Benoit Steiner
|
a86c9f037b
|
Fixed compilation error on windows
|
2016-03-24 18:54:31 -07:00 |
|
Benoit Steiner
|
0968e925a0
|
Updated the benchmarking code to use Eigen::half instead of half
|
2016-03-24 18:00:33 -07:00 |
|
Benoit Steiner
|
044efea965
|
Made sure that the cxx11_tensor_cuda test can be compiled even without support for cxx11.
|
2016-03-23 20:02:11 -07:00 |
|
Benoit Steiner
|
2e4e4cb74d
|
Use numext::abs instead of abs to avoid incorrect conversion to integer of the argument
|
2016-03-23 16:57:12 -07:00 |
|
Benoit Steiner
|
41434a8a85
|
Avoid unnecessary conversions
|
2016-03-23 16:52:38 -07:00 |
|
Benoit Steiner
|
92693b50eb
|
Fixed compilation warning
|
2016-03-23 16:40:36 -07:00 |
|
Benoit Steiner
|
9bc9396e88
|
Use portable includes
|
2016-03-23 16:30:06 -07:00 |
|
Benoit Steiner
|
393bc3b16b
|
Added comment
|
2016-03-23 16:22:15 -07:00 |
|
Benoit Steiner
|
81d340984a
|
Removed executable bit from header files
|
2016-03-23 16:15:02 -07:00 |
|
Benoit Steiner
|
bff8cbad06
|
Removed executable bit from header files
|
2016-03-23 16:14:23 -07:00 |
|
Benoit Steiner
|
7a570e50ef
|
Fixed contractions of fp16
|
2016-03-23 16:00:06 -07:00 |
|
Benoit Steiner
|
7168afde5e
|
Made the tensor benchmarks compile on MacOS
|
2016-03-23 14:21:04 -07:00 |
|
Benoit Steiner
|
2062ee2d26
|
Added a test to verify that notifications are working properly
|
2016-03-23 13:39:00 -07:00 |
|
Benoit Steiner
|
fc3660285f
|
Made type conversion explicit
|
2016-03-23 09:56:50 -07:00 |
|
Benoit Steiner
|
0e68882604
|
Added the ability to divide a half float by an index
|
2016-03-23 09:46:42 -07:00 |
|
Benoit Steiner
|
6971146ca9
|
Added more conversion operators for half floats
|
2016-03-23 09:44:52 -07:00 |
|
Christoph Hertzberg
|
9642fd7a93
|
Replace all M_PI by EIGEN_PI and add a check to the testsuite.
|
2016-03-23 15:37:45 +01:00 |
|
Benoit Steiner
|
28e02996df
|
Merged patch 672 from Justin Lebar: Don't use long doubles with cuda
|
2016-03-22 16:53:57 -07:00 |
|
Benoit Steiner
|
3d1e857327
|
Fixed compilation error
|
2016-03-22 15:48:28 -07:00 |
|
Benoit Steiner
|
de7d92c259
|
Pulled latest updates from trunk
|
2016-03-22 15:24:49 -07:00 |
|
Benoit Steiner
|
002cf0d1c9
|
Use a single Barrier instead of a collection of Notifications to reduce the thread synchronization overhead
|
2016-03-22 15:24:23 -07:00 |
|
Benoit Steiner
|
bc2b802751
|
Fixed a couple of typos
|
2016-03-22 14:27:34 -07:00 |
|
Benoit Steiner
|
e7a468c5b7
|
Filter some compilation flags that nvcc warns about.
