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

ARM64: fix fmsub patterns which assumed accum operand was first 

Confusingly, the NEON fmla instructions put the accumulator first but the
scalar versions put it at the end (like the fma lib function & LLVM's
intrinsic).

This should fix PR19345, assuming there's only one issue.

llvm-svn: 205758
This commit is contained in:
Tim Northover 2014-04-08 12:23:51 +00:00
parent 6c6bbfab19
commit 33d07468bc
2 changed files with 17 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
llvm/lib/Target/ARM64/ARM64InstrInfo.td
View File

@ -2009,11 +2009,14 @@ defm FNMSUB : ThreeOperandFPData<1, 1, "fnmsub",
// The following def pats catch the case where the LHS of an FMA is negated.
// The TriOpFrag above catches the case where the middle operand is negated.
def : Pat<(f32 (fma (fneg FPR32:$Rn), FPR32:$Rm, FPR32:$Rd)),
(FMSUBSrrr FPR32:$Rd, FPR32:$Rn, FPR32:$Rm)>;
def : Pat<(f64 (fma (fneg FPR64:$Rn), FPR64:$Rm, FPR64:$Rd)),
(FMSUBDrrr FPR64:$Rd, FPR64:$Rn, FPR64:$Rm)>;
// N.b. FMSUB etc have the accumulator at the *end* of (outs), unlike
// the NEON variant.
def : Pat<(f32 (fma (fneg FPR32:$Rn), FPR32:$Rm, FPR32:$Ra)),
(FMSUBSrrr FPR32:$Rn, FPR32:$Rm, FPR32:$Ra)>;
def : Pat<(f64 (fma (fneg FPR64:$Rn), FPR64:$Rm, FPR64:$Ra)),
(FMSUBDrrr FPR64:$Rn, FPR64:$Rm, FPR64:$Ra)>;
//===----------------------------------------------------------------------===//
// Floating point comparison instructions.

20
llvm/test/CodeGen/ARM64/fmadd.ll
View File

@ -3,7 +3,7 @@
define float @fma32(float %a, float %b, float %c) nounwind readnone ssp {
entry:
; CHECK-LABEL: fma32:
; CHECK: fmadd
; CHECK: fmadd s0, s0, s1, s2
%0 = tail call float @llvm.fma.f32(float %a, float %b, float %c)
ret float %0
}
@ -11,7 +11,7 @@ entry:
define float @fnma32(float %a, float %b, float %c) nounwind readnone ssp {
entry:
; CHECK-LABEL: fnma32:
; CHECK: fnmadd
; CHECK: fnmadd s0, s0, s1, s2
%0 = tail call float @llvm.fma.f32(float %a, float %b, float %c)
%mul = fmul float %0, -1.000000e+00
ret float %mul
@ -20,7 +20,7 @@ entry:
define float @fms32(float %a, float %b, float %c) nounwind readnone ssp {
entry:
; CHECK-LABEL: fms32:
; CHECK: fmsub
; CHECK: fmsub s0, s0, s1, s2
%mul = fmul float %b, -1.000000e+00
%0 = tail call float @llvm.fma.f32(float %a, float %mul, float %c)
ret float %0
@ -29,7 +29,7 @@ entry:
define float @fms32_com(float %a, float %b, float %c) nounwind readnone ssp {
entry:
; CHECK-LABEL: fms32_com:
; CHECK: fmsub
; CHECK: fmsub s0, s1, s0, s2
%mul = fmul float %b, -1.000000e+00
%0 = tail call float @llvm.fma.f32(float %mul, float %a, float %c)
ret float %0
@ -38,7 +38,7 @@ entry:
define float @fnms32(float %a, float %b, float %c) nounwind readnone ssp {
entry:
; CHECK-LABEL: fnms32:
; CHECK: fnmsub
; CHECK: fnmsub s0, s0, s1, s2
%mul = fmul float %c, -1.000000e+00
%0 = tail call float @llvm.fma.f32(float %a, float %b, float %mul)
ret float %0
@ -46,7 +46,7 @@ entry:
define double @fma64(double %a, double %b, double %c) nounwind readnone ssp {
; CHECK-LABEL: fma64:
; CHECK: fmadd
; CHECK: fmadd d0, d0, d1, d2
entry:
%0 = tail call double @llvm.fma.f64(double %a, double %b, double %c)
ret double %0
@ -54,7 +54,7 @@ entry:
define double @fnma64(double %a, double %b, double %c) nounwind readnone ssp {
; CHECK-LABEL: fnma64:
; CHECK: fnmadd
; CHECK: fnmadd d0, d0, d1, d2
entry:
%0 = tail call double @llvm.fma.f64(double %a, double %b, double %c)
%mul = fmul double %0, -1.000000e+00
@ -63,7 +63,7 @@ entry:
define double @fms64(double %a, double %b, double %c) nounwind readnone ssp {
; CHECK-LABEL: fms64:
; CHECK: fmsub
; CHECK: fmsub d0, d0, d1, d2
entry:
%mul = fmul double %b, -1.000000e+00
%0 = tail call double @llvm.fma.f64(double %a, double %mul, double %c)
@ -72,7 +72,7 @@ entry:
define double @fms64_com(double %a, double %b, double %c) nounwind readnone ssp {
; CHECK-LABEL: fms64_com:
; CHECK: fmsub
; CHECK: fmsub d0, d1, d0, d2
entry:
%mul = fmul double %b, -1.000000e+00
%0 = tail call double @llvm.fma.f64(double %mul, double %a, double %c)
@ -81,7 +81,7 @@ entry:
define double @fnms64(double %a, double %b, double %c) nounwind readnone ssp {
; CHECK-LABEL: fnms64:
; CHECK: fnmsub
; CHECK: fnmsub d0, d0, d1, d2
entry:
%mul = fmul double %c, -1.000000e+00
%0 = tail call double @llvm.fma.f64(double %a, double %b, double %mul)