Commit Graph

  • de27c8f616 Merge branch 'repackage' into development sfilippone 2024-07-16 13:23:16 +0200
  • 08a69985c8 Take out unneeded file sfilippone 2024-07-16 13:22:47 +0200
  • 13a402031e Fixed docs. Salvatore Filippone 2024-07-16 13:20:36 +0200
  • 497cd31018 Fix configure sfilippone 2024-07-16 13:14:02 +0200
  • 7006665d82 Introduce submodules, adjust Makefile sfilippone 2024-07-12 16:34:48 +0200
  • 0707cc0a72 Take out reference to elldev_mod sfilippone 2024-07-12 13:01:32 +0200
  • 9e8294066d Fix Makefile sfilippone 2024-07-12 13:01:22 +0200
  • 7c256df451 Merge branch 'oacc_loloum' of https://github.com/sfilippone/psblas3 into oacc_loloum tloloum 2024-07-12 09:28:35 +0200
  • 2b5f09ddf9 all methods implementations for psb_d_oacc_csr_sparse_mat tloloum 2024-07-12 09:26:06 +0200
  • 99a334d93d Merge branch 'repackage' into oacc_loloum sfilippone 2024-07-11 14:13:14 +0200
  • e9285c7aad Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage sfilippone 2024-07-11 13:12:37 +0200
  • 1911fec97b Update docs Salvatore Filippone 2024-07-11 13:12:17 +0200
  • 0aa5c9409b Remove spurious pdf file. sfilippone 2024-07-11 12:12:42 +0200
  • e9147c089e Update docs sfilippone 2024-07-11 12:11:07 +0200
  • 681ea2fff7 Updated docs sfilippone 2024-07-11 12:10:14 +0200
  • c7bbfb8b68 new Makefile, test compile well + data vect tloloum 2024-07-10 10:06:27 +0200
  • a81d1d9b68 Now oacc_vect compiles cleanly sfilippone 2024-07-09 13:45:16 +0200
  • 3bb05fab54 Merge branch 'oacc_loloum' of github.com:sfilippone/psblas3 into oacc_loloum sfilippone 2024-07-09 13:18:34 +0200
  • 1f0e591827 Reworked oacc_vect_mod. oacc_mlt_v_X generates ICE, to be fixed sfilippone 2024-07-09 13:16:36 +0200
  • 6be998ac66 oacc_env_mod tloloum 2024-07-09 11:22:28 +0200
  • e0d7091ecc Makefile in openacc/impl sfilippone 2024-07-09 10:04:32 +0200
  • 93c9df0277 Adjust Makefiles & source sfilippone 2024-07-09 10:03:57 +0200
  • e3a3e39caf Modify configure --enable-openacc --with-fcopenacc=..... sfilippone 2024-07-09 10:03:30 +0200
  • 40e40e69f5 Merge branch 'repackage' into development sfilippone 2024-07-09 09:39:48 +0200
  • 2b8671fba6 oacc : d_vect + i_vect + d_csr Théophane Loloum 2024-07-08 10:14:42 +0200
  • d25a746067 Some bugs fixed psblas-bgmres gabrielequatrana 2024-07-07 23:27:00 +0200
  • b22cba4413 Added distributed MGS QR working on GPU gabrielequatrana 2024-07-06 15:14:40 +0200
  • 3f22276aff Added Givens rotations to compute Y one time gabrielequatrana 2024-06-24 19:05:14 +0200
  • 9f2b8a2623 Cleanup sfilippone 2024-06-24 08:18:07 +0200
  • e3a55967a5 Modify CUDA code to compile with 12.4/12.5 sfilippone 2024-06-23 16:03:10 +0200
  • f7d44a70d6 Multivector Product GPU gabrielequatrana 2024-06-13 18:49:03 +0200
  • 34a2a7ddbc Update dpdegenmm.F90 gabrielequatrana 2024-05-31 13:14:27 +0200
  • 39cfcd3893 Fix allocation in coo_impl sfilippone 2024-05-29 16:54:10 +0200
  • a38867be25 Fix allocation in coo_impl sfilippone 2024-05-29 16:51:58 +0200
