0
I Use This!
Moderate Activity

Commits : Listings

Analyzed 1 day ago. based on code collected 1 day ago.
Dec 21, 2024 — Dec 21, 2025
Commit Message Contributor Files Modified Lines Added Lines Removed Code Location Date
Bugfix pxgemm_multiply_a_h_a on GPU: inivial value of c_dev should be set to 0 to protect from NaNs More... 11 months ago
trans_ev: bugfix for no-MPI branch More... 11 months ago
Link against newer RocTX (for rocprofv3): -lroctx -> -lrocprofiler-sdk-roctx More... 11 months ago
Merge remote-tracking branch 'origin/peter_trans_ev_gpu' More... 11 months ago
Add --enable-roctx flag for roctx labels More... 11 months ago
Add NVCC, NVCCFLAGS, HIPCC, HIPCCFLAGS as 'precious' configure variables More... 11 months ago
Merge remote-tracking branch 'origin/master_pre_stage' More... 11 months ago
Merge branch 'peter_rocm_merge_systems_bugfix' into 'master_pre_stage' More... 11 months ago
Add more ELPA timer labels More... 11 months ago
Add rocblas/hipblas backends for rocblas_?[syrk/herk], rocblas_?trmv More... 11 months ago
trans_ev_gpu: add Fortran interfaces for new hip kernels More... 11 months ago
Merge remote-tracking branch 'origin/peter_rocm_merge_systems_bugfix' More... 11 months ago
Merge peter_rocm_merge_systems_bugfix to peter_trans_ev_gpu More... 11 months ago
trans_ev_gpu: add new hip kernels More... 11 months ago
Add HIP/SYCL/OpenMPoffload interfaces for syrk/herk, trmv on GPU More... 11 months ago
trans_ev: partial cleanup More... 11 months ago
Fix compilation for AMD-GPUs More... 11 months ago
Fix of too high register usage in gpu_ccl_copy_buf_recv (in pxgemm_multiply, TT) More... 11 months ago
Fix compilation for HIP on NVIDIA codepath --with-rocsolver More... 11 months ago
Fix compilation for HIP on NVIDIA codepath More... 11 months ago
Fix AMD runtime error (bug in gpu_update_ndef_c) More... 11 months ago
Bugfix for rocsolver and add missing files to Makefile.am for merge_systems HIP kernels More... 12 months ago
Trigger new ci pipeline More... 12 months ago
Merge branch 'master_pre_stage' into 'master' More... about 1 year ago
Fix performance bug in gpu_copy_hvm_hvb_kernel More... about 1 year ago
trans_ev: utilize lower triangularity in trmv_kernel More... about 1 year ago
Merge update_tamt_kernel to trmv_kernel More... about 1 year ago
New gpu_trmv_kernel in trans_ev_gpu More... about 1 year ago
Fix performance bug in trans_ev kernels More... about 1 year ago
Complete NCCL port of trans_ev More... about 1 year ago