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

Utilize new SDNode flag functionality to expand current support for fmul 

Summary: This patch originated from D46562 and is a proper subset, with some issues addressed for fmul.

Reviewers: spatel, hfinkel, wristow, arsenm

Reviewed By: spatel

Subscribers: nhaehnle, wdng

Differential Revision: https://reviews.llvm.org/D47911

llvm-svn: 334514
This commit is contained in:
Michael Berg 2018-06-12 16:13:11 +00:00
parent e39fa6cbbb
commit 5d49f66570
3 changed files with 19 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -10542,12 +10542,15 @@ SDValue DAGCombiner::visitFMUL(SDNode *N) {
if (SDValue NewSel = foldBinOpIntoSelect(N))
return NewSel;
if (Options.UnsafeFPMath) {
if (Options.UnsafeFPMath ||
(Flags.hasNoNaNs() && Flags.hasNoSignedZeros())) {
// fold (fmul A, 0) -> 0
if (N1CFP && N1CFP->isZero())
return N1;
}
// fmul (fmul X, C1), X2 -> fmul X, C1 * C2
if (Options.UnsafeFPMath || Flags.hasAllowReassociation()) {
// fmul (fmul X, C1), C2 -> fmul X, C1 * C2
if (N0.getOpcode() == ISD::FMUL) {
// Fold scalars or any vector constants (not just splats).
// This fold is done in general by InstCombine, but extra fmul insts

2
llvm/test/CodeGen/X86/fmul-combines.ll
View File

@ -92,7 +92,6 @@ define <4 x float> @fmul_v4f32_two_consts_no_splat_reassoc(<4 x float> %x) {
; CHECK-LABEL: fmul_v4f32_two_consts_no_splat_reassoc:
; CHECK: # %bb.0:
; CHECK-NEXT: mulps {{.*}}(%rip), %xmm0
; CHECK-NEXT: mulps {{.*}}(%rip), %xmm0
; CHECK-NEXT: retq
%y = fmul <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 4.0>
%z = fmul reassoc <4 x float> %y, <float 5.0, float 6.0, float 7.0, float 8.0>
@ -104,7 +103,6 @@ define <4 x float> @fmul_v4f32_two_consts_no_splat_reassoc(<4 x float> %x) {
define <4 x float> @fmul_v4f32_two_consts_no_splat_reassoc_2(<4 x float> %x) {
; CHECK-LABEL: fmul_v4f32_two_consts_no_splat_reassoc_2:
; CHECK: # %bb.0:
; CHECK-NEXT: addps %xmm0, %xmm0
; CHECK-NEXT: mulps {{.*}}(%rip), %xmm0
; CHECK-NEXT: retq
%y = fadd <4 x float> %x, %x

25
llvm/test/CodeGen/X86/fp-fold.ll
View File

@ -101,18 +101,11 @@ define float @fsub_negzero_nsz(float %x) {
ret float %r
}
; TODO: handle x*0 for fast flags the same as unsafe
define float @fmul_zero(float %x) {
; STRICT-LABEL: fmul_zero:
; STRICT: # %bb.0:
; STRICT-NEXT: xorps %xmm1, %xmm1
; STRICT-NEXT: mulss %xmm1, %xmm0
; STRICT-NEXT: retq
;
; UNSAFE-LABEL: fmul_zero:
; UNSAFE: # %bb.0:
; UNSAFE-NEXT: xorps %xmm0, %xmm0
; UNSAFE-NEXT: retq
; ANY-LABEL: fmul_zero:
; ANY: # %bb.0:
; ANY-NEXT: xorps %xmm0, %xmm0
; ANY-NEXT: retq
%r = fmul nnan nsz float %x, 0.0
ret float %r
}
@ -124,3 +117,13 @@ define float @fmul_one(float %x) {
%r = fmul float %x, 1.0
ret float %r
}
define float @fmul_x_const_const(float %x) {
; ANY-LABEL: fmul_x_const_const:
; ANY: # %bb.0:
; ANY-NEXT: mulss {{.*}}(%rip), %xmm0
; ANY-NEXT: retq
%mul = fmul reassoc float %x, 9.0
%r = fmul reassoc float %mul, 4.0
ret float %r
}