1
I Use This!
Moderate Activity

Commits : Listings

Analyzed about 10 hours ago. based on code collected about 10 hours ago.
Sep 12, 2024 — Sep 12, 2025
Commit Message Contributor Files Modified Lines Added Lines Removed Code Location Date
add DPC++ recipe for A100 More... about 2 years ago
bfloat16 is awful to use More... about 2 years ago
half precision header More... about 2 years ago
xgemm-hipblas and related More... about 2 years ago
update for MI 200 series etc More... about 2 years ago
xgemm for cublas (adds FP16) More... about 2 years ago
add xgemm for cublas - WIP More... about 2 years ago
xgemm-onemkl wasn't in make rules More... about 2 years ago
MKL measurement updates More... about 2 years ago
disable TBB and related because they keep breaking it More... about 2 years ago
better xgemm test for onemkl (#630) More... about 2 years ago
Update Intel SYCL compiler driver. Update device selectors and accessors to SYCL2020. (#629) More... about 2 years ago
whitespace only More... about 2 years ago
apply the same fix to MPI+OpenMP More... about 2 years ago
whitespace only More... about 2 years ago
add NV copyright since changed More... about 2 years ago
replace omp flush with proper used of seq_cst atomics More... about 2 years ago
fix petsc transpose - closes #615 (#626) More... about 2 years ago
add SHMEM C transpose with alltoall More... about 2 years ago
perhaps not the fastest, but faster numba More... about 2 years ago
cosmetic changes More... about 2 years ago
added datatypes but they suck More... about 2 years ago
added datatypes but they suck More... about 2 years ago
this works - fixed the dumb More... about 2 years ago
this works, but is dumb More... about 2 years ago
this works, but is dumb More... about 2 years ago
step 3 in p2p More... about 2 years ago
step 2 in p2p More... about 2 years ago
step 1 in p2p More... about 2 years ago
add p2p version More... about 2 years ago