aparler/PyNorch
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

matmul cuda

Browse source
This commit is contained in:
lucasdelimanogueira 2024-04-30 01:38:08 -03:00
parent b69a652ca9
commit 5c369c6e26
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
csrc/cuda.h
View file

@ -13,10 +13,10 @@
__global__ void elementwise_mul_tensor_cuda_kernel(float* data1, float* data2, float* result_data, int size);
__host__ void elementwise_mul_tensor_cuda(Tensor* tensor1, Tensor* tensor2, float* result_data);
__global__ void matmul_tensor_cuda_kernel(float* data1, float* data2, float* result_data, int rows1, int cols1, int cols2);
__host__ void matmul_tensor_cuda(Tensor* tensor1, Tensor* tensor2, float* result_data);
__global__ void pow_tensor_cuda_kernel(float* data, float power, float* result_data, int size);
__host__ void pow_tensor_cuda(Tensor* tensor, float power, float* result_data);
__global__ void matmul_tensor_cuda_kernel(float* data1, float* data2, float* result_data, int rows1, int cols1, int cols2)
__host__ void matmul_tensor_cuda(Tensor* tensor1, Tensor* tensor2, float* result_data);
#endif /* CUDA_KERNEL_H_ */