  • b9ad357648 Improve temp memory allocation in fix_coo sfilippone 2024-05-29 16:25:49 +0200
  • cfa0a785c5 Fixed multiple bugs gabrielequatrana 2024-05-28 18:38:19 +0200
  • fe87ca52e3 Missing impl files repack-csga Salvatore Filippone 2024-05-27 07:15:00 -0400
  • 173ffec2d3 First working version of CSGA. To be tested and refined. Salvatore Filippone 2024-05-27 07:02:00 -0400
  • 3ba2002e60 First attempt at running CSGA. To be debugged. sfilippone 2024-05-24 17:03:46 +0200
  • c35b3b9ef3 Merge branch 'repackage' into repack-csga sfilippone 2024-05-21 17:57:59 +0200
  • 42293c62b6 Fix usage of sync() Salvatore Filippone 2024-05-21 17:49:48 +0200
  • a177e94ba5 Fix comments, Salvatore Filippone 2024-05-21 17:49:40 +0200
  • a3f839ad62 Push some intermediate mods. sfilippone 2024-05-21 17:44:44 +0200
  • c547de218d Merge branch 'repackage' into repack-csga sfilippone 2024-05-21 13:01:59 +0200
  • 15477c9eb2 Fix csga_mod sfilippone 2024-05-21 13:00:53 +0200
  • d71d355b68 Refactor cusparse includes.. sfilippone 2024-05-21 12:59:44 +0200
  • 2e3f862e42 Start refactoring cusparse.h sfilippone 2024-05-21 12:31:02 +0200
  • f91c887c36 Start working on CSR adaptive sfilippone 2024-05-21 11:53:16 +0200
  • 97b962e280 Merge branch 'repackage' into repack-csga sfilippone 2024-05-21 11:33:11 +0200
  • 80d7b1362b Preparation for csga sfilippone 2024-05-21 11:32:02 +0200
  • ee66db5efd Refactor interface to cusparse in preparation for CSR Adaptive sfilippone 2024-05-21 11:25:38 +0200
  • 12a4c21fed Fixes for OpenMP compilation in map_mod sfilippone 2024-05-20 11:47:32 +0200
  • 8e04a4224a Merge changes from repackage. sfilippone 2024-05-16 11:07:58 +0200
  • 54104e0cc6 Merge changes from repackage sfilippone 2024-05-16 10:24:29 +0200
  • e19284eb6c Small omp addition sfilippone 2024-05-16 10:10:08 +0200
  • 10f81577f4 Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage sfilippone 2024-05-16 10:05:45 +0200
  • 35096a2ef9 Cosmetic changes to coo_impl sfilippone 2024-05-16 10:05:11 +0200
  • add3389a81 Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage sfilippone 2024-05-15 16:40:16 +0200
  • c8cc2275d0 Fix cuda/makefile for make -j sfilippone 2024-05-15 16:39:22 +0200
  • 80f54fed09 Test fix gabrielequatrana 2024-05-15 14:10:30 +0200
  • 70f51b9da8 Improve handling of fix_coo buffers with OpenMP sfilippone 2024-05-15 12:05:15 +0200
  • 448533effb Merge remote-tracking branch 'origin/cuda-multivect' into psblas-bgmres gabrielequatrana 2024-05-13 14:35:04 +0200
  • efccdc88cd Fixed another typo cuda-multivect gabrielequatrana 2024-05-13 14:34:13 +0200
  • fabf53a225 Fixed some typos gabrielequatrana 2024-05-13 00:55:29 +0200
  • c08431d71e Merge remote-tracking branch 'origin/cuda-multivect' into psblas-bgmres gabrielequatrana 2024-05-11 14:38:41 +0200
  • 4ff0f112a9 SpMM HDIAG working gabrielequatrana 2024-05-10 22:59:41 +0200
  • ecccb13914 Fix COO fix_coo_inner_rowmajor not to overflow on integers. sfilippone 2024-05-10 13:53:35 +0200
