[Misc] Consolidate csrc shared headers and prune dead code (#60721)

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
Misha Goin
2026-10-12 09:46:22 -07:00
committed by GitHub
co-authored by Claude
parent e0317b28ce
commit d79b52b182
242 changed files with 2783 additions and 3638 deletions
+1 -24
View File
@@ -1,21 +1,8 @@
#pragma once
#include <cstdint>
#include <stdio.h>
#if defined(__HIPCC__)
#define HOST_DEVICE_INLINE __host__ __device__
#define DEVICE_INLINE __device__
#define HOST_INLINE __host__
#elif defined(__CUDACC__) || defined(_NVHPC_CUDA)
#define HOST_DEVICE_INLINE __host__ __device__ __forceinline__
#define DEVICE_INLINE __device__ __forceinline__
#define HOST_INLINE __host__ __forceinline__
#else
#define HOST_DEVICE_INLINE inline
#define DEVICE_INLINE inline
#define HOST_INLINE inline
#endif
#define CUDA_CHECK(cmd) \
do { \
cudaError_t e = cmd; \
@@ -29,13 +16,3 @@
int64_t get_device_attribute(int64_t attribute, int64_t device_id);
int64_t get_max_shared_memory_per_block_device_attribute(int64_t device_id);
namespace cuda_utils {
template <typename T>
HOST_DEVICE_INLINE constexpr std::enable_if_t<std::is_integral_v<T>, T>
ceil_div(T a, T b) {
return (a + b - 1) / b;
}
}; // namespace cuda_utils