Commit Graph

475 Commits (2f514d1959c9b5ed953c6fce7c925de5787c1f02)

Author SHA1 Message Date
Salvatore Filippone 25f73d15db Fix spspmm allocation to avoid double free error 8 months ago
sfilippone e25d25460e Revert one INTEL fix no longer needed 8 months ago
sfilippone 0239569e2b Final fixes for compilation with INTEL 8 months ago
sfilippone aa30839074 Fix define for compilers, and INTEL fix. 8 months ago
sfilippone 5a0ef22cc2 Rename spspmm 8 months ago
sfilippone 23261bafe6 Restore funny fix for intel 8 months ago
sfilippone 2539b6c715 Fix interface location and use in spspmm 8 months ago
sfilippone dc25c789ef Fixes for Intel compilation take 2. To be completed. 8 months ago
sfilippone 727dc13a98 First attempt at a fix for INTEL 8 months ago
sfilippone da3f16ba56 Use less memory, check on symbmm 11 months ago
sfilippone 86a6ab413a Use less memory in spspmm 11 months ago
sfilippone 07fa2323eb Fixes for IPK8 1 year ago
Salvatore Filippone 4a1610d705 Add check for allocation in certain OpenMP paths 1 year ago
sfilippone 922f7dd278 Tweak SIMD directives for CSR. 1 year ago
sfilippone 110a66e7d0 Switch off some debug write 1 year ago
sfilippone ea6c4181f7 Changed all defines with prefix PSB_ 1 year ago
sfilippone 9ef812bf4a Fix compile mismatch warnings 1 year ago
sfilippone e282fb1a2a Silence more warnings/errors from INTEL 1 year ago
sfilippone 701f297163 Silence warnings uncovered by INTEL 1 year ago
sfilippone 329a295315 Fix bug in heapsort on complex data 1 year ago
sfilippone 7700d4e0da Update copyright 1 year ago
sfilippone c9386c58d8 Remove default(none) from some OpenMP directives. 1 year ago
sfilippone 30810f804e Additional OpenMP tweaks, to be redesigned in the future. 1 year ago
sfilippone 772533b6f1 Avoid excessive OpenMP overhead in SPINS. Will have to be redesigned. 1 year ago
sfilippone 4e71fa971c Modify clean_zeros and have it only at base% 1 year ago
Salvatore Filippone f10c6c1822 Fix GEPRT 2 years ago
sfilippone 949499265e Simplify clean_zeros 2 years ago
sfilippone 1c235f9281 Improve clean_zeros 2 years ago
sfilippone 108d544fc1 Fix clean_zeros to always keep the diagonal 2 years ago
sfilippone 4461b44eda Change name abgdxyz into upd_xyz 2 years ago
sfilippone 39cfcd3893 Fix allocation in coo_impl 2 years ago
sfilippone a38867be25 Fix allocation in coo_impl 2 years ago
sfilippone b9ad357648 Improve temp memory allocation in fix_coo 2 years ago
Salvatore Filippone 42293c62b6 Fix usage of sync() 2 years ago
sfilippone e19284eb6c Small omp addition 2 years ago
sfilippone 35096a2ef9 Cosmetic changes to coo_impl 2 years ago
sfilippone 70f51b9da8 Improve handling of fix_coo buffers with OpenMP 2 years ago
sfilippone ecccb13914 Fix COO fix_coo_inner_rowmajor not to overflow on integers. 2 years ago
sfilippone a613e963db First step in fix for coo_impl on OpenMP 2 years ago
sfilippone 4e0a9e5db8 Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage 2 years ago
sfilippone e72c0f0bf9 Fix OMP impl of sparse-sparse product 2 years ago
Salvatore Filippone d444a12879 Condition call to x%sync() in vect_mv 2 years ago
Salvatore Filippone 5e2e1e34fd Introduce set_host() in inner_vect_sv 2 years ago
sfilippone 025350a361 Make sure realloc is always called with size >0 2 years ago
sfilippone ba8c32c507 Define merge_nd method 2 years ago
sfilippone 86be8ebcd0 New method W%XYZW() 2 years ago
Salvatore Filippone 4e611bb078 Enable psi_abgdxyz 2 years ago
sfilippone 83ededd02b Implementatino of abgd_xyz 2 years ago
sfilippone 3aa3c795e9 Refactor assembly and cnv 2 years ago
sfilippone 49e99a3e82 Fix conversion and product to enable overlap with GPU 2 years ago