  • a613e963db First step in fix for coo_impl on OpenMP sfilippone 2024-05-10 10:10:54 +0200
  • d01b8145c6 Fix cuda makefile dependencies sfilippone 2024-05-09 17:08:45 +0200
  • d8ed01218d Cleanup hash_map using new indx_map%set_lc sfilippone 2024-05-09 12:30:06 +0200
  • 7ec394ce1c Rename indx_map_mod and put SET_LR/C under ifdef sfilippone 2024-05-09 11:29:23 +0200
  • 7dc64692cc Fix for OpenMP runs in hash_map_mod sfilippone 2024-05-08 14:46:27 +0200
  • e711c53fab Make sure we compile when LPK /= IPK Salvatore Filippone 2024-05-07 07:07:18 -0400
  • f159c7fd4d Merge branch 'repackage' into repack-ovrlp repack-ovrlp sfilippone 2024-05-07 12:42:07 +0200
  • b5a32a59f9 Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage Salvatore Filippone 2024-05-07 06:14:54 -0400
  • 773b79e7bc OpenMP in repl_map Salvatore Filippone 2024-05-07 06:11:15 -0400
  • 98a9005602 Further advances on OpenMP versions of various index maps. Salvatore Filippone 2024-05-07 05:50:45 -0400
  • fa86c91411 Fix OpenMP version of hash_map and hash Salvatore Filippone 2024-05-07 05:04:48 -0400
  • 188dee6842 Add indx_map%inc_lc() method Salvatore Filippone 2024-05-07 04:58:31 -0400
  • bdd04a6911 Adding support to HDIAG SpMM gabrielequatrana 2024-05-06 20:54:37 +0200
  • 0490dd77db ELG SpMM now working gabrielequatrana 2024-05-05 17:39:44 +0200
  • b99aa7a90f Switch off OMP in HASH g2l_ins sfilippone 2024-04-29 15:07:49 +0200
  • 4e0a9e5db8 Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage sfilippone 2024-04-29 15:06:03 +0200
  • e72c0f0bf9 Fix OMP impl of sparse-sparse product sfilippone 2024-04-29 15:04:23 +0200
  • d444a12879 Condition call to x%sync() in vect_mv Salvatore Filippone 2024-04-26 11:35:44 +0200
  • 5e2e1e34fd Introduce set_host() in inner_vect_sv Salvatore Filippone 2024-04-25 18:59:24 +0200
  • c73097d771 Fix rowsum and friends sfilippone 2024-04-24 14:12:45 +0200
  • 14653f9ae3 Add ivshft= in impl sfilippone 2024-04-24 13:27:49 +0200
  • 65519fdb05 Rescale AND col numbers and cleanup impl sfilippone 2024-04-24 13:27:04 +0200
  • 106b92687b Make sure not to call a%a%get_nrows() when not guaranteed sfilippone 2024-04-24 12:20:21 +0200
  • 84cbca96da Fix intent in ilu/inv sfilippone 2024-04-24 09:53:19 +0200
  • 546171316b Fix ILU and set_upper() Salvatore Filippone 2024-04-23 09:58:46 -0400
  • 025350a361 Make sure realloc is always called with size >0 sfilippone 2024-04-23 14:06:27 +0200
  • b74339d2d5 First attempt at a vs ad/and in spmat sfilippone 2024-04-23 10:25:28 +0200
  • ed0da1aef5 Fix base SPMV to include shift sfilippone 2024-04-23 10:25:10 +0200
  • dc6e5bb942 ELG SpMM (compiling but not working) gabrielequatrana 2024-04-22 19:10:22 +0200
  • 6b8199f84b ELG SpMM (not compiling) gabrielequatrana 2024-04-22 17:06:15 +0200
  • 9daa04c3dc Updated HLG SpMM (s,d,c,z) gabrielequatrana 2024-04-18 22:35:27 +0200
  • ba8c32c507 Define merge_nd method sfilippone 2024-04-17 14:27:35 +0200
  • aca1848401 New timings in CG sfilippone 2024-04-17 13:53:23 +0200