aboutsummaryrefslogtreecommitdiff
path: root/test/CodeGen/AMDGPU/fmax_legacy.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/AMDGPU/fmax_legacy.ll')
-rw-r--r--test/CodeGen/AMDGPU/fmax_legacy.ll156
1 files changed, 0 insertions, 156 deletions
diff --git a/test/CodeGen/AMDGPU/fmax_legacy.ll b/test/CodeGen/AMDGPU/fmax_legacy.ll
deleted file mode 100644
index 7643c3ea533c..000000000000
--- a/test/CodeGen/AMDGPU/fmax_legacy.ll
+++ /dev/null
@@ -1,156 +0,0 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=SI-SAFE -check-prefix=FUNC %s
-; RUN: llc -enable-no-nans-fp-math -enable-unsafe-fp-math -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI-NONAN -check-prefix=SI -check-prefix=FUNC %s
-; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
-
-; FIXME: Should replace unsafe-fp-math with no signed zeros.
-
-declare i32 @llvm.r600.read.tidig.x() #1
-
-; FUNC-LABEL: @test_fmax_legacy_uge_f32
-; SI: buffer_load_dword [[A:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
-; SI: buffer_load_dword [[B:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
-; SI-SAFE: v_max_legacy_f32_e32 {{v[0-9]+}}, [[B]], [[A]]
-; SI-NONAN: v_max_f32_e32 {{v[0-9]+}}, [[B]], [[A]]
-
-; EG: MAX
-define amdgpu_kernel void @test_fmax_legacy_uge_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
- %tid = call i32 @llvm.r600.read.tidig.x() #1
- %gep.0 = getelementptr float, float addrspace(1)* %in, i32 %tid
- %gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
-
- %a = load volatile float, float addrspace(1)* %gep.0, align 4
- %b = load volatile float, float addrspace(1)* %gep.1, align 4
-
- %cmp = fcmp uge float %a, %b
- %val = select i1 %cmp, float %a, float %b
- store float %val, float addrspace(1)* %out, align 4
- ret void
-}
-
-; FUNC-LABEL: @test_fmax_legacy_oge_f32
-; SI: buffer_load_dword [[A:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
-; SI: buffer_load_dword [[B:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
-; SI-SAFE: v_max_legacy_f32_e32 {{v[0-9]+}}, [[A]], [[B]]
-; SI-NONAN: v_max_f32_e32 {{v[0-9]+}}, [[B]], [[A]]
-; EG: MAX
-define amdgpu_kernel void @test_fmax_legacy_oge_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
- %tid = call i32 @llvm.r600.read.tidig.x() #1
- %gep.0 = getelementptr float, float addrspace(1)* %in, i32 %tid
- %gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
-
- %a = load volatile float, float addrspace(1)* %gep.0, align 4
- %b = load volatile float, float addrspace(1)* %gep.1, align 4
-
- %cmp = fcmp oge float %a, %b
- %val = select i1 %cmp, float %a, float %b
- store float %val, float addrspace(1)* %out, align 4
- ret void
-}
-
-; FUNC-LABEL: @test_fmax_legacy_ugt_f32
-; SI: buffer_load_dword [[A:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
-; SI: buffer_load_dword [[B:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
-; SI-SAFE: v_max_legacy_f32_e32 {{v[0-9]+}}, [[B]], [[A]]
-; SI-NONAN: v_max_f32_e32 {{v[0-9]+}}, [[B]], [[A]]
-; EG: MAX
-define amdgpu_kernel void @test_fmax_legacy_ugt_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
- %tid = call i32 @llvm.r600.read.tidig.x() #1
- %gep.0 = getelementptr float, float addrspace(1)* %in, i32 %tid
- %gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
-
- %a = load volatile float, float addrspace(1)* %gep.0, align 4
- %b = load volatile float, float addrspace(1)* %gep.1, align 4
-
- %cmp = fcmp ugt float %a, %b
- %val = select i1 %cmp, float %a, float %b
- store float %val, float addrspace(1)* %out, align 4
- ret void
-}
-
-; FUNC-LABEL: @test_fmax_legacy_ogt_f32
-; SI: buffer_load_dword [[A:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
