Reapply "r363684: AMDGPU: Add GWS instruction builtins"

llvm-svn: 363871

2 files changed, 14 insertions, 0 deletions

diff --git a/clang/include/clang/Basic/BuiltinsAMDGPU.def b/clang/include/clang/Basic/BuiltinsAMDGPU.def
index 89f68fbe82f..a8aadff770d 100644
--- a/clang/include/clang/Basic/BuiltinsAMDGPU.def
+++ b/clang/include/clang/Basic/BuiltinsAMDGPU.def
@@ -45,6 +45,8 @@ BUILTIN(__builtin_amdgcn_s_barrier, "v", "n")
 BUILTIN(__builtin_amdgcn_wave_barrier, "v", "n")
 BUILTIN(__builtin_amdgcn_s_dcache_inv, "v", "n")
 BUILTIN(__builtin_amdgcn_buffer_wbinvl1, "v", "n")
+BUILTIN(__builtin_amdgcn_ds_gws_init, "vUiUi", "n")
+BUILTIN(__builtin_amdgcn_ds_gws_barrier, "vUiUi", "n")
 
 // FIXME: Need to disallow constant address space.
 BUILTIN(__builtin_amdgcn_div_scale, "dddbb*", "n")
diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
index bd7fe78fc96..27a91a18cc9 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
@@ -548,6 +548,18 @@ kernel void test_ds_consume_lds(global int* out, local int* ptr) {
   *out = __builtin_amdgcn_ds_consume(ptr);
 }
 
+// CHECK-LABEL: @test_gws_init(
+// CHECK: call void @llvm.amdgcn.ds.gws.init(i32 %value, i32 %id)
+kernel void test_gws_init(uint value, uint id) {
+  __builtin_amdgcn_ds_gws_init(value, id);
+}
+
+// CHECK-LABEL: @test_gws_barrier(
+// CHECK: call void @llvm.amdgcn.ds.gws.barrier(i32 %value, i32 %id)
+kernel void test_gws_barrier(uint value, uint id) {
+  __builtin_amdgcn_ds_gws_barrier(value, id);
+}
+
 // CHECK-DAG: [[$WI_RANGE]] = !{i32 0, i32 1024}
 // CHECK-DAG: attributes #[[$NOUNWIND_READONLY:[0-9]+]] = { nounwind readonly }
 // CHECK-DAG: attributes #[[$READ_EXEC_ATTRS]] = { convergent }