diff options
Diffstat (limited to 'llvm')
| -rw-r--r-- | llvm/lib/Target/PTX/PTXInstrInfo.td | 21 | ||||
| -rw-r--r-- | llvm/test/CodeGen/PTX/mad-disabling.ll | 12 |
2 files changed, 24 insertions, 9 deletions
diff --git a/llvm/lib/Target/PTX/PTXInstrInfo.td b/llvm/lib/Target/PTX/PTXInstrInfo.td index a3fcea9038c..fbddac5ce7d 100644 --- a/llvm/lib/Target/PTX/PTXInstrInfo.td +++ b/llvm/lib/Target/PTX/PTXInstrInfo.td @@ -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)>; diff --git a/llvm/test/CodeGen/PTX/mad-disabling.ll b/llvm/test/CodeGen/PTX/mad-disabling.ll index ad7b3417ec4..603c3ba69f7 100644 --- a/llvm/test/CodeGen/PTX/mad-disabling.ll +++ b/llvm/test/CodeGen/PTX/mad-disabling.ll @@ -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 |
