52 lines
1.6 KiB
C++
52 lines
1.6 KiB
C++
#pragma once
|
|
|
|
#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; \
|
|
if (e != cudaSuccess) { \
|
|
printf("Failed: Cuda error %s:%d '%s'\n", __FILE__, __LINE__, \
|
|
cudaGetErrorString(e)); \
|
|
exit(EXIT_FAILURE); \
|
|
} \
|
|
} while (0)
|
|
|
|
int64_t get_device_attribute(int64_t attribute, int64_t device_id) {
|
|
static int value = [=]() {
|
|
int device = static_cast<int>(device_id);
|
|
if (device < 0) {
|
|
CUDA_CHECK(cudaGetDevice(&device));
|
|
}
|
|
int value;
|
|
CUDA_CHECK(cudaDeviceGetAttribute(
|
|
&value, static_cast<cudaDeviceAttr>(attribute), device));
|
|
return static_cast<int>(value);
|
|
}();
|
|
|
|
return value;
|
|
}
|
|
|
|
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
|