RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-12-28 22:43:29 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

PTX: Fix disabling of MAD instruction selection

Browse Source 
llvm-svn: 142352
This commit is contained in:
Justin Holewinski 2011-10-18 13:39:20 +00:00
parent 2faab7dd2a
commit 361b3c9ff2
2 changed files with 24 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
lib/Target/PTX/PTXInstrInfo.td
View File

@ -885,19 +885,26 @@ def : Pat<(f64 (fdiv RegF64:$a, fpimm:$b)),
// FMUL+FADD
def : Pat<(f32 (fadd (fmul RegF32:$a, RegF32:$b), RegF32:$c)),
(FMADrrr32 RndDefault, RegF32:$a, RegF32:$b, RegF32:$c)>;
(FMADrrr32 RndDefault, RegF32:$a, RegF32:$b, RegF32:$c)>,
Requires<[SupportsFMA]>;
def : Pat<(f32 (fadd (fmul RegF32:$a, RegF32:$b), fpimm:$c)),
(FMADrri32 RndDefault, RegF32:$a, RegF32:$b, fpimm:$c)>;
(FMADrri32 RndDefault, RegF32:$a, RegF32:$b, fpimm:$c)>,
Requires<[SupportsFMA]>;
def : Pat<(f32 (fadd (fmul RegF32:$a, fpimm:$b), fpimm:$c)),
(FMADrrr32 RndDefault, RegF32:$a, fpimm:$b, fpimm:$c)>;
(FMADrrr32 RndDefault, RegF32:$a, fpimm:$b, fpimm:$c)>,
Requires<[SupportsFMA]>;
def : Pat<(f32 (fadd (fmul RegF32:$a, RegF32:$b), fpimm:$c)),
(FMADrri32 RndDefault, RegF32:$a, RegF32:$b, fpimm:$c)>;
(FMADrri32 RndDefault, RegF32:$a, RegF32:$b, fpimm:$c)>,
Requires<[SupportsFMA]>;
def : Pat<(f64 (fadd (fmul RegF64:$a, RegF64:$b), RegF64:$c)),
(FMADrrr64 RndDefault, RegF64:$a, RegF64:$b, RegF64:$c)>;
(FMADrrr64 RndDefault, RegF64:$a, RegF64:$b, RegF64:$c)>,
Requires<[SupportsFMA]>;
def : Pat<(f64 (fadd (fmul RegF64:$a, RegF64:$b), fpimm:$c)),
(FMADrri64 RndDefault, RegF64:$a, RegF64:$b, fpimm:$c)>;
(FMADrri64 RndDefault, RegF64:$a, RegF64:$b, fpimm:$c)>,
Requires<[SupportsFMA]>;
def : Pat<(f64 (fadd (fmul RegF64:$a, fpimm:$b), fpimm:$c)),
(FMADrri64 RndDefault, RegF64:$a, fpimm:$b, fpimm:$c)>;
(FMADrri64 RndDefault, RegF64:$a, fpimm:$b, fpimm:$c)>,
Requires<[SupportsFMA]>;
// FNEG
def : Pat<(f32 (fneg RegF32:$a)), (FNEGrr32 RndDefault, RegF32:$a)>;

12
test/CodeGen/PTX/mad-disabling.ll
View File

@ -1,8 +1,13 @@
; RUN: llc < %s -march=ptx32 -mattr=+ptx20,+sm20 | grep "mad"
; RUN: llc < %s -march=ptx32 -mattr=+ptx20,+sm20,+no-fma | grep -v "mad"
; RUN: llc < %s -march=ptx32 -mattr=+ptx20,+sm20 | FileCheck %s -check-prefix=FMA
; RUN: llc < %s -march=ptx32 -mattr=+ptx20,+sm20,+no-fma | FileCheck %s -check-prefix=MUL
; RUN: llc < %s -march=ptx64 -mattr=+ptx20,+sm20 | FileCheck %s -check-prefix=FMA
; RUN: llc < %s -march=ptx64 -mattr=+ptx20,+sm20,+no-fma | FileCheck %s -check-prefix=MUL
define ptx_device float @test_mul_add_f(float %x, float %y, float %z) {
entry:
; FMA: mad.rn.f32
; MUL: mul.rn.f32
; MUL: add.rn.f32
%a = fmul float %x, %y
%b = fadd float %a, %z
ret float %b
@ -10,6 +15,9 @@ entry:
define ptx_device double @test_mul_add_d(double %x, double %y, double %z) {
entry:
; FMA: mad.rn.f64
; MUL: mul.rn.f64
; MUL: add.rn.f64
%a = fmul double %x, %y
%b = fadd double %a, %z
ret double %b