Benoit Steiner
|
46fc23f91c
|
Print an error message to stderr when the initialization of the CUDA runtime fails. This helps debugging setup issues.
|
2016-02-19 13:44:22 -08:00 |
|
Benoit Steiner
|
670db7988d
|
Updated the contraction code to make it compatible with half floats.
|
2016-02-19 13:03:26 -08:00 |
|
Benoit Steiner
|
180156ba1a
|
Added support for tensor reductions on half floats
|
2016-02-19 10:05:59 -08:00 |
|
Benoit Steiner
|
f268db1c4b
|
Added the ability to query the minor version of a cuda device
|
2016-02-19 16:31:04 +00:00 |
|
Benoit Steiner
|
a08d2ff0c9
|
Started to work on contractions and reductions using half floats
|
2016-02-19 15:59:59 +00:00 |
|
Benoit Steiner
|
f3352e0fb0
|
Don't make the array constructors explicit
|
2016-02-19 15:58:57 +00:00 |
|
Benoit Steiner
|
cd042dbbfd
|
Fixed a bug in the tensor type converter
|
2016-02-19 15:03:26 +00:00 |
|
Benoit Steiner
|
ac5d706a94
|
Added support for simple coefficient wise tensor expression using half floats on CUDA devices
|
2016-02-19 08:19:12 +00:00 |
|
Benoit Steiner
|
0606a0a39b
|
FP16 on CUDA are only available starting with cuda 7.5. Disable them when using an older version of CUDA
|
2016-02-18 23:15:23 -08:00 |
|
Benoit Steiner
|
f36c0c2c65
|
Added regression test for float16
|
2016-02-19 06:23:28 +00:00 |
|
Benoit Steiner
|
7151bd8768
|
Reverted unintended changes introduced by a bad merge
|
2016-02-19 06:20:50 +00:00 |
|
Benoit Steiner
|
17b9fbed34
|
Added preliminary support for half floats on CUDA GPU. For now we can simply convert floats into half floats and vice versa
|
2016-02-19 06:16:07 +00:00 |
|
Benoit Steiner
|
9e3f3a2d27
|
Deleted outdated comment
|
2016-02-11 17:27:35 -08:00 |
|
Benoit Steiner
|
de345eff2e
|
Added a method to conjugate the content of a tensor or the result of a tensor expression.
|
2016-02-11 16:34:07 -08:00 |
|
Benoit Steiner
|
9a21b38ccc
|
Worked around a few clang compilation warnings
|
2016-02-10 08:02:04 -08:00 |
|
Benoit Steiner
|
72ab7879f7
|
Fixed clang comilation warnings
|
2016-02-10 06:48:28 -08:00 |
|
Benoit Steiner
|
e88535634d
|
Fixed some clang compilation warnings
|
2016-02-09 23:32:41 -08:00 |
|
Benoit Steiner
|
6323851ea9
|
Fixed compilation warning
|
2016-02-09 20:43:41 -08:00 |
|
Benoit Steiner
|
d69946183d
|
Updated the TensorIntDivisor code to work properly on LLP64 systems
|
2016-02-08 21:03:59 -08:00 |
|
Benoit Steiner
|
4d4211c04e
|
Avoid unecessary type conversions
|
2016-02-05 18:19:41 -08:00 |
|
Benoit Steiner
|
d2cba52015
|
Only enable the cxx11_tensor_uint128 test on 64 bit machines since 32 bit systems don't support the __uin128_t type
|
2016-02-05 18:14:23 -08:00 |
|
Benoit Steiner
|
fb00a4af2b
|
Made the tensor fft test compile on tegra x1
|
2016-02-06 01:42:14 +00:00 |
|
Benoit Steiner
|
f535378995
|
Added support for vectorized type casting of int to char.
|
2016-02-03 18:58:29 -08:00 |
|
Benoit Steiner
|
4ab63a3f6f
|
Fixed the initialization of the dummy member of the array class to make it compatible with pairs of element.
|
2016-02-03 17:23:07 -08:00 |
|
Benoit Steiner
|
1cbb79cdfd
|
Made sure the dummy element of size 0 array is always intialized to silence some compiler warnings
|
2016-02-03 15:58:26 -08:00 |
|
Benoit Steiner
|
5d82e47ef6
|
Properly disable nvcc warning messages in user code.
