Salvatore Filippone
|
42293c62b6
|
Fix usage of sync()
|
6 months ago |
|
Salvatore Filippone
|
a177e94ba5
|
Fix comments,
|
6 months ago |
sfilippone
|
d71d355b68
|
Refactor cusparse includes..
|
6 months ago |
|
sfilippone
|
2e3f862e42
|
Start refactoring cusparse.h
|
6 months ago |
|
sfilippone
|
ee66db5efd
|
Refactor interface to cusparse in preparation for CSR Adaptive
|
6 months ago |
|
sfilippone
|
12a4c21fed
|
Fixes for OpenMP compilation in map_mod
|
6 months ago |
|
sfilippone
|
e19284eb6c
|
Small omp addition
|
6 months ago |
|
sfilippone
|
10f81577f4
|
Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage
|
6 months ago |
|
sfilippone
|
35096a2ef9
|
Cosmetic changes to coo_impl
|
6 months ago |
|
sfilippone
|
add3389a81
|
Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage
|
6 months ago |
|
sfilippone
|
c8cc2275d0
|
Fix cuda/makefile for make -j
|
6 months ago |
|
sfilippone
|
70f51b9da8
|
Improve handling of fix_coo buffers with OpenMP
|
6 months ago |
|
sfilippone
|
ecccb13914
|
Fix COO fix_coo_inner_rowmajor not to overflow on integers.
|
6 months ago |
|
sfilippone
|
a613e963db
|
First step in fix for coo_impl on OpenMP
|
6 months ago |
|
sfilippone
|
d01b8145c6
|
Fix cuda makefile dependencies
|
6 months ago |
|
sfilippone
|
d8ed01218d
|
Cleanup hash_map using new indx_map%set_lc
|
6 months ago |
|
sfilippone
|
7ec394ce1c
|
Rename indx_map_mod and put SET_LR/C under ifdef
|
6 months ago |
|
sfilippone
|
7dc64692cc
|
Fix for OpenMP runs in hash_map_mod
|
6 months ago |
|
Salvatore Filippone
|
e711c53fab
|
Make sure we compile when LPK /= IPK
|
6 months ago |
|
Salvatore Filippone
|
b5a32a59f9
|
Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage
|
6 months ago |
|
Salvatore Filippone
|
773b79e7bc
|
OpenMP in repl_map
|
6 months ago |
|
Salvatore Filippone
|
98a9005602
|
Further advances on OpenMP versions of various index maps.
|
6 months ago |
|
Salvatore Filippone
|
fa86c91411
|
Fix OpenMP version of hash_map and hash
|
6 months ago |
|
Salvatore Filippone
|
188dee6842
|
Add indx_map%inc_lc() method
|
6 months ago |
|
sfilippone
|
b99aa7a90f
|
Switch off OMP in HASH g2l_ins
|
6 months ago |
|
sfilippone
|
4e0a9e5db8
|
Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage
|
6 months ago |
|
sfilippone
|
e72c0f0bf9
|
Fix OMP impl of sparse-sparse product
|
6 months ago |
|
Salvatore Filippone
|
d444a12879
|
Condition call to x%sync() in vect_mv
|
6 months ago |
|
Salvatore Filippone
|
5e2e1e34fd
|
Introduce set_host() in inner_vect_sv
|
7 months ago |
|
sfilippone
|
025350a361
|
Make sure realloc is always called with size >0
|
7 months ago |
|
sfilippone
|
ba8c32c507
|
Define merge_nd method
|
7 months ago |
|
sfilippone
|
aca1848401
|
New timings in CG
|
7 months ago |
|
sfilippone
|
e18de650f2
|
Take out debug print
|
7 months ago |
|
sfilippone
|
6f92a5c37a
|
Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage
|
7 months ago |
|
sfilippone
|
553531eefb
|
Take out obsolete ilu_fct source files
|
7 months ago |
|
sfilippone
|
2f575894fc
|
Fix --with-cudacc in configure
|
7 months ago |
|
sfilippone
|
0760e4d553
|
Fix C function declarations for compilation with LLVM/clang in CUDA
|
7 months ago |
|
sfilippone
|
4347c663c2
|
Change conftest **argv to recognize CUDA_VERSION.
|
7 months ago |
|
sfilippone
|
a2f92e616f
|
Put VOLATILE under ifdef for FLANG
|
7 months ago |
|
sfilippone
|
59e6df73a4
|
Make sure configure recognizes FLANG
|
7 months ago |
|
sfilippone
|
0023b8ac78
|
Compile adjcncy_fnd_owner
|
8 months ago |
|
sfilippone
|
3a25d7b04a
|
Fixes for LLVM compilation
|
8 months ago |
|
sfilippone
|
373d841bce
|
Don't need renaming of psi_gth and psi_sct
|
8 months ago |
|
sfilippone
|
472f16f0df
|
Fix compilation with --enable-serial
|
8 months ago |
|
sfilippone
|
e0a4d362fa
|
Define flag TRACK_CUDA_MALLOC
|
8 months ago |
|
Salvatore Filippone
|
b5f1442ac8
|
Merge branch 'nond-rep' into repackage
|
8 months ago |
|
sfilippone
|
48455190ec
|
Add GPU version of XYZW
|
8 months ago |
|
sfilippone
|
a11f328e62
|
Added CUDA version of XYZW
|
8 months ago |
|
sfilippone
|
86be8ebcd0
|
New method W%XYZW()
|
8 months ago |
|
sfilippone
|
b5d5f97661
|
Improve cuda%zero()
|
9 months ago |