diff options
| -rw-r--r-- | llvm/test/CodeGen/R600/ffloor.f64.ll | 105 | ||||
| -rw-r--r-- | llvm/test/CodeGen/R600/ffloor.ll | 131 | ||||
| -rw-r--r-- | llvm/test/CodeGen/R600/floor.ll | 7 | ||||
| -rw-r--r-- | llvm/test/CodeGen/R600/llvm.floor.ll | 54 |
4 files changed, 146 insertions, 151 deletions
diff --git a/llvm/test/CodeGen/R600/ffloor.f64.ll b/llvm/test/CodeGen/R600/ffloor.f64.ll new file mode 100644 index 00000000000..194d0aaa181 --- /dev/null +++ b/llvm/test/CodeGen/R600/ffloor.f64.ll @@ -0,0 +1,105 @@ +; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s +; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s + +declare double @llvm.floor.f64(double) nounwind readnone +declare <2 x double> @llvm.floor.v2f64(<2 x double>) nounwind readnone +declare <3 x double> @llvm.floor.v3f64(<3 x double>) nounwind readnone +declare <4 x double> @llvm.floor.v4f64(<4 x double>) nounwind readnone +declare <8 x double> @llvm.floor.v8f64(<8 x double>) nounwind readnone +declare <16 x double> @llvm.floor.v16f64(<16 x double>) nounwind readnone + +; FUNC-LABEL: {{^}}ffloor_f64: +; CI: v_floor_f64_e32 + +; SI: s_bfe_u32 [[SEXP:s[0-9]+]], {{s[0-9]+}}, 0xb0014 +; SI: s_add_i32 s{{[0-9]+}}, [[SEXP]], 0xfffffc01 +; SI: s_lshr_b64 +; SI: s_not_b64 +; SI: s_and_b64 +; SI-DAG: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000 +; SI-DAG: cmp_lt_i32 +; SI: cndmask_b32 +; SI: cndmask_b32 +; SI: cmp_gt_i32 +; SI: cndmask_b32 +; SI: cndmask_b32 +; SI: v_cmp_lg_f64 +; SI: v_cmp_lt_f64 +; SI: s_and_b64 +; SI: v_cndmask_b32 +; SI: v_cndmask_b32 +; SI: v_add_f64 +; SI: s_endpgm +define void @ffloor_f64(double addrspace(1)* %out, double %x) { + %y = call double @llvm.floor.f64(double %x) nounwind readnone + store double %y, double addrspace(1)* %out + ret void +} + +; FUNC-LABEL: {{^}}ffloor_v2f64: +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +define void @ffloor_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) { + %y = call <2 x double> @llvm.floor.v2f64(<2 x double> %x) nounwind readnone + store <2 x double> %y, <2 x double> addrspace(1)* %out + ret void +} + +; FIXME-FUNC-LABEL: {{^}}ffloor_v3f64: +; FIXME-CI: v_floor_f64_e32 +; FIXME-CI: v_floor_f64_e32 +; FIXME-CI: v_floor_f64_e32 +; define void @ffloor_v3f64(<3 x double> addrspace(1)* %out, <3 x double> %x) { +; %y = call <3 x double> @llvm.floor.v3f64(<3 x double> %x) nounwind readnone +; store <3 x double> %y, <3 x double> addrspace(1)* %out +; ret void +; } + +; FUNC-LABEL: {{^}}ffloor_v4f64: +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +define void @ffloor_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %x) { + %y = call <4 x double> @llvm.floor.v4f64(<4 x double> %x) nounwind readnone + store <4 x double> %y, <4 x double> addrspace(1)* %out + ret void +} + +; FUNC-LABEL: {{^}}ffloor_v8f64: +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +define void @ffloor_v8f64(<8 x double> addrspace(1)* %out, <8 x double> %x) { + %y = call <8 x double> @llvm.floor.v8f64(<8 x double> %x) nounwind readnone + store <8 x double> %y, <8 x double> addrspace(1)* %out + ret void +} + +; FUNC-LABEL: {{^}}ffloor_v16f64: +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +; CI: v_floor_f64_e32 +define void @ffloor_v16f64(<16 x double> addrspace(1)* %out, <16 x double> %x) { + %y = call <16 x double> @llvm.floor.v16f64(<16 x double> %x) nounwind readnone + store <16 x double> %y, <16 x double> addrspace(1)* %out + ret void +} diff --git a/llvm/test/CodeGen/R600/ffloor.ll