[AMDGPU] Add ds_fadd, ds_fmin, ds_fmax builtins functions

Reviewed by arsenm

Differential Revision: https://reviews.llvm.org/D42578

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@323890 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Basic/BuiltinsAMDGPU.def b/include/clang/Basic/BuiltinsAMDGPU.def
index ec6a0fb91765753772881240526dd95d9048445e..e63f6e4099442151cd5598b7d9918b3a8b5deaae 100644 (file)
--- a/include/clang/Basic/BuiltinsAMDGPU.def
+++ b/include/clang/Basic/BuiltinsAMDGPU.def
@@ -93,6 +93,9 @@ BUILTIN(__builtin_amdgcn_ds_bpermute, "iii", "nc")
 BUILTIN(__builtin_amdgcn_readfirstlane, "ii", "nc")
 BUILTIN(__builtin_amdgcn_readlane, "iii", "nc")
 BUILTIN(__builtin_amdgcn_fmed3f, "ffff", "nc")
+BUILTIN(__builtin_amdgcn_ds_fadd, "ff*3fiib", "n")
+BUILTIN(__builtin_amdgcn_ds_fmin, "ff*3fiib", "n")
+BUILTIN(__builtin_amdgcn_ds_fmax, "ff*3fiib", "n")
 
 //===----------------------------------------------------------------------===//
 // VI+ only builtins.

diff --git a/test/CodeGenOpenCL/builtins-amdgcn-vi.cl b/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
index 1dad67491832548a5808821ccfc69ec36af0e550..11be516b20de7a6a4b092814c8e2ff1dcf6683e7 100644 (file)
--- a/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
+++ b/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
@@ -89,3 +89,23 @@ void test_mov_dpp(global int* out, int src)
   *out = __builtin_amdgcn_mov_dpp(src, 0, 0, 0, false);
 }
 
+// CHECK-LABEL: @test_ds_fadd
+// CHECK: call float @llvm.amdgcn.ds.fadd(float addrspace(3)* %out, float %src, i32 0, i32 0, i1 false)
+void test_ds_fadd(local float *out, float src)
+{
+  *out = __builtin_amdgcn_ds_fadd(out, src, 0, 0, false);
+}
+
+// CHECK-LABEL: @test_ds_fmin
+// CHECK: call float @llvm.amdgcn.ds.fmin(float addrspace(3)* %out, float %src, i32 0, i32 0, i1 false)
+void test_ds_fmin(local float *out, float src)
+{
+  *out = __builtin_amdgcn_ds_fmin(out, src, 0, 0, false);
+}
+
+// CHECK-LABEL: @test_ds_fmax
+// CHECK: call float @llvm.amdgcn.ds.fmax(float addrspace(3)* %out, float %src, i32 0, i32 0, i1 false)
+void test_ds_fmax(local float *out, float src)
+{
+  *out = __builtin_amdgcn_ds_fmax(out, src, 0, 0, false);
+}