CFD/hypre
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
12,100 Commits 1 Branch 84 Tags 207 MiB
c8f1aba2d6
Commit Graph

12100 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Fredrik Ekre
e8990caf7a
Fix a typo in documentation for hybrid solver. (#685) 2022-07-20 06:52:01 -07:00
Ruipeng Li
275d04d987
Cmake cuda update (#675) 
This PR contains CMake changes for CUDA.

Co-authored-by: pengwang <penwang@nvidia.com>
Co-authored-by: Sarah Virginia Osborn <osborn9@llnl.gov>
 2022-07-19 22:04:42 -07:00
Ruipeng Li
22d35a4d09
Backward compatible ROCm header update. (#680) 
Backward compatible update to rocm header include path.

Co-authored-by: Paul T. Bauman <ptbauman@gmail.com>
 2022-07-15 23:28:00 -07:00
Ruipeng Li
5eb84ec1db
Fix GPU memory leak (#677) 
This PR fixes a memory leak on GPUs.
 2022-07-15 11:20:41 -07:00
Ruipeng Li
ad50e4e123
config/update.sh (#671) 
Minor changes to `configure`.
 2022-07-08 16:33:48 -07:00
Wayne Mitchell
6c4803b90d
Sycl pmis (#664) 
Port PMIS coarsening to SYCL
 2022-07-08 14:00:23 -07:00
Ruipeng Li
bd514cf998
Cusolver (#653) 
This PR adds the option of using cuSolver.

Co-authored-by: Paul Mullowney <Paul.Mullowney@nrel.gov>
 2022-07-06 09:37:32 -07:00
Ruipeng Li
14ee602fbf
Regression (#668) 
This PR updates regression test scripts and benchmark performance results.
 2022-07-05 17:10:43 -07:00
Wayne Mitchell
6f3bccb92c
Sycl interp (#638) 
This adds sycl support for interpolation optionsExtInterp, ExtPIInterp,
and ExtPEInterp (which correspond to InterpType 6, 14, 16, 17, 18).
Generation of the strength matrix is also ported to sycl.
Further unification of cuda/hip/sycl kernel functions.
Adds regression tests for the sycl backend on arcticus including both ij and struct tests.
 2022-07-05 16:10:36 -07:00
Ruipeng Li
63ed624709
Merge pull request #666 from hypre-space/interp_trunc 
This PR optimizes interpolation truncation routines on GPUs.
 2022-06-30 14:34:59 -07:00
Ruipeng Li
aa153c9c89 astyle 2022-06-30 14:23:24 -07:00
Ruipeng Li
750d4877a4 Merge branch 'interp_trunc' of github.com:hypre-space/hypre into interp_trunc 2022-06-29 11:54:06 -07:00
Ruipeng Li
5dfda6b009 update saved.lassen 2022-06-29 11:42:23 -07:00
Ruipeng Li
6611451694 update tioga saved 2022-06-29 10:41:47 -07:00
Ruipeng Li
ac09576ef9 bug fix 2022-06-29 10:41:22 -07:00
Ruipeng Li
2fa29169c6 bug fix 2022-06-29 10:06:09 -07:00
Ruipeng Li
172787d7d9 delete files 2022-06-28 22:18:39 -07:00
Ruipeng Li
b03f350bf1 fix after merge 2022-06-28 22:15:45 -07:00
Ruipeng Li
4ed68414e5 Merge branch 'master' of github.com:hypre-space/hypre into interp_trunc 2022-06-28 22:10:57 -07:00
Ruipeng Li
b3573fb7a5 .saved 2022-06-28 21:09:23 -07:00
Wayne Mitchell
4411530e76
hypre_Item (#645) 
Introduce hypre_DeviceItem to further unify cuda/hip/sycl implementation.
Unify some wrappers for thread/warp-level kernel routines.
 2022-06-28 08:27:36 -07:00
Ruipeng Li
e270c561b0
Spgemm (#639) 
This PR includes optimizations for hypre's SpGEMM and ParSpGEMM kernels

