[clang] [Clang] Implement resource directory headers for common GPU intrinsics (PR #110179)

[Joseph Huber via cfe-commits]

================
@@ -0,0 +1,187 @@
+//===-- amdgpuintrin.h - AMDPGU intrinsic functions -----------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef __AMDGPUINTRIN_H
+#define __AMDGPUINTRIN_H
+
+#ifndef __AMDGPU__
+#error "This file is intended for AMDGPU targets or offloading to AMDGPU
+#endif
+
+#include <stdbool.h>
+#include <stdint.h>
+
+#if defined(__HIP__) || defined(__CUDA__)
+#define _DEFAULT_ATTRS __attribute__((device)) __attribute__((always_inline))
+#else
+#define _DEFAULT_ATTRS __attribute__((always_inline))
+#endif
+
+#pragma omp begin declare target device_type(nohost)
+#pragma omp begin declare variant match(device = {arch(amdgcn)})
+
+// Type aliases to the address spaces used by the AMDGPU backend.
+#define _private __attribute__((opencl_private))
+#define _constant __attribute__((opencl_constant))
+#define _local __attribute__((opencl_local))
+#define _global __attribute__((opencl_global))
+
+// Attribute to declare a function as a kernel.
+#define _kernel __attribute__((amdgpu_kernel, visibility("protected")))
+
+// Returns the number of workgroups in the 'x' dimension of the grid.
+_DEFAULT_ATTRS static inline uint32_t _get_num_blocks_x() {
+  return __builtin_amdgcn_grid_size_x() / __builtin_amdgcn_workgroup_size_x();
+}
+
+// Returns the number of workgroups in the 'y' dimension of the grid.
+_DEFAULT_ATTRS static inline uint32_t _get_num_blocks_y() {
+  return __builtin_amdgcn_grid_size_y() / __builtin_amdgcn_workgroup_size_y();
+}
+
+// Returns the number of workgroups in the 'z' dimension of the grid.
+_DEFAULT_ATTRS static inline uint32_t _get_num_blocks_z() {
+  return __builtin_amdgcn_grid_size_z() / __builtin_amdgcn_workgroup_size_z();
+}
+
+// Returns the total number of workgruops in the grid.
+_DEFAULT_ATTRS static inline uint64_t _get_num_blocks() {
----------------
jhuber6 wrote:

This is being conservative with the API as listed, AFAIK CUDA says that the maximum X block size is 2^31 - 1 and Y and Z are 2^16 -1, meaning if you get the "global" ID, it could technically be more than 2^32 - 1. Maybe @Artem-B could chime in here.

https://github.com/llvm/llvm-project/pull/110179