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
Paul T. Bauman
d55a409bdb
Silence uninitialized var HIP warnings
...
This should be a benign change. What happens is that the first one or two
workitems/threads in each workgroup/block read a value and then broadcast
it (with __shfl_sync or similar) and then code branching happens
based on this value. But the compiler can't see it all the way
through it so we get some uninitialized var warnings.
2022-03-09 13:31:32 -06:00
Ruipeng Li
9c33e9a263
regression tests
2022-03-09 08:54:42 -08:00
Ruipeng Li
63c9fa65a2
add using hypre's spmv option
2022-03-08 22:11:31 -08:00
Wayne Mitchell
5e90f43cbc
astyle
2022-03-08 23:51:41 +00:00
Wayne Mitchell
34c16787b7
Addition of MatMat and TMatMat routines and clean up
2022-03-08 23:50:48 +00:00
Wayne Mitchell
297ff5d5a7
Par matmat is verified correcct for a small example
2022-03-08 21:08:47 +00:00
Ruipeng Li
7443a2ac6c
missed some sync in the last commit
2022-03-07 23:54:03 -08:00
Ruipeng Li
e1b9a56405
add gpu sync for mpi
2022-03-07 23:34:33 -08:00
Ruipeng Li
8ee20f4812
cudamallocasync
2022-03-07 16:54:56 -08:00
Ruipeng Li
df0f6dbba7
configure options: cublas; cudamallocasync
2022-03-07 16:40:32 -08:00
Ruipeng Li
d7728d0bce
updated ij driver for 2nd solve
2022-03-07 15:16:00 -08:00
Ruipeng Li
b97fbc13ed
sync device at ending timing
2022-03-07 15:13:08 -08:00
Ruipeng Li
c2e4836c1e
bug fix
2022-03-05 10:36:53 -08:00
Ruipeng Li
a51bb880a8
bug fix
2022-03-05 09:46:16 -08:00
Ruipeng Li
03546b428f
Merge branch 'master' of github.com:hypre-space/hypre into nvcollab
2022-03-04 22:18:02 -08:00
Paul T. Bauman
251cd3d269
Need -O1 instead of -O0 for HIP in debug mode ( #588 )
...
This PR changes -O0 in debug mode to -O1 with HIP (at this time).
2022-03-04 12:40:35 -08:00
Ruipeng Li
95e6433fc7
GPU support with single precision ( #572 )
...
This PR fixes the GPU support with single precision.
2022-03-04 12:05:32 -08:00
Ruipeng Li
ebd6eb88c3
bug fix; nonsquare rap ( #581 )
...
This PR fixes a corner case of the RAP routine for RAP matrix that is globally square but not locally.
2022-03-03 21:26:17 -08:00