|
2016-02-03 14:10:06 -08:00 |
|
Benoit Steiner
|
af8436b196
|
Silenced the "calling a __host__ function from a __host__ __device__ function is not allowed" messages
|
2016-02-03 13:48:36 -08:00 |
|
Benoit Steiner
|
dc413dbe8a
|
Merged in ville-k/eigen/explicit_long_constructors (pull request PR-158)
Add constructor for long types.
|
2016-02-02 20:58:06 -08:00 |
|
Ville Kallioniemi
|
783018d8f6
|
Use EIGEN_STATIC_ASSERT for backward compatibility.
|
2016-02-02 16:45:12 -07:00 |
|
Benoit Steiner
|
99cde88341
|
Don't try to use direct offsets when computing a tensor product, since the required stride isn't available.
|
2016-02-02 11:06:53 -08:00 |
|
Ville Kallioniemi
|
aedea349aa
|
Replace separate low word constructors with a single templated constructor.
|
2016-02-01 20:25:02 -07:00 |
|
Ville Kallioniemi
|
f0fdefa96f
|
Rebase to latest.
|
2016-02-01 19:32:31 -07:00 |
|
Benoit Steiner
|
64ce78c2ec
|
Cleaned up a tensor contraction test
|
2016-02-01 13:57:41 -08:00 |
|
Benoit Steiner
|
0ce5d32be5
|
Sharded the cxx11_tensor_contract_cuda test
|
2016-02-01 13:33:23 -08:00 |
|
Benoit Steiner
|
922b5f527b
|
Silenced a few compilation warnings
|
2016-02-01 13:30:49 -08:00 |
|
Benoit Steiner
|
6b5dff875e
|
Made it possible to limit the number of blocks that will be used to evaluate a tensor expression on a CUDA device. This makesit possible to set aside streaming multiprocessors for other computations.
|
2016-02-01 12:46:32 -08:00 |
|
Benoit Steiner
|
264f8141f8
|
Shared the tensor reduction test
|
2016-02-01 07:44:31 -08:00 |
|
Benoit Steiner
|
11bb71c8fc
|
Sharded the tensor device test
|
2016-02-01 07:34:59 -08:00 |
|
Benoit Steiner
|
e80ed948e1
|
Fixed a number of compilation warnings generated by the cuda tests
|
2016-01-31 20:09:41 -08:00 |
|
Benoit Steiner
|
6720b38fbf
|
Fixed a few compilation warnings
|
2016-01-31 16:48:50 -08:00 |
|
Benoit Steiner
|
4a2ddfb81d
|
Sharded the CUDA argmax tensor test
|
2016-01-31 10:44:15 -08:00 |
|
Benoit Steiner
|
483082ef6e
|
Fixed a few memory leaks in the cuda tests
|
2016-01-30 11:59:22 -08:00 |
|
Benoit Steiner
|
bd21aba181
|
Sharded the cxx11_tensor_cuda test and fixed a memory leak
|
2016-01-30 11:47:09 -08:00 |
|
Benoit Steiner
|
9de155d153
|
Added a test to cover threaded tensor shuffling
|
2016-01-30 10:56:47 -08:00 |
|
Benoit Steiner
|
32088c06a1
|
Made the comparison between single and multithreaded contraction results more resistant to numerical noise to prevent spurious test failures.
|
2016-01-30 10:51:14 -08:00 |
|
Benoit Steiner
|
2053478c56
|
Made sure to use a tensor of rank 0 to store the result of a full reduction in the tensor thread pool test
|
2016-01-30 10:46:36 -08:00 |
|
Benoit Steiner
|
d0db95f730
|
Sharded the tensor thread pool test
|
2016-01-30 10:43:57 -08:00 |
|
Benoit Steiner
|
ba27c8a7de
|
Made the CUDA contract test more robust to numerical noise.
|
2016-01-30 10:28:43 -08:00 |
|
Benoit Steiner
|
963f2d2a8f
|
Marked several methods EIGEN_DEVICE_FUNC
|
2016-01-28 23:37:48 -08:00 |
|
Benoit Steiner
|
c5d25bf1d0
|
Fixed a couple of compilation warnings.
|
2016-01-28 23:15:45 -08:00 |
|