[ARM] Do not fuse VADD and VMUL, continued (2/2)

This is patch 2/2, following up on D53314, and is the functional change
to prevent fusing mul + add sequences into VFMAs.

Differential revision: https://reviews.llvm.org/D53315

llvm-svn: 344683
This commit is contained in:
Sjoerd Meijer 2018-10-17 10:05:44 +00:00
parent 7c8f91aa60
commit 64cfb74a61
2 changed files with 13 additions and 2 deletions

View File

@ -365,12 +365,14 @@ let RecomputePerFunction = 1 in {
def UseMulOps : Predicate<"Subtarget->useMulOps()">;
// Prefer fused MAC for fp mul + add over fp VMLA / VMLS if they are available.
// But only select them if more precision in FP computation is allowed.
// But only select them if more precision in FP computation is allowed, and when
// they are not slower than a mul + add sequence.
// Do not use them for Darwin platforms.
def UseFusedMAC : Predicate<"(TM.Options.AllowFPOpFusion =="
" FPOpFusion::Fast && "
" Subtarget->hasVFP4()) && "
"!Subtarget->isTargetDarwin()">;
"!Subtarget->isTargetDarwin() &&"
"Subtarget->useFPVMLx()">;
def HasFastVGETLNi32 : Predicate<"!Subtarget->hasSlowVGETLNi32()">;
def HasSlowVGETLNi32 : Predicate<"Subtarget->hasSlowVGETLNi32()">;

View File

@ -1,4 +1,8 @@
; RUN: llc < %s -mtriple=armv7-eabi -mattr=+neon,+vfp4 -fp-contract=fast | FileCheck %s
; RUN: llc < %s -mtriple=arm-arm-eabi -mcpu=cortex-m7 -fp-contract=fast | FileCheck %s
; RUN: llc < %s -mtriple=arm-arm-eabi -mcpu=cortex-m4 -fp-contract=fast | FileCheck %s -check-prefix=DONT-FUSE
; RUN: llc < %s -mtriple=arm-arm-eabi -mcpu=cortex-m33 -fp-contract=fast | FileCheck %s -check-prefix=DONT-FUSE
; Check generated fused MAC and MLS.
define double @fusedMACTest1(double %d1, double %d2, double %d3) {
@ -12,6 +16,11 @@ define double @fusedMACTest1(double %d1, double %d2, double %d3) {
define float @fusedMACTest2(float %f1, float %f2, float %f3) {
;CHECK-LABEL: fusedMACTest2:
;CHECK: vfma.f32
;DONT-FUSE-LABEL: fusedMACTest2:
;DONT-FUSE: vmul.f32
;DONT-FUSE-NEXT: vadd.f32
%1 = fmul float %f1, %f2
%2 = fadd float %1, %f3
ret float %2