Arsmart1 issues

Results 4 issues of


                                            Arsmart1

LINK : fatal error LNK1181: 无法打开输入文件 Error

I meet this when compile the python setup.py install in cuda file.... Any help will be highly appreciated!!! (new_env) C:\Users\20247\Downloads\pytorch-parallel-master\pytorch-parallel-master\cuda>python setup.py install running install running bdist_egg running egg_info writing sigmoid_cuda_linear_cpp.egg-info\PKG-INFO...

How GPU task are implemented by CPU thread?

This might be a naive question.... It is mentioned in paper that GPU task can be bonded to a CPU thread...? I am wondering is any references discuss more details...

How GEMM is implemented?

I am wondering how the GEMM is implemented, is it like, CPU RAM store all the matrix A and B. Suppose we have 2 GPUs and we send A(i, k)...

[W C:\w\b\windows\pytorch\aten\src\ATen\native\cuda\Indexing.cu:963] Warning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead. (function masked_fill__cuda)

I meet this error and really can not solve it: [W C:\w\b\windows\pytorch\aten\src\ATen\native\cuda\Indexing.cu:963] Warning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype...