sfilippone
|
d887d5ee8a
|
Split mods from impl in build process
|
2025-11-21 15:13:10 +01:00 |
|
sfilippone
|
e508de917f
|
Fix CUDA include copying
|
2025-11-21 13:51:21 +01:00 |
|
sfilippone
|
390144126c
|
Fixes for compilation with CUDA 13.0
|
2025-09-25 13:35:30 +02:00 |
|
sfilippone
|
9e682111be
|
Merge branch 'development' into cmake
|
2025-06-03 08:41:14 +02:00 |
|
sfilippone
|
07fa2323eb
|
Fixes for IPK8
|
2025-06-01 20:56:11 +02:00 |
|
gnumlab
|
1b667c2c1e
|
remove unused files from building
|
2025-05-05 15:30:33 +02:00 |
|
Luca Pepè Sciarria
|
aea5e36b63
|
init cuda CMakeLists.txt
|
2025-04-28 10:22:41 +02:00 |
|
sfilippone
|
24e4b76241
|
Fix cuda subdir makefile
|
2025-03-31 10:39:54 +02:00 |
|
sfilippone
|
c4ab4be45d
|
Cleanup some cuda compile warnings.
|
2025-03-27 11:23:40 +01:00 |
|
sfilippone
|
243fe4e78f
|
Split type definitions from psb_config
|
2025-03-17 17:50:26 +01:00 |
|
sfilippone
|
ea6c4181f7
|
Changed all defines with prefix PSB_
|
2025-03-14 12:54:18 +01:00 |
|
sfilippone
|
333f0e0fb7
|
Fix cuda sources to use psb_config.h
|
2025-03-09 18:40:45 +01:00 |
|
Salvatore Filippone
|
67876fec73
|
Use $(AR) in makefiles merged from EXT
|
2025-03-02 12:13:56 +01:00 |
|
sfilippone
|
e2b00032b6
|
Fix compile warnings for printf and missing return()
|
2025-02-09 16:21:50 +01:00 |
|
sfilippone
|
2af0d56938
|
Malloc and trasnfers with CUDA should use (size_t) casts
|
2025-01-02 11:49:08 +01:00 |
|
sfilippone
|
ade79bcc7e
|
Fixes for compilation with CUDA
|
2024-10-09 14:27:17 +02:00 |
|
sfilippone
|
abdf7fc05a
|
Fix constructor name for multivector
|
2024-10-09 13:32:29 +02:00 |
|
sfilippone
|
3d9fee2dd7
|
Fix DOT on CUDA vectors.
|
2024-10-08 17:07:10 +02:00 |
|
sfilippone
|
c74be820ea
|
Rework configry for CUDA
|
2024-10-08 11:48:15 +02:00 |
|
sfilippone
|
4461b44eda
|
Change name abgdxyz into upd_xyz
|
2024-07-29 16:59:27 +02:00 |
|
sfilippone
|
9f2b8a2623
|
Cleanup
|
2024-06-24 08:18:07 +02:00 |
|
sfilippone
|
e3a55967a5
|
Modify CUDA code to compile with 12.4/12.5
|
2024-06-23 16:03:10 +02:00 |
|
sfilippone
|
d71d355b68
|
Refactor cusparse includes..
|
2024-05-21 12:59:44 +02:00 |
|
sfilippone
|
2e3f862e42
|
Start refactoring cusparse.h
|
2024-05-21 12:31:02 +02:00 |
|
sfilippone
|
ee66db5efd
|
Refactor interface to cusparse in preparation for CSR Adaptive
|
2024-05-21 11:25:38 +02:00 |
|
sfilippone
|
c8cc2275d0
|
Fix cuda/makefile for make -j
|
2024-05-15 16:39:22 +02:00 |
|
sfilippone
|
d01b8145c6
|
Fix cuda makefile dependencies
|
2024-05-09 17:08:45 +02:00 |
|
sfilippone
|
e18de650f2
|
Take out debug print
|
2024-04-17 13:53:04 +02:00 |
|
sfilippone
|
0760e4d553
|
Fix C function declarations for compilation with LLVM/clang in CUDA
|
2024-04-04 10:53:20 +02:00 |
|
sfilippone
|
3a25d7b04a
|
Fixes for LLVM compilation
|
2024-03-22 17:10:30 +01:00 |
|
sfilippone
|
e0a4d362fa
|
Define flag TRACK_CUDA_MALLOC
|
2024-03-14 12:08:57 +01:00 |
|
Salvatore Filippone
|
b5f1442ac8
|
Merge branch 'nond-rep' into repackage
|
2024-03-05 19:46:14 +01:00 |
|
sfilippone
|
48455190ec
|
Add GPU version of XYZW
|
2024-03-05 13:57:03 +01:00 |
|
sfilippone
|
a11f328e62
|
Added CUDA version of XYZW
|
2024-03-05 12:42:21 +01:00 |
|
sfilippone
|
b5d5f97661
|
Improve cuda%zero()
|
2024-02-20 14:04:23 +01:00 |
|
sfilippone
|
0e269ed641
|
typo in Cabgdxyz
|
2024-02-20 13:57:32 +01:00 |
|
Salvatore Filippone
|
d95077ffd6
|
Fix typo in vectordev_mod
|
2024-02-20 13:46:58 +01:00 |
|
Salvatore Filippone
|
2d3773df98
|
CUDA kernels for ABGDXYZ
|
2024-02-20 13:05:16 +01:00 |
|
Salvatore Filippone
|
2a75d677d0
|
ABGDXYZ in vectordev_mod
|
2024-02-20 13:04:40 +01:00 |
|
sfilippone
|
2391f64df6
|
X_cuda_vect%abgdxyz
|
2024-02-20 12:30:07 +01:00 |
|
sfilippone
|
93c71c4316
|
Fix %ZERO() on cuda
|
2024-02-20 10:25:31 +01:00 |
|
sfilippone
|
0568a83734
|
Fix ifdef and old code
|
2024-02-19 10:53:23 +01:00 |
|
Salvatore Filippone
|
35d68aa4e3
|
Reuse calls to getDeviceProperties done at init time
|
2024-02-18 16:44:37 +01:00 |
|
Salvatore Filippone
|
1ba8dfc7b7
|
Switch FOR and IF in AXPBY
|
2024-02-18 10:31:32 +01:00 |
|
Salvatore Filippone
|
f9677bc892
|
Enabled new CUDA version of ABGDXYZ
|
2024-02-17 18:42:56 +01:00 |
|
Salvatore Filippone
|
4681767ef8
|
New implementation for ABGDXYZ in CUDA
|
2024-02-17 18:20:12 +01:00 |
|
Salvatore Filippone
|
105aa3c570
|
Intermediate impl of ABGDXYZ
|
2024-02-17 17:46:09 +01:00 |
|
Salvatore Filippone
|
864872ecac
|
Intermediate implementation of abgdxyz on cuda
|
2024-02-17 17:28:32 +01:00 |
|
Salvatore Filippone
|
a41b209144
|
Better AXPBY implementation in CUDA.
|
2024-02-17 17:18:59 +01:00 |
|
Salvatore Filippone
|
ebc7c6b3b4
|
Fix call to base%abgdxyz
|
2024-02-12 16:29:48 +01:00 |
|