Was that a typo in fp16ScalarProduct?
in line 97& line 121 of Samples/0_Introduction/fp16ScalarProduct/fp16ScalarProduct.cu
for (int i = threadIdx.x + blockDim.x + blockIdx.x; i < size; i += stride)
shouldn't it be int i = threadIdx.x + blockDim.x * blockIdx.x ?
2 条评论