MIOpenGEMM
MIOpenGEMM copied to clipboard
ROCmSoftwarePlatform
From what I can see, this hasn't been moved to the ``ROCm`` organization like the others, nor has it been updated past ``5.5.0``. The [last commit](https://github.com/ROCmSoftwarePlatform/MIOpenGEMM/commit/c974d961355920cc5f1a87fcf55afcbf3905fe38) was also more than...
When building examples via "make examples", we get below error: /usr/bin/ld: ../miopengemm/libmiopengemm.so.1.0: undefined reference to `pthread_create' There is no link reference to pthread library.
Hi, I'm packaging this and many other ROCm projects for nixpkgs. Generally, for these projects I'm trying to do ``${project_version}-${rocm-version}``, but am not entirely sure that's applicable to this project....
GemmBwd1x1_stride1 kernel verficiation failure. kernel writes only 320 values of result to image buffer, rest 4 values always zeros. If to try use bigger input image like (--spatial_dim_elements 2 18...
@kingplim;@newling; We are going to enforce two factor authentication in (https://github.com/ROCmSoftwarePlatform/) organization on 29th April, 2022 . Since we identified you as outside collaborator for ROCmSoftwarePlatform organization, you need to...
I'm using rx 560 16CU 4GB/gfx803 I run into performance issue when working with matrices of this specific size M=4096, N=4096, K=16, if I modify N to 4097 or 4095...
libmiopengemm.so uses symbols from libpthread, but doesn't explicitly link to it ``` sclarkson@localhost:~/miopengemm$ nm -D /opt/rocm/miopengemm/lib/libmiopengemm.so | grep pthread U pthread_create w pthread_equal w __pthread_key_create w pthread_mutex_lock w pthread_mutex_unlock w...
@newling I'm a newbie to MIOpenGEMM. Could you tell me how to save the params and OpenCL kernel after doing geometry? Sorry for raising this as an issue:) But I...
I was wondering if any of you have any feedback on ways I could speed up the cachetxt additions to the kernel cache? I know these files change occasionally, but...
Updated cache for Jing's optimizations on RNN with GEMM fusion