|
2016-03-22 14:26:50 -07:00 |
|
Benoit Steiner
|
6a31b7be3e
|
Avoid using std::vector whenever possible
|
2016-03-22 14:02:50 -07:00 |
|
Benoit Steiner
|
65a7113a36
|
Use an enum instead of a static const int to prevent possible link error
|
2016-03-22 09:33:54 -07:00 |
|
Benoit Steiner
|
f9ad25e4d8
|
Fixed contractions of 16 bit floats
|
2016-03-22 09:30:23 -07:00 |
|
Benoit Steiner
|
8ef3181f15
|
Worked around a constness related issue
|
2016-03-21 11:24:05 -07:00 |
|
Benoit Steiner
|
7a07d6aa2b
|
Small cleanup
|
2016-03-21 11:12:17 -07:00 |
|
Konstantinos Margaritis
|
a9a6710e15
|
add initial s390x(zEC13) ZVECTOR support
|
2016-03-21 13:46:47 -04:00 |
|
Benoit Steiner
|
e91f255301
|
Marked variables that's only used in debug mode as such
|
2016-03-21 10:02:00 -07:00 |
|
Benoit Steiner
|
db5c14de42
|
Explicitly cast the default value into the proper scalar type.
|
2016-03-21 09:52:58 -07:00 |
|
Christoph Hertzberg
|
b224771f40
|
bug #1178: Simplified modification of the SSE control register for better portability
|
2016-03-20 10:57:08 +01:00 |
|
Benoit Steiner
|
8e03333f06
|
Renamed some class members to make the code more readable.
|
2016-03-18 15:21:04 -07:00 |
|
Benoit Steiner
|
6c08943d9f
|
Fixed a bug in the padding of extracted image patches.
|
2016-03-18 15:19:10 -07:00 |
|
Benoit Steiner
|
134d750eab
|
Completed the implementation of vectorized type casting of half floats.
|
2016-03-18 13:36:28 -07:00 |
|
Benoit Steiner
|
7bd551b3a9
|
Make all the conversions explicit
|
2016-03-18 12:20:08 -07:00 |
|
Benoit Steiner
|
bb0e73c191
|
Gate all the CUDA tests under the EIGEN_TEST_NVCC option
|
2016-03-18 12:17:37 -07:00 |
|
Benoit Steiner
|
2db4a04827
|
Fixed a typo
|
2016-03-18 12:08:01 -07:00 |
|
Benoit Steiner
|
dd514de8a9
|
Added a test to validate the fallback path for half floats
|
2016-03-18 12:02:39 -07:00 |
|
Benoit Steiner
|
9a7ece9caf
|
Worked around constness issue
|
2016-03-18 10:38:29 -07:00 |
|
Benoit Steiner
|
edc679f6c6
|
Fixed compilation warning
|
2016-03-18 07:12:34 -07:00 |
|
Benoit Steiner
|
53d498ef06
|
Fixed compilation warnings in the cuda tests
|
2016-03-18 07:04:54 -07:00 |
|
Benoit Steiner
|
e10e126cd0
|
pulled latest updates from trunk
|
2016-03-17 21:48:38 -07:00 |
|
Benoit Steiner
|
70eb70f5f8
|
Avoid mutable class members when possible
|
2016-03-17 21:47:18 -07:00 |
|
Benoit Steiner
|
7b98de1f15
|
Implemented some of the missing type casting for half floats
|
2016-03-17 21:45:45 -07:00 |
|
Benoit Steiner
|
afb81b7ded
|
Made sure to use the hard abi when compiling with NEON instructions to avoid the "gnu/stubs-soft.h: No such file or directory" error
|
2016-03-17 21:24:24 -07:00 |
|
Benoit Steiner
|
95b8961a9b
|
Allocate the mersenne twister used by the random number generators on the heap instead of on the stack since they tend to keep a lot of state (i.e. about 5k) around.
|
2016-03-17 15:23:51 -07:00 |
|
Benoit Steiner
|
f7329619da
|
Fix bug in tensor contraction. The code assumes that contraction axis indices for the LHS (after possibly swapping to ColMajor!) is increasing. Explicitly sort the contraction axis pairs to make it so.
|
2016-03-17 15:08:02 -07:00 |
|
Christoph Hertzberg
|
46aa9772fc
|
Merged in ebrevdo/eigen (pull request PR-169)
Bugfixes to cuda tests, igamma & igammac implemented, & tests for digamma, igamma, igammac on CPU & GPU.
|
2016-03-16 21:59:08 +01:00 |
|
Eugene Brevdo
|
f1f7181f53
|
Merge default branch.
|
2016-03-16 12:46:19 -07:00 |
|