gabrielequatrana
|
fabf53a225
|
Fixed some typos
|
2 years ago |
|
gabrielequatrana
|
4ff0f112a9
|
SpMM HDIAG working
|
2 years ago |
|
gabrielequatrana
|
bdd04a6911
|
Adding support to HDIAG SpMM
|
2 years ago |
|
gabrielequatrana
|
0490dd77db
|
ELG SpMM now working
|
2 years ago |
|
gabrielequatrana
|
dc6e5bb942
|
ELG SpMM (compiling but not working)
|
2 years ago |
|
gabrielequatrana
|
6b8199f84b
|
ELG SpMM (not compiling)
|
2 years ago |
|
gabrielequatrana
|
9daa04c3dc
|
Updated HLG SpMM (s,d,c,z)
|
2 years ago |
Salvatore Filippone
|
ccb4f73dca
|
Choose version of HLG-multivect kernel
|
2 years ago |
sfilippone
|
19aa3f56b6
|
Merge branch 'repackage' into cuda-multivect
|
2 years ago |
|
sfilippone
|
148a5e5e14
|
Check for shmemsize
|
2 years ago |
|
sfilippone
|
6f92a5c37a
|
Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage
|
2 years ago |
|
sfilippone
|
553531eefb
|
Take out obsolete ilu_fct source files
|
2 years ago |
|
sfilippone
|
2f575894fc
|
Fix --with-cudacc in configure
|
2 years ago |
|
Salvatore Filippone
|
378c126055
|
Use MMBSZ=8, prepare to check shmem size
|
2 years ago |
|
Salvatore Filippone
|
897cfb4028
|
Multicolumn HLG product
|
2 years ago |
|
Salvatore Filippone
|
5b95f1920c
|
Regenerate configure, fix typo in hlg_vect_mv
|
2 years ago |
|
gabrielequatrana
|
08984619dc
|
Fixed SpMM for HLG
|
2 years ago |
|
gabrielequatrana
|
beb418e00b
|
Fixed SpMM for ELG (AXPBY GPU not working)
|
2 years ago |
|
gabrielequatrana
|
c807d88c57
|
SpMM using Cusparse dedicated routine (CSRG)
|
2 years ago |
|
Salvatore Filippone
|
399818a482
|
Never do arithmetic on a (void *)
|
2 years ago |
|
Salvatore Filippone
|
1ecf36c9c3
|
Merge branch 'psblas-bgmres' of github.com:sfilippone/psblas3 into psblas-bgmres
|
2 years ago |
|
Salvatore Filippone
|
7d74ebf5c4
|
Make multivectors work
|
2 years ago |
|
gabrielequatrana
|
82715fec9b
|
Fixed SpMM for CSRG
|
2 years ago |
|
gabrielequatrana
|
409b51e609
|
Try to fix SpMM
|
2 years ago |
|
gabrielequatrana
|
ee140bc8dd
|
Read/Write multivect fixed (SpMM bug)
|
2 years ago |
|
gabrielequatrana
|
a624b7098b
|
Cuda multivect methods implementation
|
2 years ago |
|
sfilippone
|
c1e4f9c2b1
|
Merge branch 'repackage' into psblas-bgmres, fixes to resolve merge
|
2 years ago |
|
sfilippone
|
0760e4d553
|
Fix C function declarations for compilation with LLVM/clang in CUDA
|
2 years ago |
|
sfilippone
|
4347c663c2
|
Change conftest **argv to recognize CUDA_VERSION.
|
2 years ago |
|
sfilippone
|
a2f92e616f
|
Put VOLATILE under ifdef for FLANG
|
2 years ago |
|
sfilippone
|
59e6df73a4
|
Make sure configure recognizes FLANG
|
2 years ago |
|
gabrielequatrana
|
02fb43ba82
|
Fixed convergence
|
2 years ago |
|
gabrielequatrana
|
6b785d66c6
|
Check convergence now working
|
2 years ago |
|
gabrielequatrana
|
0839165bdc
|
Added convergence check
|
2 years ago |
|
sfilippone
|
0023b8ac78
|
Compile adjcncy_fnd_owner
|
2 years ago |
|
sfilippone
|
3a25d7b04a
|
Fixes for LLVM compilation
|
2 years ago |
|
sfilippone
|
373d841bce
|
Don't need renaming of psi_gth and psi_sct
|
2 years ago |
|
sfilippone
|
472f16f0df
|
Fix compilation with --enable-serial
|
2 years ago |
|
gabrielequatrana
|
1b79939255
|
Fixed some bugs (QR_fact serial)
|
2 years ago |
|
gabrielequatrana
|
676652fcff
|
Working parallel (QR_fact serial)
|
2 years ago |
|
gabrielequatrana
|
d10631530f
|
Init Parallelize
|
2 years ago |
|
sfilippone
|
e0a4d362fa
|
Define flag TRACK_CUDA_MALLOC
|
2 years ago |
|
gabrielequatrana
|
6987582c30
|
Done SERIAL
|
2 years ago |
|
Salvatore Filippone
|
b5f1442ac8
|
Merge branch 'nond-rep' into repackage
|
2 years ago |
|
sfilippone
|
48455190ec
|
Add GPU version of XYZW
|
2 years ago |
|
sfilippone
|
a11f328e62
|
Added CUDA version of XYZW
|
2 years ago |
|
sfilippone
|
86be8ebcd0
|
New method W%XYZW()
|
2 years ago |
|
sfilippone
|
b5d5f97661
|
Improve cuda%zero()
|
2 years ago |
|
sfilippone
|
0e269ed641
|
typo in Cabgdxyz
|
2 years ago |
|
Salvatore Filippone
|
d95077ffd6
|
Fix typo in vectordev_mod
|
2 years ago |