-; SI: buffer_load_dword [[B:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
-; SI-SAFE: v_max_legacy_f32_e32 {{v[0-9]+}}, [[A]], [[B]]
-; SI-NONAN: v_max_f32_e32 {{v[0-9]+}}, [[B]], [[A]]
-; EG: MAX
-define amdgpu_kernel void @test_fmax_legacy_ogt_f32(float addrspace(1)* %out, float addrspace(1)* %in) #0 {
- %tid = call i32 @llvm.r600.read.tidig.x() #1
- %gep.0 = getelementptr float, float addrspace(1)* %in, i32 %tid
- %gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
-
- %a = load volatile float, float addrspace(1)* %gep.0, align 4
- %b = load volatile float, float addrspace(1)* %gep.1, align 4
-
- %cmp = fcmp ogt float %a, %b
- %val = select i1 %cmp, float %a, float %b
- store float %val, float addrspace(1)* %out, align 4
- ret void
-}
-
-; FUNC-LABEL: {{^}}test_fmax_legacy_ogt_v1f32:
-; SI: buffer_load_dword [[A:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
-; SI: buffer_load_dword [[B:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
-; SI-SAFE: v_max_legacy_f32_e32 {{v[0-9]+}}, [[A]], [[B]]
-; SI-NONAN: v_max_f32_e32 {{v[0-9]+}}, [[B]], [[A]]
-; EG: MAX
-define amdgpu_kernel void @test_fmax_legacy_ogt_v1f32(<1 x float> addrspace(1)* %out, <1 x float> addrspace(1)* %in) #0 {
- %tid = call i32 @llvm.r600.read.tidig.x() #1
- %gep.0 = getelementptr <1 x float>, <1 x float> addrspace(1)* %in, i32 %tid
- %gep.1 = getelementptr <1 x float>, <1 x float> addrspace(1)* %gep.0, i32 1
-
- %a = load <1 x float>, <1 x float> addrspace(1)* %gep.0
- %b = load <1 x float>, <1 x float> addrspace(1)* %gep.1
-
- %cmp = fcmp ogt <1 x float> %a, %b
- %val = select <1 x i1> %cmp, <1 x float> %a, <1 x float> %b
- store <1 x float> %val, <1 x float> addrspace(1)* %out
- ret void
-}
-
-; FUNC-LABEL: {{^}}test_fmax_legacy_ogt_v3f32:
-; SI-SAFE: v_max_legacy_f32_e32
-; SI-SAFE: v_max_legacy_f32_e32
-; SI-SAFE: v_max_legacy_f32_e32
-; SI-NONAN: v_max_f32_e32
-; SI-NONAN: v_max_f32_e32
-; SI-NONAN: v_max_f32_e32
-define amdgpu_kernel void @test_fmax_legacy_ogt_v3f32(<3 x float> addrspace(1)* %out, <3 x float> addrspace(1)* %in) #0 {
- %tid = call i32 @llvm.r600.read.tidig.x() #1
- %gep.0 = getelementptr <3 x float>, <3 x float> addrspace(1)* %in, i32 %tid
- %gep.1 = getelementptr <3 x float>, <3 x float> addrspace(1)* %gep.0, i32 1
-
- %a = load <3 x float>, <3 x float> addrspace(1)* %gep.0
- %b = load <3 x float>, <3 x float> addrspace(1)* %gep.1
-
- %cmp = fcmp ogt <3 x float> %a, %b
- %val = select <3 x i1> %cmp, <3 x float> %a, <3 x float> %b
- store <3 x float> %val, <3 x float> addrspace(1)* %out
- ret void
-}
-
-; FUNC-LABEL: @test_fmax_legacy_ogt_f32_multi_use
-; SI: buffer_load_dword [[A:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64{{$}}
-; SI: buffer_load_dword [[B:v[0-9]+]], {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0 addr64 offset:4
-; SI-NOT: v_max_
-; SI: v_cmp_gt_f32
-; SI-NEXT: v_cndmask_b32
-; SI-NOT: v_max_
-
-; EG: MAX
-define amdgpu_kernel void @test_fmax_legacy_ogt_f32_multi_use(float addrspace(1)* %out0, i1 addrspace(1)* %out1, float addrspace(1)* %in) #0 {
- %tid = call i32 @llvm.r600.read.tidig.x() #1
- %gep.0 = getelementptr float, float addrspace(1)* %in, i32 %tid
- %gep.1 = getelementptr float, float addrspace(1)* %gep.0, i32 1
-
- %a = load volatile float, float addrspace(1)* %gep.0, align 4
- %b = load volatile float, float addrspace(1)* %gep.1, align 4
-
- %cmp = fcmp ogt float %a, %b
- %val = select i1 %cmp, float %a, float %b
- store float %val, float addrspace(1)* %out0, align 4
- store i1 %cmp, i1addrspace(1)* %out1
- ret void
-}
-
-attributes #0 = { nounwind }
-attributes #1 = { nounwind readnone }