Ruipeng Li
e5393bc0eb
fix domp build
2022-03-28 22:55:18 -07:00
Ruipeng Li
caec03c7ad
Merge branch 'sycl_par_matmat' of github.com:hypre-space/hypre into parspgemm
2022-03-25 18:59:19 -07:00
Ruipeng Li
23b8527c1d
fix after merge
2022-03-25 18:53:02 -07:00
Ruipeng Li
68be11b70f
fix after merge; change CUDAKernel to GPUKernel
2022-03-25 18:52:40 -07:00
Wayne Mitchell
ce30e2faa4
Backward compatibility for UseCusparse
2022-03-26 01:09:17 +00:00
Ruipeng Li
ac65ca58fe
changes to mm
2022-03-25 15:53:16 -07:00
Wayne Mitchell
5f7608b875
Change UseCusparse to UseVendor
2022-03-25 22:07:05 +00:00
Wayne Mitchell
112691e2d1
Remove debugging code
2022-03-25 21:07:58 +00:00
Wayne Mitchell
b860e28c72
Clean up
2022-03-25 20:57:41 +00:00
Wayne Mitchell
bb2cb43232
Merge branch 'master' into sycl_par_matmat
2022-03-25 20:27:17 +00:00
Wayne Mitchell
b5de7f7dfd
MGR bug fix and no longer throw error for zero len kernel launches for sycl
2022-03-25 19:41:45 +00:00
Ruipeng Li
86cff8da61
Merge branch 'master' of github.com:hypre-space/hypre into parspgemm
2022-03-25 12:31:12 -07:00
Wayne Mitchell
6b5a13cedf
Bug fix! Still need to clean up some further debugging code.
2022-03-25 00:56:39 +00:00
Wayne Mitchell
511c0ec77e
Remove some debugging code. Temporary changes to solvers.jobs
2022-03-23 18:49:46 +00:00
Ruipeng Li
5fe37b2286
hypre_ParPrintf ( #604 )
...
This PR adds hypre_ParPrintf. Prints to standard out, only from the first processor in the communicator. Calls from other processes are ignored.
2022-03-21 09:10:01 -07:00
Wayne Mitchell
f2fa2e9577
Lots of ugly debugging code in here, but I have also fixed a couple esoteric things. Saving with debugging code in just in case I need to go back and use it.
2022-03-18 23:49:23 +00:00
Ruipeng Li
5513fd5115
Merge branch 'ParPrintf' of github.com:hypre-space/hypre into parspgemm
2022-03-18 15:20:52 -07:00
Ruipeng Li
7300f4b937
Merge branch 'master' of github.com:hypre-space/hypre into parspgemm
2022-03-18 15:17:45 -07:00
Ruipeng Li
04239e769a
remove hypre_vprintf
2022-03-18 13:32:22 -07:00
Ruipeng Li
96985f04e2
ParPrintf; hypre_vprintf
2022-03-18 12:10:47 -07:00
Ruipeng Li
adfd07c509
Fix build on FreeBSD/powerpc*. ( #603 )
...
lr collides with lr from machine/frame.h header (link register):
Co-authored-by: Piotr Kubaj <pkubaj@FreeBSD.org>
2022-03-18 10:16:20 -07:00
Rob Falgout
fa43ea82e3
Bug fix in prefix sum for OpenMP IJ interface ( #602 )
...
This fixes a bug found in issue #522 for the prefix sum openmp code in IJ.
2022-03-16 10:56:09 -07:00
Ruipeng Li
e5f6655ba0
initial support for pattern only matrices (spgemm only)
2022-03-16 09:32:12 -07:00
Ruipeng Li
d079a90fb8
Merge branch 'master' of github.com:hypre-space/hypre into nvcollab
2022-03-15 08:32:25 -07:00
Ruipeng Li
92faac9748
fix memory location ( #600 )
...
This PR fixes a number of memory location issues in memory copy and memset. It also adds more strict checking in memory.c in the debug mode.
