我有一个CUDA内核-
template <typename T, typename C>
__global__
void cuda_ListArray_num(
C *tonum,
const T *fromstarts,
const T *fromstops
) {
int64_t block_id = blockIdx.x + blockIdx.y * gridDim.x + gridDim.x * gridDim.y * blockIdx.z;
int64_t thread_id = block_id * blockDim.x + threadIdx.x;
int64_t start = fromstarts[thread_id];
int64_t stop = fromstops[thread_id];
tonum[thread_id] = (C) (stop - start);
}
ERROR
awkward_ListArray32_num_64(
int64_t* tonum,
const int32_t* fromstarts,
const int32_t* fromstops,
int64_t length) {
dim3 blocks_per_grid;
dim3 threads_per_block;
if (length > 1024) {
blocks_per_grid = dim3(ceil((length) / 1024.0), 1, 1);
threads_per_block = dim3(1024, 1, 1);
} else {
blocks_per_grid = dim3(1, 1, 1);
threads_per_block = dim3(length, 1, 1);
}
cuda_ListArray_num<int32_t, int64_t><<<blocks_per_grid, threads_per_block>>>(
tonum,
fromstarts,
fromstops);
cudaDeviceSynchronize();
return success();
}
我可以将它添加到.so
文件中,并使用ctypes
从Python加载它。之后,我尝试从Python中使用它
这是在上述代码块中返回的ERROR
结构的Python等价物-
class Error(ctypes.Structure):
_fields_ = [
("str", ctypes.POINTER(ctypes.c_char)),
("identity", ctypes.c_int64),
("attempt", ctypes.c_int64),
("pass_through", ctypes.c_bool),
]
下面是我如何从Python中使用它-
lib = ctypes.CDLL("cuda-kernels.so")
funcC = getattr(lib, 'awkward_ListArray32_num_64')
funcC.restype = Error
tonum = cupy.array([123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123, 123], dtype=cupy.in64)
tonumx = ctypes.cast(tonum.data.ptr, ctypes.POINTER(ctypes.c_int64))
fromstarts = cupy.array([2, 0, 2, 1, 2, 1, 2, 1, 2, 1, 2, 1], dtype=cupy.int32)
fromstarts = ctypes.cast(fromstarts.data.ptr, ctypes.POINTER(ctypes.c_int32))
fromstops = cupy.array([3, 2, 4, 5, 3, 4, 2, 5, 3, 4, 6, 11], dtype=cupy.int32)
fromstops = ctypes.cast(fromstops.data.ptr, ctypes.POINTER(ctypes.c_int32))
length = 3
funcC.argtypes = (ctypes.POINTER(ctypes.c_int64), ctypes.POINTER(ctypes.c_int32), ctypes.POINTER(ctypes.c_int32), ctypes.c_int64)
ret_pass = funcC(tonumx, fromstarts, fromstops, length)
但是当我打印tonum
>>> tonum[:3]
array([0, 0, 0])
但是值应该是-[1, 2, 2]
(基于cuda_ListArray_num
的工作方式)
我可能做错了什么?我想我可能在如何将cupy
指针传递到cuda内核上犯了一个错误
您必须将python代码更改为
原因是CuPy数组是用RAII管理的,因此当您将
fromstarts
变量重新分配给另一个对象(ctypes指针)时,实际数组将被销毁,其内存块将返回到CuPy的内存池。在此之后,当您创建fromstops
数组时,它将使用相同的内存块,覆盖fromstarts
数组的内容,因为该数组不再活动,并且共享同一个指针然后,当您调用c代码时,
fromstarts
和fromstops
实际上是同一个指针。您可以使用调试器或printf验证这一点相关问题 更多 >
编程相关推荐