXT: [[MAX:%.*]] = select i1 [[CMP]], i8 [[A]], i8 120
; CHECK-NEXT: [[R:%.*]] = call i8 @llvm.ssub.sat.i8(i8 -10, i8 [[MAX]])
; CHECK-NEXT: ret i8 [[R]]
; CHECK-NEXT: ret i8 -128
;
%cmp = icmp sgt i8 %a, 120
%max = select i1 %cmp, i8 %a, i8 120
@ -842,10 +833,7 @@ define i8 @test_scalar_ssub_always_overflows_low(i8 %a) {
define i8 @test_scalar_ssub_always_overflows_high(i8 %a) {
; CHECK-LABEL: @test_scalar_ssub_always_overflows_high(
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i8 [[A:%.*]], -120
; CHECK-NEXT: [[MIN:%.*]] = select i1 [[CMP]], i8 [[A]], i8 -120
; CHECK-NEXT: [[R:%.*]] = call i8 @llvm.ssub.sat.i8(i8 10, i8 [[MIN]])
; CHECK-NEXT: ret i8 [[R]]
; CHECK-NEXT: ret i8 127
;
%cmp = icmp slt i8 %a, -120
%min = select i1 %cmp, i8 %a, i8 -120