Commit Graph

415 Commits

Author SHA1 Message Date
Benoit Steiner
b5d2078c4a Optimized outer reduction on GPUs. 2015-12-22 15:06:17 -08:00
Benoit Steiner
1c3e78319d Added missing const 2015-12-21 15:05:01 -08:00
Benoit Steiner
1b82969559 Add alignment requirement for local buffer used by the slicing op. 2015-12-18 14:36:35 -08:00
Benoit Steiner
75a7fa1919 Doubled the speed of full reductions on GPUs. 2015-12-18 14:07:31 -08:00
Benoit Steiner
8dd17cbe80 Fixed a clang compilation warning triggered by the use of arrays of size 0. 2015-12-17 14:00:33 -08:00
Benoit Steiner
4aac55f684 Silenced some compilation warnings triggered by nvcc 2015-12-17 13:39:01 -08:00
Benoit Steiner
40e6250fc3 Made it possible to run tensor chipping operations on CUDA devices 2015-12-17 13:29:08 -08:00
Benoit Steiner
2ca55a3ae4 Fixed some compilation error triggered by the tensor code with msvc 2008 2015-12-16 20:45:58 -08:00
Benoit Steiner
17352e2792 Made the entire TensorFixedSize api callable from a CUDA kernel. 2015-12-14 15:20:31 -08:00
Benoit Steiner
75e19fc7ca Marked the tensor constructors as EIGEN_DEVICE_FUNC: This makes it possible to call them from a CUDA kernel. 2015-12-14 15:12:55 -08:00
Gael Guennebaud
ca39b1546e Merged in ebrevdo/eigen (pull request PR-148)
Add special functions to eigen: lgamma, erf, erfc.
2015-12-11 11:52:09 +01:00
Benoit Steiner
6af52a1227 Fixed a typo in the constructor of tensors of rank 5. 2015-12-10 23:31:12 -08:00
Benoit Steiner
8e00ea9a92 Fixed the coefficient accessors use for the 2d and 3d case when compiling without cxx11 support. 2015-12-10 22:45:10 -08:00
Eugene Brevdo
fa4f933c0f Add special functions to Eigen: lgamma, erf, erfc.
Includes CUDA support and unit tests.
2015-12-07 15:24:49 -08:00
Benoit Steiner
7dfe75f445 Fixed compilation warnings 2015-12-07 08:12:30 -08:00
Benoit Steiner
f4ca8ad917 Use signed integers instead of unsigned ones more consistently in the codebase. 2015-12-04 18:14:16 -08:00
Benoit Steiner
490d26e4c1 Use integers instead of std::size_t to encode the number of dimensions in the Tensor class since most of the code currently already use integers. 2015-12-04 10:15:11 -08:00
Benoit Steiner
d20efc974d Made it possible to use the sigmoid functor within a CUDA kernel. 2015-12-04 09:38:15 -08:00
Benoit Steiner
029052d276 Deleted redundant code 2015-12-03 17:08:47 -08:00
Mark Borgerding
7ddcf97da7 added scalar_sign_op (both real,complex) 2015-11-24 17:15:07 -05:00
Benoit Steiner
44848ac39b Fixed a bug in TensorArgMax.h 2015-11-23 15:58:47 -08:00
Benoit Steiner
547a8608e5 Fixed the implementation of Eigen::internal::count_leading_zeros for MSVC.
Also updated the code to silence bogux warnings generated by nvcc when compilining this function.
2015-11-23 12:17:45 -08:00
Benoit Steiner
562078780a Don't create more cuda blocks than necessary 2015-11-23 11:00:10 -08:00
Benoit Steiner
df31ca3b9e Made it possible to refer t oa GPUDevice from code compile with a regular C++ compiler 2015-11-23 10:03:53 -08:00
Benoit Steiner
1e04059012 Deleted unused variable. 2015-11-23 08:36:54 -08:00
Benoit Steiner
9fa65d3838 Split TensorDeviceType.h in 3 files to make it more manageable 2015-11-20 17:42:50 -08:00
Benoit Steiner
a367804856 Added option to force the usage of the Eigen array class instead of the std::array class. 2015-11-20 12:41:40 -08:00
Benoit Steiner
383d1cc2ed Added proper support for fast 64bit integer division on CUDA 2015-11-20 11:09:46 -08:00
Benoit Steiner
f37a5f1c53 Fixed compilation error triggered by nvcc 2015-11-19 14:34:26 -08:00
Benoit Steiner
f8df393165 Added support for 128bit integers on CUDA devices. 2015-11-19 13:57:27 -08:00
Benoit Steiner
1dd444ea71 Avoid using the version of TensorIntDiv optimized for 32-bit integers when the divisor can be equal to one since it isn't supported. 2015-11-18 11:37:58 -08:00
Benoit Steiner
f1fbd74db9 Added sanity check 2015-11-13 09:07:27 -08:00
Benoit Steiner
7815b84be4 Fixed a compilation warning 2015-11-12 20:16:59 -08:00
Benoit Steiner
10a91930cc Fixed a compilation warning triggered by nvcc 2015-11-12 20:10:52 -08:00
Benoit Steiner
ed4b37de02 Fixed a few compilation warnings 2015-11-12 20:08:01 -08:00
Benoit Steiner
b69248fa2a Added a couple of missing EIGEN_DEVICE_FUNC 2015-11-12 20:01:50 -08:00
Benoit Steiner
0aaa5941df Silenced some compilation warnings triggered by nvcc 2015-11-12 19:11:43 -08:00
Benoit Steiner
2c73633b28 Fixed a few more typos 2015-11-12 18:39:19 -08:00
Benoit Steiner
be08e82953 Fixed typos 2015-11-12 18:37:40 -08:00
Benoit Steiner
150c12e138 Completed the IndexList rewrite 2015-11-12 18:11:56 -08:00
Benoit Steiner
8037826367 Simplified more of the IndexList code. 2015-11-12 17:19:45 -08:00
Benoit Steiner
e9ecfad796 Started to make the IndexList code compile by more compilers 2015-11-12 16:41:14 -08:00
Benoit Steiner
7a1316fcc5 Fixed compilation error with xcode. 2015-11-12 11:05:54 -08:00
Benoit Steiner
737d237722 Made it possible to run some of the CXXMeta functions on a CUDA device. 2015-11-12 09:02:59 -08:00
Benoit Steiner
1e072424e8 Moved the array code into it's own file. 2015-11-12 08:57:04 -08:00
Benoit Steiner
aa5f1ca714 gen_numeric_list takes a size_t, not a int 2015-11-12 08:30:10 -08:00
Benoit Steiner
9fa10fe52d Don't use std::array when compiling with nvcc since nvidia doesn't support the use of STL containers on GPU. 2015-11-11 15:38:30 -08:00
Benoit Steiner
c587293e48 Fixed a compilation warning 2015-11-11 15:35:12 -08:00
Benoit Steiner
7f1c29fb0c Make it possible for a vectorized tensor expression to be executed in a CUDA kernel. 2015-11-11 15:22:50 -08:00
Benoit Steiner
99f4778506 Disable SFINAE when compiling with nvcc 2015-11-11 15:04:58 -08:00
Benoit Steiner
5cb18e5b5e Fixed CUDA compilation errors 2015-11-11 14:36:33 -08:00
Benoit Steiner
228edfe616 Use Eigen::NumTraits instead of std::numeric_limits 2015-11-11 09:26:23 -08:00
Benoit Steiner
20e2ab1121 Fixed another compilation warning 2015-12-07 16:17:57 -08:00
Benoit Steiner
d573efe303 Code cleanup 2015-11-06 14:54:28 -08:00
Benoit Steiner
9fa283339f Silenced a compilation warning 2015-11-06 11:44:22 -08:00
