Philippe Tillet
|
df9f6142ef
|
Models: added basic database structure
|
2015-08-05 17:01:42 -07:00 |
|
Philippe Tillet
|
ef14e3aa17
|
Code quality: more MSVD warnings removal
|
2015-08-05 12:47:20 -07:00 |
|
Philippe Tillet
|
54c4a31af0
|
Code quality: more warning fixes
|
2015-08-05 12:07:51 -07:00 |
|
Philippe Tillet
|
35b2550665
|
Code quality: safer getenv on windows
|
2015-08-05 11:16:14 -07:00 |
|
Philippe Tillet
|
1a42494411
|
Code quality: renamed "backend/" folder to "kernels". More explicit and no longer conflicts with "driver/"
|
2015-08-04 20:56:05 -07:00 |
|
Philippe Tillet
|
03178fc5c8
|
Tuning: added ger default sizes
|
2015-08-04 16:03:14 -07:00 |
|
Philippe Tillet
|
dd61041df4
|
Driver: moved ProgramCache to a separate file
|
2015-08-04 11:11:38 -07:00 |
|
Philippe Tillet
|
9ef5331a1b
|
Models: more robust programs caching
|
2015-08-04 10:53:39 -07:00 |
|
Philippe Tillet
|
df2d5e7d00
|
Models: cleaning of the global caching mechanism
|
2015-08-04 10:06:52 -07:00 |
|
Philippe Tillet
|
dd5f592fd8
|
Code quality: destructors of static global objects will no longer call external dependencies. Manual cleaning possible through backend::release()
This should solve errors when libOpenCL's ICD was unloaded prior to libisaac.
|
2015-07-31 15:47:41 -07:00 |
|
Philippe Tillet
|
afc4ecee98
|
Driver: Back to global programs caching
|
2015-07-31 00:43:17 -07:00 |
|
Philippe Tillet
|
81b9f01336
|
Driver: Contexts are now unique and non-copyable
|
2015-07-31 00:41:03 -07:00 |
|
Philippe Tillet
|
21a2566904
|
Driver: moved programs allocation logic to a static variable
|
2015-07-30 14:35:41 -07:00 |
|
Philippe Tillet
|
9c15debf8b
|
Code quality: removed tools::shared_ptr<>
|
2015-07-28 15:26:10 -07:00 |
|
Philippe Tillet
|
89ee015f7f
|
General: Bugfixes here and there
|
2015-07-27 11:37:19 -07:00 |
|
Philippe Tillet
|
cd155cb9e3
|
Code quality: Improved compliance to MSVC
|
2015-07-21 17:18:50 -04:00 |
|
Philippe Tillet
|
1e3c853b58
|
GEMM: Incorporated K bounds checking inside kernel
|
2015-07-16 14:25:32 -04:00 |
|
Philippe Tillet
|
cfa6ea812d
|
Cleaning: Largely renamed templates to BLAS-like names
|
2015-07-11 11:21:15 -04:00 |
|
Philippe Tillet
|
e25dcf97ea
|
Bugfix in SIMD handling for other layouts
|
2015-07-10 16:05:28 -04:00 |
|
Philippe Tillet
|
a676b15448
|
Fixup
|
2015-07-09 11:40:26 -04:00 |
|
Philippe Tillet
|
b18442c220
|
Fixup
|
2015-07-07 23:39:17 -07:00 |
|
Philippe Tillet
|
4c123c4b38
|
Backend: GEMM - Improved bounds checking
|
2015-07-02 16:44:02 -04:00 |
|
Philippe Tillet
|
cf2dba43ef
|
Backend: A lot of bugfixes in dot() for handling shapes better
|
2015-06-30 17:55:57 -04:00 |
|
Philippe
|
743a559f76
|
Backend: Bugfix in GEMM bound-checking
|
2015-06-27 13:14:46 -04:00 |
|
Philippe Tillet
