summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/AMDGPU/fneg-combines.ll
diff options
context:
space:
mode:
authorMatt Arsenault <Matthew.Arsenault@amd.com>2017-01-12 18:48:09 +0000
committerMatt Arsenault <Matthew.Arsenault@amd.com>2017-01-12 18:48:09 +0000
commit31c039ef2e16a85cd5ac15defabfaf9ddcd50f60 (patch)
tree8400fa174f41b53b7b689e018a74c63fc9bb54ff /llvm/test/CodeGen/AMDGPU/fneg-combines.ll
parent555e5980a5c7037fba5b40e8bab556a17e272511 (diff)
downloadbcm5719-llvm-31c039ef2e16a85cd5ac15defabfaf9ddcd50f60.tar.gz
bcm5719-llvm-31c039ef2e16a85cd5ac15defabfaf9ddcd50f60.zip
AMDGPU: Fold free fneg into sin
llvm-svn: 291790
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/fneg-combines.ll')
-rw-r--r--llvm/test/CodeGen/AMDGPU/fneg-combines.ll42
1 files changed, 42 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/fneg-combines.ll b/llvm/test/CodeGen/AMDGPU/fneg-combines.ll
index c09b7e1fcde..d555d8d871d 100644
--- a/llvm/test/CodeGen/AMDGPU/fneg-combines.ll
+++ b/llvm/test/CodeGen/AMDGPU/fneg-combines.ll
@@ -1229,9 +1229,51 @@ define void @v_fneg_mul_legacy_multi_use_fneg_x_f32(float addrspace(1)* %out, fl
ret void
}
+; --------------------------------------------------------------------------------
+; sin tests
+; --------------------------------------------------------------------------------
+
+; GCN-LABEL: {{^}}v_fneg_sin_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: v_mov_b32_e32 [[K:v[0-9]+]], 0x3e22f983
+; GCN: v_mul_f32_e64 [[MUL:v[0-9]+]], [[K]], -[[A]]
+; GCN: v_fract_f32_e32 [[FRACT:v[0-9]+]], [[MUL]]
+; GCN: v_sin_f32_e32 [[RESULT:v[0-9]+]], [[FRACT]]
+; GCN: buffer_store_dword [[RESULT]]
+define void @v_fneg_sin_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr) #0 {
+ %tid = call i32 @llvm.amdgcn.workitem.id.x()
+ %tid.ext = sext i32 %tid to i64
+ %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+ %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+ %a = load volatile float, float addrspace(1)* %a.gep
+ %sin = call float @llvm.sin.f32(float %a)
+ %fneg = fsub float -0.000000e+00, %sin
+ store float %fneg, float addrspace(1)* %out.gep
+ ret void
+}
+
+; GCN-LABEL: {{^}}v_fneg_amdgcn_sin_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: v_sin_f32_e64 [[RESULT:v[0-9]+]], -[[A]]
+; GCN: buffer_store_dword [[RESULT]]
+define void @v_fneg_amdgcn_sin_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr) #0 {
+ %tid = call i32 @llvm.amdgcn.workitem.id.x()
+ %tid.ext = sext i32 %tid to i64
+ %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+ %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+ %a = load volatile float, float addrspace(1)* %a.gep
+ %sin = call float @llvm.amdgcn.sin.f32(float %a)
+ %fneg = fsub float -0.000000e+00, %sin
+ store float %fneg, float addrspace(1)* %out.gep
+ ret void
+}
+
declare i32 @llvm.amdgcn.workitem.id.x() #1
declare float @llvm.fma.f32(float, float, float) #1
declare float @llvm.fmuladd.f32(float, float, float) #1
+declare float @llvm.sin.f32(float) #1
+
+declare float @llvm.amdgcn.sin.f32(float) #1
declare float @llvm.amdgcn.rcp.f32(float) #1
declare float @llvm.amdgcn.rcp.legacy(float) #1
declare float @llvm.amdgcn.fmul.legacy(float, float) #1
OpenPOWER on IntegriCloud