b/llvm/test/CodeGen/R600/ffloor.ll index 194d0aaa181..7a9a1e9870d 100644 --- a/llvm/test/CodeGen/R600/ffloor.ll +++ b/llvm/test/CodeGen/R600/ffloor.ll @@ -1,105 +1,50 @@ -; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s +; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s + +; FUNC-LABEL: {{^}}floor_f32: +; SI: v_floor_f32_e32 +; R600: FLOOR +define void @floor_f32(float addrspace(1)* %out, float %in) { + %tmp = call float @llvm.floor.f32(float %in) #0 + store float %tmp, float addrspace(1)* %out + ret void +} -declare double @llvm.floor.f64(double) nounwind readnone -declare <2 x double> @llvm.floor.v2f64(<2 x double>) nounwind readnone -declare <3 x double> @llvm.floor.v3f64(<3 x double>) nounwind readnone -declare <4 x double> @llvm.floor.v4f64(<4 x double>) nounwind readnone -declare <8 x double> @llvm.floor.v8f64(<8 x double>) nounwind readnone -declare <16 x double> @llvm.floor.v16f64(<16 x double>) nounwind readnone - -; FUNC-LABEL: {{^}}ffloor_f64: -; CI: v_floor_f64_e32 +; FUNC-LABEL: {{^}}floor_v2f32: +; SI: v_floor_f32_e32 +; SI: v_floor_f32_e32 -; SI: s_bfe_u32 [[SEXP:s[0-9]+]], {{s[0-9]+}}, 0xb0014 -; SI: s_add_i32 s{{[0-9]+}}, [[SEXP]], 0xfffffc01 -; SI: s_lshr_b64 -; SI: s_not_b64 -; SI: s_and_b64 -; SI-DAG: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000 -; SI-DAG: cmp_lt_i32 -; SI: cndmask_b32 -; SI: cndmask_b32 -; SI: cmp_gt_i32 -; SI: cndmask_b32 -; SI: cndmask_b32 -; SI: v_cmp_lg_f64 -; SI: v_cmp_lt_f64 -; SI: s_and_b64 -; SI: v_cndmask_b32 -; SI: v_cndmask_b32 -; SI: v_add_f64 -; SI: s_endpgm -define void @ffloor_f64(double addrspace(1)* %out, double %x) { - %y = call double @llvm.floor.f64(double %x) nounwind readnone - store double %y, double addrspace(1)* %out +; R600: FLOOR +; R600: FLOOR +define void @floor_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) { + %tmp = call <2 x float> @llvm.floor.v2f32(<2 x float> %in) #0 + store <2 x float> %tmp, <2 x float> addrspace(1)* %out ret void } -; FUNC-LABEL: {{^}}ffloor_v2f64: -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -define void @ffloor_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) { - %y = call <2 x double> @llvm.floor.v2f64(<2 x double> %x) nounwind readnone - store <2 x double> %y, <2 x double> addrspace(1)* %out +; FUNC-LABEL: {{^}}floor_v4f32: +; SI: v_floor_f32_e32 +; SI: v_floor_f32_e32 +; SI: v_floor_f32_e32 +; SI: v_floor_f32_e32 + +; R600: FLOOR +; R600: FLOOR +; R600: FLOOR +; R600: FLOOR +define void @floor_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) { + %tmp = call <4 x float> @llvm.floor.v4f32(<4 x float> %in) #0 + store <4 x float> %tmp, <4 x float> addrspace(1)* %out ret void } -; FIXME-FUNC-LABEL: {{^}}ffloor_v3f64: -; FIXME-CI: v_floor_f64_e32 -; FIXME-CI: v_floor_f64_e32 -; FIXME-CI: v_floor_f64_e32 -; define void @ffloor_v3f64(<3 x double> addrspace(1)* %out, <3 x double> %x) { -; %y = call <3 x double> @llvm.floor.v3f64(<3 x double> %x) nounwind readnone -; store <3 x double> %y, <3 x double> addrspace(1)* %out -; ret void -; } +; Function Attrs: nounwind readonly +declare float @llvm.floor.f32(float) #0 -; FUNC-LABEL: {{^}}ffloor_v4f64: -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -define void @ffloor_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %x) { - %y = call <4 x double> @llvm.floor.v4f64(<4 x double> %x) nounwind readnone - store <4 x double> %y, <4 x double> addrspace(1)* %out - ret void -} +; Function Attrs: nounwind readonly +declare <2 x float> @llvm.floor.v2f32(<2 