diff options
author | Dimitry Andric <dim@FreeBSD.org> | 2016-07-23 20:41:05 +0000 |
---|---|---|
committer | Dimitry Andric <dim@FreeBSD.org> | 2016-07-23 20:41:05 +0000 |
commit | 01095a5d43bbfde13731688ddcf6048ebb8b7721 (patch) | |
tree | 4def12e759965de927d963ac65840d663ef9d1ea /test/CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll | |
parent | f0f4822ed4b66e3579e92a89f368f8fb860e218e (diff) |
Diffstat (limited to 'test/CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll')
-rw-r--r-- | test/CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll | 94 |
1 files changed, 47 insertions, 47 deletions
diff --git a/test/CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll b/test/CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll index f388f8ffe2930..461caf5b5d204 100644 --- a/test/CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll +++ b/test/CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll @@ -1,58 +1,58 @@ -;RUN: llc < %s -march=r600 -mcpu=cayman +; RUN: llc -march=r600 -mcpu=cayman < %s -define void @main(<4 x float> inreg, <4 x float> inreg) #0 { +define amdgpu_ps void @main(<4 x float> inreg %arg, <4 x float> inreg %arg1) { main_body: - %2 = extractelement <4 x float> %0, i32 0 - %3 = extractelement <4 x float> %0, i32 1 - %4 = extractelement <4 x float> %0, i32 2 - %5 = extractelement <4 x float> %0, i32 3 - %6 = insertelement <4 x float> undef, float %2, i32 0 - %7 = insertelement <4 x float> %6, float %3, i32 1 - %8 = insertelement <4 x float> %7, float %4, i32 2 - %9 = insertelement <4 x float> %8, float %5, i32 3 - %10 = call <4 x float> @llvm.AMDGPU.cube(<4 x float> %9) - %11 = extractelement <4 x float> %10, i32 0 - %12 = extractelement <4 x float> %10, i32 1 - %13 = extractelement <4 x float> %10, i32 2 - %14 = extractelement <4 x float> %10, i32 3 - %15 = call float @fabs(float %13) - %16 = fdiv float 1.000000e+00, %15 - %17 = fmul float %11, %16 - %18 = fadd float %17, 1.500000e+00 - %19 = fmul float %12, %16 - %20 = fadd float %19, 1.500000e+00 - %21 = insertelement <4 x float> undef, float %20, i32 0 - %22 = insertelement <4 x float> %21, float %18, i32 1 - %23 = insertelement <4 x float> %22, float %14, i32 2 - %24 = insertelement <4 x float> %23, float %5, i32 3 - %25 = extractelement <4 x float> %24, i32 0 - %26 = extractelement <4 x float> %24, i32 1 - %27 = extractelement <4 x float> %24, i32 2 - %28 = extractelement <4 x float> %24, i32 3 - %29 = insertelement <4 x float> undef, float %25, i32 0 - %30 = insertelement <4 x float> %29, float %26, i32 1 - %31 = insertelement <4 x float> %30, float %27, i32 2 - %32 = insertelement <4 x float> %31, float %28, i32 3 - %33 = call <4 x float> @llvm.AMDGPU.tex(<4 x float> %32, i32 16, i32 0, i32 13) - %34 = extractelement <4 x float> %33, i32 0 - %35 = insertelement <4 x float> undef, float %34, i32 0 - %36 = insertelement <4 x float> %35, float %34, i32 1 - %37 = insertelement <4 x float> %36, float %34, i32 2 - %38 = insertelement <4 x float> %37, float 1.000000e+00, i32 3 - call void @llvm.R600.store.swizzle(<4 x float> %38, i32 0, i32 0) + %tmp = extractelement <4 x float> %arg, i32 0 + %tmp2 = extractelement <4 x float> %arg, i32 1 + %tmp3 = extractelement <4 x float> %arg, i32 2 + %tmp4 = extractelement <4 x float> %arg, i32 3 + %tmp5 = insertelement <4 x float> undef, float %tmp, i32 0 + %tmp6 = insertelement <4 x float> %tmp5, float %tmp2, i32 1 + %tmp7 = insertelement <4 x float> %tmp6, float %tmp3, i32 2 + %tmp8 = insertelement <4 x float> %tmp7, float %tmp4, i32 3 + %tmp9 = call <4 x float> @llvm.AMDGPU.cube(<4 x float> %tmp8) + %tmp10 = extractelement <4 x float> %tmp9, i32 0 + %tmp11 = extractelement <4 x float> %tmp9, i32 1 + %tmp12 = extractelement <4 x float> %tmp9, i32 2 + %tmp13 = extractelement <4 x float> %tmp9, i32 3 + %tmp14 = call float @fabs(float %tmp12) + %tmp15 = fdiv float 1.000000e+00, %tmp14 + %tmp16 = fmul float %tmp10, %tmp15 + %tmp17 = fadd float %tmp16, 1.500000e+00 + %tmp18 = fmul float %tmp11, %tmp15 + %tmp19 = fadd float %tmp18, 1.500000e+00 + %tmp20 = insertelement <4 x float> undef, float %tmp19, i32 0 + %tmp21 = insertelement <4 x float> %tmp20, float %tmp17, i32 1 + %tmp22 = insertelement <4 x float> %tmp21, float %tmp13, i32 2 + %tmp23 = insertelement <4 x float> %tmp22, float %tmp4, i32 3 + %tmp24 = extractelement <4 x float> %tmp23, i32 0 + %tmp25 = extractelement <4 x float> %tmp23, i32 1 + %tmp26 = extractelement <4 x float> %tmp23, i32 2 + %tmp27 = extractelement <4 x float> %tmp23, i32 3 + %tmp28 = insertelement <4 x float> undef, float %tmp24, i32 0 + %tmp29 = insertelement <4 x float> %tmp28, float %tmp25, i32 1 + %tmp30 = insertelement <4 x float> %tmp29, float %tmp26, i32 2 + %tmp31 = insertelement <4 x float> %tmp30, float %tmp27, i32 3 + %tmp32 = shufflevector <4 x float> %tmp31, <4 x float> %tmp31, <4 x i32> <i32 0, i32 1, i32 2, i32 3> + %tmp33 = call <4 x float> @llvm.r600.texc(<4 x float> %tmp32, i32 0, i32 0, i32 0, i32 16, i32 0, i32 1, i32 1, i32 1, i32 1) + %tmp34 = extractelement <4 x float> %tmp33, i32 0 + %tmp35 = insertelement <4 x float> undef, float %tmp34, i32 0 + %tmp36 = insertelement <4 x float> %tmp35, float %tmp34, i32 1 + %tmp37 = insertelement <4 x float> %tmp36, float %tmp34, i32 2 + %tmp38 = insertelement <4 x float> %tmp37, float 1.000000e+00, i32 3 + call void @llvm.r600.store.swizzle(<4 x float> %tmp38, i32 0, i32 0) ret void } ; Function Attrs: readnone -declare <4 x float> @llvm.AMDGPU.cube(<4 x float>) #1 +declare <4 x float> @llvm.AMDGPU.cube(<4 x float>) #0 ; Function Attrs: readnone -declare float @fabs(float) #1 +declare float @fabs(float) #0 -; Function Attrs: readnone -declare <4 x float> @llvm.AMDGPU.tex(<4 x float>, i32, i32, i32) #1 +declare void @llvm.r600.store.swizzle(<4 x float>, i32, i32) -declare void @llvm.R600.store.swizzle(<4 x float>, i32, i32) +; Function Attrs: readnone +declare <4 x float> @llvm.r600.texc(<4 x float>, i32, i32, i32, i32, i32, i32, i32, i32, i32) #0 -attributes #0 = { "ShaderType"="0" } -attributes #1 = { readnone } +attributes #0 = { nounwind readnone } |