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

[InstCombine] fold fdiv with powi divisor (PR49147) 

This extends b40fde062c for the especially non-standard
powi pattern. We want to avoid being completely wrong
on the negation-of-int-min corner case, so I'm adding
an extra FMF check for 'ninf' assuming that gives us
the flexibility to handle that possibility.
https://llvm.org/PR49147
This commit is contained in:
Sanjay Patel 2021-02-24 16:12:48 -05:00
parent 868d43fbd6
commit a7cee55762
2 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
View File

@ -1294,6 +1294,17 @@ static Instruction *foldFDivPowDivisor(BinaryOperator &I,
Args.push_back(II->getArgOperand(0));
Args.push_back(Builder.CreateFNegFMF(II->getArgOperand(1), &I));
break;
case Intrinsic::powi:
// Require 'ninf' assuming that makes powi(X, -INT_MIN) acceptable.
// That is, X ** (huge negative number) is 0.0, ~1.0, or INF and so
// dividing by that is INF, ~1.0, or 0.0. Code that uses powi allows
// non-standard results, so this corner case should be acceptable if the
// code rules out INF values.
if (!I.hasNoInfs())
return nullptr;
Args.push_back(II->getArgOperand(0));
Args.push_back(Builder.CreateNeg(II->getArgOperand(1)));
break;
case Intrinsic::exp:
case Intrinsic::exp2:
Args.push_back(Builder.CreateFNegFMF(II->getArgOperand(0), &I));

11
llvm/test/Transforms/InstCombine/fdiv.ll
View File

@ -865,8 +865,9 @@ define <2 x half> @exp2_recip(<2 x half> %x, <2 x half> %y) {
define float @powi_divisor(float %x, i32 %y, float %z) {
; CHECK-LABEL: @powi_divisor(
; CHECK-NEXT: [[P:%.*]] = call float @llvm.powi.f32(float [[X:%.*]], i32 [[Y:%.*]])
; CHECK-NEXT: [[R:%.*]] = fdiv reassoc ninf arcp float [[Z:%.*]], [[P]]
; CHECK-NEXT: [[TMP1:%.*]] = sub i32 0, [[Y:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = call reassoc ninf arcp float @llvm.powi.f32(float [[X:%.*]], i32 [[TMP1]])
; CHECK-NEXT: [[R:%.*]] = fmul reassoc ninf arcp float [[TMP2]], [[Z:%.*]]
; CHECK-NEXT: ret float [[R]]
;
%p = call float @llvm.powi.f32(float %x, i32 %y)
@ -919,9 +920,9 @@ define float @powi_divisor_not_enough_fmf2(float %x, i32 %y, float %z) {
define <2 x half> @powi_recip(<2 x half> %x, i32 %y) {
; CHECK-LABEL: @powi_recip(
; CHECK-NEXT: [[P:%.*]] = call <2 x half> @llvm.powi.v2f16(<2 x half> [[X:%.*]], i32 [[Y:%.*]])
; CHECK-NEXT: [[R:%.*]] = fdiv reassoc nnan ninf arcp <2 x half> <half 0xH3C00, half 0xH3C00>, [[P]]
; CHECK-NEXT: ret <2 x half> [[R]]
; CHECK-NEXT: [[TMP1:%.*]] = sub i32 0, [[Y:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = call reassoc nnan ninf arcp <2 x half> @llvm.powi.v2f16(<2 x half> [[X:%.*]], i32 [[TMP1]])
; CHECK-NEXT: ret <2 x half> [[TMP2]]
;
%p = call <2 x half> @llvm.powi.v2f16(<2 x half> %x, i32 %y)
%r = fdiv reassoc arcp nnan ninf <2 x half> <half 1.0, half 1.0>, %p