x float>) #0 -; FUNC-LABEL: {{^}}ffloor_v8f64: -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -define void @ffloor_v8f64(<8 x double> addrspace(1)* %out, <8 x double> %x) { - %y = call <8 x double> @llvm.floor.v8f64(<8 x double> %x) nounwind readnone - store <8 x double> %y, <8 x double> addrspace(1)* %out - ret void -} +; Function Attrs: nounwind readonly +declare <4 x float> @llvm.floor.v4f32(<4 x float>) #0 -; FUNC-LABEL: {{^}}ffloor_v16f64: -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -; CI: v_floor_f64_e32 -define void @ffloor_v16f64(<16 x double> addrspace(1)* %out, <16 x double> %x) { - %y = call <16 x double> @llvm.floor.v16f64(<16 x double> %x) nounwind readnone - store <16 x double> %y, <16 x double> addrspace(1)* %out - ret void -} +attributes #0 = { nounwind readonly } diff --git a/llvm/test/CodeGen/R600/floor.ll b/llvm/test/CodeGen/R600/floor.ll index 67e86c41fdc..c6bfb8567a0 100644 --- a/llvm/test/CodeGen/R600/floor.ll +++ b/llvm/test/CodeGen/R600/floor.ll @@ -1,7 +1,6 @@ -;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s - -;CHECK: FLOOR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} +; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck %s +; CHECK: FLOOR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}} define void @test(<4 x float> inreg %reg0) #0 { %r0 = extractelement <4 x float> %reg0, i32 0 %r1 = call float @floor(float %r0) @@ -13,4 +12,4 @@ define void @test(<4 x float> inreg %reg0) #0 { declare float @floor(float) readonly declare void @llvm.R600.store.swizzle(<4 x float>, i32, i32) -attributes #0 = { "ShaderType"="0" }
\ No newline at end of file +attributes #0 = { "ShaderType"="0" } diff --git a/llvm/test/CodeGen/R600/llvm.floor.ll b/llvm/test/CodeGen/R600/llvm.floor.ll deleted file mode 100644 index 1016ff75ce9..00000000000 --- a/llvm/test/CodeGen/R600/llvm.floor.ll +++ /dev/null @@ -1,54 +0,0 @@ -; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s --check-prefix=R600-CHECK -; RUN: llc < %s -march=amdgcn -mcpu=SI -verify-machineinstrs | FileCheck %s --check-prefix=SI-CHECK - -; R600-CHECK: {{^}}f32: -; R600-CHECK: FLOOR -; SI-CHECK: {{^}}f32: -; SI-CHECK: v_floor_f32_e32 -define void @f32(float addrspace(1)* %out, float %in) { -entry: - %0 = call float @llvm.floor.f32(float %in) - store float %0, float addrspace(1)* %out - ret void -} - -; R600-CHECK: {{^}}v2f32: -; R600-CHECK: FLOOR -; R600-CHECK: FLOOR -; SI-CHECK: {{^}}v2f32: -; SI-CHECK: v_floor_f32_e32 -; SI-CHECK: v_floor_f32_e32 -define void @v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) { -entry: - %0 = call <2 x float> @llvm.floor.v2f32(<2 x float> %in) - store <2 x float> %0, <2 x float> addrspace(1)* %out - ret void -} - -; R600-CHECK: {{^}}v4f32: -; R600-CHECK: FLOOR -; R600-CHECK: FLOOR -; R600-CHECK: FLOOR -; R600-CHECK: FLOOR -; SI-CHECK: {{^}}v4f32: -; SI-CHECK: v_floor_f32_e32 -; SI-CHECK: v_floor_f32_e32 -; SI-CHECK: v_floor_f32_e32 -; SI-CHECK: v_floor_f32_e32 -define void @v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) { -entry: - %0 = call <4 x float> @llvm.floor.v4f32(<4 x float> %in) - store <4 x float> %0, <4 x float> addrspace(1)* %out - ret void -} - -; Function Attrs: nounwind readonly -declare float @llvm.floor.f32(float) #0 - -; Function Attrs: nounwind readonly -declare <2 x float> @llvm.floor.v2f32(<2 x float>) #0 - -; Function Attrs: nounwind readonly -declare <4 x float> @llvm.floor.v4f32(<4 x float>) #0 - -attributes #0 = { nounwind readonly } |
