[PATCH] D102427: [HIP] Clean up llvm intrinsics using __asm

[Aaron Enye Shi via Phabricator via cfe-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGa249ffa42137: [HIP] Clean up llvm intrinsics using __asm 
(authored by ashi1).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D102427/new/

https://reviews.llvm.org/D102427

Files:
  clang/lib/Headers/__clang_hip_libdevice_declares.h


Index: clang/lib/Headers/__clang_hip_libdevice_declares.h
===================================================================
--- clang/lib/Headers/__clang_hip_libdevice_declares.h
+++ clang/lib/Headers/__clang_hip_libdevice_declares.h
@@ -138,14 +138,22 @@
 __device__ __attribute__((const)) float __ocml_fma_rtp_f32(float, float, 
float);
 __device__ __attribute__((const)) float __ocml_fma_rtz_f32(float, float, 
float);
 
-__device__ __attribute__((const)) float
-__llvm_amdgcn_cos_f32(float) __asm("llvm.amdgcn.cos.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rcp_f32(float) __asm("llvm.amdgcn.rcp.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rsq_f32(float) __asm("llvm.amdgcn.rsq.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_sin_f32(float) __asm("llvm.amdgcn.sin.f32");
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_cos_f32(float __x) {
+  return __builtin_amdgcn_cosf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rcp_f32(float __x) {
+  return __builtin_amdgcn_rcpf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rsq_f32(float __x) {
+  return __builtin_amdgcn_rsqf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_sin_f32(float __x) {
+  return __builtin_amdgcn_sinf(__x);
+}
 // END INTRINSICS
 // END FLOAT
 
@@ -269,10 +277,14 @@
 __device__ __attribute__((const)) double __ocml_fma_rtz_f64(double, double,
                                                             double);
 
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rcp_f64(double) __asm("llvm.amdgcn.rcp.f64");
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rsq_f64(double) __asm("llvm.amdgcn.rsq.f64");
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rcp_f64(double __x) {
+  return __builtin_amdgcn_rcp(__x);
+}
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rsq_f64(double __x) {
+  return __builtin_amdgcn_rsq(__x);
+}
 
 __device__ __attribute__((const)) _Float16 __ocml_ceil_f16(_Float16);
 __device__ _Float16 __ocml_cos_f16(_Float16);



Index: clang/lib/Headers/__clang_hip_libdevice_declares.h
===================================================================
--- clang/lib/Headers/__clang_hip_libdevice_declares.h
+++ clang/lib/Headers/__clang_hip_libdevice_declares.h
@@ -138,14 +138,22 @@
 __device__ __attribute__((const)) float __ocml_fma_rtp_f32(float, float, float);
 __device__ __attribute__((const)) float __ocml_fma_rtz_f32(float, float, float);
 
-__device__ __attribute__((const)) float
-__llvm_amdgcn_cos_f32(float) __asm("llvm.amdgcn.cos.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rcp_f32(float) __asm("llvm.amdgcn.rcp.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_rsq_f32(float) __asm("llvm.amdgcn.rsq.f32");
-__device__ __attribute__((const)) float
-__llvm_amdgcn_sin_f32(float) __asm("llvm.amdgcn.sin.f32");
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_cos_f32(float __x) {
+  return __builtin_amdgcn_cosf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rcp_f32(float __x) {
+  return __builtin_amdgcn_rcpf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_rsq_f32(float __x) {
+  return __builtin_amdgcn_rsqf(__x);
+}
+__device__ inline __attribute__((const)) float
+__llvm_amdgcn_sin_f32(float __x) {
+  return __builtin_amdgcn_sinf(__x);
+}
 // END INTRINSICS
 // END FLOAT
 
@@ -269,10 +277,14 @@
 __device__ __attribute__((const)) double __ocml_fma_rtz_f64(double, double,
                                                             double);
 
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rcp_f64(double) __asm("llvm.amdgcn.rcp.f64");
-__device__ __attribute__((const)) double
-__llvm_amdgcn_rsq_f64(double) __asm("llvm.amdgcn.rsq.f64");
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rcp_f64(double __x) {
+  return __builtin_amdgcn_rcp(__x);
+}
+__device__ inline __attribute__((const)) double
+__llvm_amdgcn_rsq_f64(double __x) {
+  return __builtin_amdgcn_rsq(__x);
+}
 
 __device__ __attribute__((const)) _Float16 __ocml_ceil_f16(_Float16);
 __device__ _Float16 __ocml_cos_f16(_Float16);

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits