Salvatore Filippone
|
5430ba0e22
|
Fix multivect constructor in CUDA
|
2 months ago |
sfilippone
|
6972c50542
|
Updated readme
|
3 months ago |
|
sfilippone
|
744f14d2f5
|
Merge branch 'oacc_loloum' into repackage
|
3 months ago |
|
sfilippone
|
5903c0b272
|
Fix DOT in OpenACC
|
3 months ago |
|
sfilippone
|
4822861b73
|
Merge branch 'oacc_loloum' of github.com:sfilippone/psblas3 into oacc_loloum
|
3 months ago |
|
sfilippone
|
49469ce021
|
Various changes into openacc
|
3 months ago |
|
sfilippone
|
3d9fee2dd7
|
Fix DOT on CUDA vectors.
|
3 months ago |
|
sfilippone
|
949499265e
|
Simplify clean_zeros
|
3 months ago |
|
sfilippone
|
c74be820ea
|
Rework configry for CUDA
|
3 months ago |
|
sfilippone
|
ee56c6be3c
|
Cosmetic changes to OpenACC vectors
|
3 months ago |
|
sfilippone
|
740609a4d8
|
Fix present() clauses
|
3 months ago |
|
sfilippone
|
68f20c0e7a
|
Modify init
|
3 months ago |
|
sfilippone
|
9601a837f5
|
Define --enable-cuda --with-cudadir for CUDA configry
|
3 months ago |
|
sfilippone
|
1c235f9281
|
Improve clean_zeros
|
3 months ago |
|
sfilippone
|
108d544fc1
|
Fix clean_zeros to always keep the diagonal
|
3 months ago |
|
sfilippone
|
8ab5cef448
|
OpenACC environment fixes
|
3 months ago |
|
sfilippone
|
174a8e7aef
|
Merge branch 'oacc_loloum' into repackage
|
4 months ago |
|
sfilippone
|
a8dcba2964
|
Merge branch 'development' into repackage
|
4 months ago |
|
sfilippone
|
736f3cc629
|
Merge branch 'repackage' of github.com:sfilippone/psblas3 into repackage
|
4 months ago |
|
sfilippone
|
e5504ddddc
|
Fix memory traffic in GTH/SCT
|
4 months ago |
|
sfilippone
|
096bce08c1
|
Merged changes from V4 OpenACC
|
4 months ago |
|
sfilippone
|
bcbe0c89c7
|
Backporting fixes from version 4
|
4 months ago |
|
sfilippone
|
6236f3489c
|
Remove obsolete files
|
5 months ago |
|
sfilippone
|
f783478df3
|
Merge updates from V4
|
5 months ago |
|
sfilippone
|
fbb974fb8b
|
Change name sync|free space, unify allocate impl
|
5 months ago |
|
sfilippone
|
479135c62d
|
Merge some changes from V4
|
5 months ago |
|
sfilippone
|
95c546aadd
|
Fix OpenACC version of ELL vect_mv
|
5 months ago |
|
sfilippone
|
fa5e7ff945
|
Fixes for vector methods and sync()
|
5 months ago |
|
sfilippone
|
9314b2cf53
|
Fix missing method in oacc_ell
|
5 months ago |
|
sfilippone
|
8220140729
|
Merged recent changes from development
|
5 months ago |
|
sfilippone
|
cf2cc6cab9
|
Precedence of oacc_vect modules
|
5 months ago |
|
sfilippone
|
3168b7e8f7
|
Merge branch 'development' into oacc_loloum
|
5 months ago |
|
sfilippone
|
7857015923
|
Cosmetic changes to vect_mod
|
5 months ago |
|
sfilippone
|
2709aa9f16
|
Fix upd_xyz name
|
5 months ago |
|
sfilippone
|
2982aaee27
|
Implementation in OpenACC for ELL and HLL into templates. Merge from development
|
5 months ago |
|
sfilippone
|
ff8513b4c6
|
Ignore .smod files in git
|
5 months ago |
|
sfilippone
|
03aaa090db
|
New AX_OPENACC macro and supporting flags
|
5 months ago |
|
sfilippone
|
464baceb13
|
HLL loop nest cannot run with collapse
|
5 months ago |
|
sfilippone
|
a28d3b048b
|
Fix configure for OpenACC (added warning message)
|
5 months ago |
tloloum
|
9c244964db
|
Merge branch 'development' into oacc_merge
merge development into oacc
|
5 months ago |
|
tloloum
|
55d1067ec2
|
collapse loop
|
5 months ago |
tloloum
|
e6fa1d17a2
|
oacc hll
|
6 months ago |
|
sfilippone
|
4461b44eda
|
Change name abgdxyz into upd_xyz
|
6 months ago |
|
tloloum
|
10ec5eafab
|
ELL oacc impl
|
6 months ago |
|
tloloum
|
162b2fc78f
|
beginning of oacc_ell
|
6 months ago |
|
tloloum
|
08a9744413
|
moving test
|
6 months ago |
|
tloloum
|
b5a8c549dd
|
psb_d_oacc_pde3d draft
|
6 months ago |
|
sfilippone
|
e8491380e2
|
Take out obsolete test targets from makefile
|
6 months ago |
|
sfilippone
|
9e18545151
|
Fix typos
|
6 months ago |
|
sfilippone
|
686bac4224
|
Account for S/D/C/Z variants
|
6 months ago |