Co-authored-by: Wayne Mitchell <mitchell82@llnl.gov>
Co-authored-by: Paul T. Bauman <ptbauman@gmail.com>
Co-authored-by: Sarah Osborn <30503782+osborn9@users.noreply.github.com>
 2022-06-24 10:42:16 -07:00
Victor A. Paludetto Magri
8268b9f1e1
hypre_ParCSRMatrixPrintIJ on device (#655) 
hypre_ParCSRMatrixPrintIJ works for matrices living on the device w/o the need of UVM support. A explicit copy is to host memory is performed in this function prior to printing the files.
 2022-06-22 20:49:57 -04:00
Victor A. Paludetto Magri
850fd47d07
Fix chebyshev smoother for singular problems (#657) 
See PR's description for additional info
 2022-06-22 20:47:09 -04:00
Ruipeng Li
b58585e0f0
add a func (#646) 
This PR adds a function to perform local transposition of ParCSR.
 2022-06-21 08:52:21 -07:00
Ruipeng Li
322e6a5e6e astyle 2022-06-17 10:14:00 -07:00
Ruipeng Li
18f85886ff remove debug code 2022-06-17 09:15:08 -07:00
Ruipeng Li
b9b93c45ef save debug code of Pass0 2022-06-17 09:13:58 -07:00
Ruipeng Li
8d54b78730 fix some nvtx region names 2022-06-15 23:18:00 -07:00
Ruipeng Li
3509640354 optimized interp_trunc 2022-06-15 22:55:35 -07:00
Ulrike Yang
ac9d7d0d7b updated CHANGELOG 2022-06-14 12:02:25 -07:00
Rob Falgout
03e0150ee4 Change release number to 2.25.0 2022-06-13 17:17:54 -07:00
Rob Falgout
14cfc2db1e Update CHANGELOG for 2.25.0 release 2022-06-13 17:14:43 -07:00
Ruipeng Li
6b34e985eb minor change 2022-06-13 16:20:03 -07:00
Ruipeng Li
dfa39f680b filtering out srun warnings 2022-06-13 11:11:08 -07:00
Ruipeng Li
e6bfe8bd62 fixed typo 2022-06-12 23:50:39 -07:00
Ruipeng Li
5dbe0a2a10 saved.tioga 2022-06-12 23:46:01 -07:00
Ruipeng Li
a5b10499cb tune for AMD GPUs 2022-06-12 11:34:22 -07:00
Ruipeng Li
ee88d0b1a4 header 2022-06-11 11:49:56 -07:00
Ruipeng Li
c76cd1fd04 bug fix 2022-06-10 15:08:56 -07:00
Ruipeng Li
84baffc1da add license 2022-06-10 15:08:41 -07:00
Ruipeng Li
cb5814c4f4 minor change 2022-06-10 15:07:57 -07:00
Ruipeng Li
6ce70c135e bug fix 2022-06-10 14:47:46 -07:00
Ruipeng Li
7a7a63f802 Merge branch 'spgemm' of github.com:hypre-space/hypre into spgemm 2022-06-10 12:50:32 -07:00
Ruipeng Li
834bac5d8f update bench perf. on lassen 2022-06-10 12:50:24 -07:00
Ruipeng Li
637af55397 Merge branch 'spgemm' of github.com:hypre-space/hypre into spgemm 2022-06-10 12:14:35 -07:00
Ruipeng Li
c9b9a36354 update bench perf. on ray 2022-06-10 12:14:20 -07:00
Wayne Mitchell
3a735f9ccd Merge branch 'spgemm' of github.com:hypre-space/hypre into spgemm 2022-06-10 19:07:39 +00:00
Wayne Mitchell
951fa56baa Fix copy paste error 2022-06-10 19:06:34 +00:00
Wayne Mitchell
7dc8321f4a Additional fixes for sycl build. Note that CSR matrix memory location must be set correctly before calling hypre_CSRMatrixSetRownnz. 2022-06-10 19:02:35 +00:00