|
b0cd25ac4b
|
Added C BLAS1 test
|
2015-06-25 23:12:26 -07:00 |
|
Philippe Tillet
|
80bcbd095f
|
C++: Some renaming; added possibility to pass buffers when constructing arrays
|
2015-06-23 09:38:34 -07:00 |
|
Philippe Tillet
|
cf5028d55b
|
Squashed feature branch:
* Added CUDA support
* Performance improvements
* API improvements
* Added "depth" parameter to GEMM
* Android cross-compilation
|
2015-04-29 15:52:21 -04:00 |
|
Philippe Tillet
|
e453031094
|
More efficient access pattern in the GEMV kernel
|
2015-02-11 02:06:16 -05:00 |
|
Philippe Tillet
|
85b7eb8b5e
|
Added another parameter to GEMV
|
2015-02-10 16:33:38 -05:00 |
|
Philippe Tillet
|
37fc98c532
|
Fixed bug on marix-vector products with vectorization
|
2015-02-10 03:09:41 -05:00 |
|
Philippe Tillet
|
a89f6d88be
|
Fix bug in operation-specific tuning
|
2015-02-09 01:58:32 -05:00 |
|
Philippe Tillet
|
a6d7671831
|
removing C++11 interface
|
2015-02-08 23:19:38 -05:00 |
|
Philippe Tillet
|
85fb438806
|
More convenient use of specific runtime tuning
|
2015-02-08 14:23:38 -05:00 |
|
Philippe Tillet
|
e214927b16
|
Better control flow through options
|
2015-02-05 04:43:50 -05:00 |
|
Philippe Tillet
|
bbf2f0188e
|
Ported to C++11
|
2015-02-05 04:43:40 -05:00 |
|
Philippe Tillet
|
2afc574724
|
Implemented simple operation cache
|
2015-02-01 23:56:05 -05:00 |
|
Philippe Tillet
|
535706f35a
|
Some renaming; lower overhead in benchmark
|
2015-02-01 22:28:49 -05:00 |
|
Philippe Tillet
|
3f1fa822f8
|
save
|
2015-02-01 15:58:05 -05:00 |
|
Philippe Tillet
|
b0bf235cc2
|
Reverted strange change on model.cpp
|
2015-01-31 22:10:09 -05:00 |
|
Philippe Tillet
|
d29f1252ad
|
Clearer array_expression with hopefully lower overhead.
Also removed pyc's
|
2015-01-31 22:01:48 -05:00 |
|
Philippe Tillet
|
c7665021d1
|
reducing overhead; reverted custom CL/ header because CL/cl.hpp was buggy
|
2015-01-28 23:04:19 -05:00 |
|
Philippe Tillet
|
0dcf4d3617
|
Better exception handling, lowered CMake requirement ; blas-bench now benchmarks square matrices
|
2015-01-28 17:08:39 -05:00 |
|
Philippe Tillet
|
c37d8a2a81
|
Now using system CL include
|
2015-01-27 16:19:50 -05:00 |
|
Philippe Tillet
|
a96c897cb3
|
Various fixes
|
2015-01-27 02:41:27 -05:00 |
|
Philippe Tillet
|
6d7f103ab1
|
Added GEMM benchmark
|
2015-01-25 18:19:19 -05:00 |
|
Philippe Tillet
|
4a9e16fefd
|
various bugfixes
|
2015-01-25 01:08:18 -05:00 |
|
Philippe Tillet
|
4f73fb384f
|
More flexibility in scalars
|
2015-01-19 21:29:47 -05:00 |
|
Philippe Tillet
|
8694bacaab
|
Multiple devices for tests
|
2015-01-19 14:40:13 -05:00 |
|
Philippe Tillet
|
0068560bc6
|
Some cleaning + outer product
|
2015-01-17 10:49:36 -05:00 |
|
Philippe Tillet
|
faa3974f3c
|
Fixed some warnings
|
2015-01-16 07:38:26 -05:00 |
|