2022-03-14 11:19:28 -07:00
Victor A. Paludetto Magri
6fd043c9c2
(S)Struct IO on GPUs ( #599 )
...
This PR extends the (semi)-struct matrix/vector IO functions added on #583 with GPU support. Additionally:
* Fix regression tests on Lassen.
* Read data values into host memory
* Update Umatrix read algorithm when the ParCSRMatrix is expected to live on the device
* Reset deallocated pointers at hypre_IJMatrixDestroyParCSR to NULL
* Clone rownnz info if present on a CSRMatrix
* Reduce memory transfer and remove unused variables
* Fix bug with -print option
* Build rownnz info also when the ParCSRMatrix is in assembled state
* Remove a few instances of "return ierr"
* Refactor (s)struct IO - code works with cuda and without UM
* Add executables to gitignore
2022-03-13 20:14:23 -07:00
Ruipeng Li
c9a6c67229
Merge branch 'master' of github.com:hypre-space/hypre into nvcollab
2022-03-11 18:34:45 -08:00
Ruipeng Li
f7787ab0ae
fixes coarsening.jobs.14 ( #598 )
...
a temporary "fix"
2022-03-11 18:25:03 -08:00
Ruipeng Li
793b22aaf0
Merge branch 'nvcollab' of github.com:hypre-space/hypre into nvcollab
2022-03-11 08:34:20 -08:00
Ruipeng Li
97f3254d71
Merge branch 'master' of github.com:hypre-space/hypre into nvcollab
2022-03-11 08:33:31 -08:00
Ruipeng Li
8c344aee9a
Invalid assumption on exclusive_scan ( #575 )
...
This PR fixes a number of initialization problems with exclusive_scan on GPUs due to invalid assumptions of this function.
2022-03-11 08:32:26 -08:00
Rui-peng Li
700b0328bf
bug fix
2022-03-10 22:19:22 -06:00
Ruipeng Li
9498625db4
Merge branch 'nvcollab' of github.com:hypre-space/hypre into nvcollab
2022-03-10 18:31:13 -08:00
Ruipeng Li
50c88ab95d
minor changes
2022-03-10 18:30:52 -08:00
Ruipeng Li
c143265c61
regression on ray
2022-03-10 17:41:49 -08:00
Ruipeng Li
14a336c28b
accidentally deleted io.sh
2022-03-10 13:30:31 -08:00
Ruipeng Li
2d06b53c4e
benchmark ij on lassen
2022-03-10 13:26:15 -08:00
Ruipeng Li
815f2d57e0
add cublas/cusparse precision macros
2022-03-10 12:12:32 -08:00
Ruipeng Li
90cbe64fee
saved.lassen
2022-03-10 08:45:27 -08:00
Ruipeng Li
7681f7f180
add cublas to makefile
2022-03-10 08:43:44 -08:00
Ruipeng Li
8ecee0b47d
update hypre's spmv
2022-03-09 22:36:16 -08:00
Ruipeng Li
31ca2338d2
saved.lassen
2022-03-09 16:22:22 -08:00
Ruipeng Li
009501d51c
bug fix
2022-03-09 16:14:56 -08:00
Ruipeng Li
86dae0be5b
a minor change
2022-03-09 14:29:22 -08:00
Ruipeng Li
1dc1261fe8
fix cpu regression
2022-03-09 14:26:40 -08:00
Ruipeng Li
f8fd57ab2a
updated saved perf on ray
2022-03-09 13:54:00 -08:00
Ruipeng Li
9b8627ce84
update lassen banchmark saved results
2022-03-09 13:09:36 -08:00
Ruipeng Li
7a8cf68b9a
add -repeats 2 for struct benchmark jobs
2022-03-09 13:09:07 -08:00
Ruipeng Li
9dda5af3c4
struct.c driver for reps == 2
2022-03-09 12:31:46 -08:00
Paul T. Bauman
08b901f24d
Silence clang warning
...
Should not be a change in behavior, just making explicit the
order of operations with parantheses and silencing a clang warning.
2022-03-09 13:31:32 -06:00