Benoit Steiner
53432a17b2 Added static assertions to avoid misuses of padding, broadcasting and concatenation ops. 2015-11-06 10:26:19 -08:00
Benoit Steiner
6857a35a11 Fixed typos 2015-11-06 09:42:05 -08:00
Benoit Steiner
33cbdc2d15 Added more missing EIGEN_DEVICE_FUNC 2015-11-06 09:29:59 -08:00
Benoit Steiner
ed1962b464 Reimplement the tensor comparison operators by using the scalar_cmp_op functors. This makes them more cuda friendly. 2015-11-06 09:18:43 -08:00
Benoit Steiner
29038b982d Added support for modulo operation 2015-11-05 19:39:48 -08:00
Benoit Steiner
c75a19f815 Misc fixes to full reductions 2015-11-05 14:21:20 -08:00
Benoit Steiner
ec5a81b45a Fixed a bug in the extraction of sizes of fixed sized tensors of rank 0 2015-11-05 13:39:48 -08:00
Benoit Steiner
beedd9630d Updated the reduction code so that full reductions now return a tensor of rank 0. 2015-11-04 13:57:36 -08:00
Benoit Steiner
6a02c2a85d Fixed a compilation warning 2015-10-29 20:21:29 -07:00
Benoit Steiner
ca12d4c3b3 Pulled latest updates from trunk 2015-10-29 17:57:48 -07:00
Benoit Steiner
ce19e38c1f Added support for tensor maps of rank 0. 2015-10-29 17:49:04 -07:00
Benoit Steiner
3785c69294 Added support for fixed sized tensors of rank 0 2015-10-29 17:31:03 -07:00
Benoit Steiner
0d7a23d34e Extended the reduction code so that reducing an empty set returns the neural element for the operation 2015-10-29 17:29:49 -07:00
Benoit Steiner
1b0685d09a Added support for rank-0 tensors 2015-10-29 17:27:38 -07:00
Benoit Steiner
c444a0a8c3 Consistently use the same index type in the fft codebase. 2015-10-29 16:39:47 -07:00
Benoit Steiner
09ea3a7acd Silenced a few more compilation warnings 2015-10-29 16:22:52 -07:00
Benoit Steiner
0974a57910 Silenced compiler warning 2015-10-29 15:00:06 -07:00
Benoit Steiner
1c8312c811 Started to add support for tensors of rank 0 2015-10-26 14:29:26 -07:00
Benoit Steiner
1f4c98abb1 Fixed compilation warning 2015-10-26 12:42:55 -07:00
Benoit Steiner
9dc236bc83 Fixed compilation warning 2015-10-26 12:41:48 -07:00
Benoit Steiner
9f721384e0 Added support for empty dimensions 2015-10-26 11:21:27 -07:00
Benoit Steiner
a3e144727c Fixed compilation warning 2015-10-26 10:48:11 -07:00
Benoit Steiner
56983f6d43 Fixed compilation warning 2015-10-23 12:03:42 -07:00
Benoit Steiner
57857775b4 Added support for arrays of size 0 2015-10-23 10:20:51 -07:00
Benoit Steiner
c40c2ceb27 Reordered the code of fft constructor to prevent compilation warnings 2015-10-23 09:38:19 -07:00
Benoit Steiner
a586fdaa91 Reworked the tensor contraction mapper code to make it compile on Android 2015-10-23 09:33:41 -07:00
Benoit Steiner
9ea39ce13c Refined the #ifdef __CUDACC__ guard to ensure that when trying to compile gpu code with a non cuda compiler results in a linking error instead of bogus code. 2015-10-23 09:15:34 -07:00
Benoit Steiner
ac99b49249 Added missing glue logic 2015-10-22 16:54:21 -07:00
Benoit Steiner
2dd9446613 Added mapping between a specific device and the corresponding packet type 2015-10-22 16:53:36 -07:00
Benoit Steiner
a147c62998 Added support for fourier transforms (code courtesy of thucjw@gmail.com) 2015-10-22 16:51:30 -07:00
Benoit Steiner
4cf7da63de Added a constructor to simplify the construction of tensormap from tensor 2015-10-22 11:48:02 -07:00
Benoit Steiner
b178cc3479 Added some syntactic sugar to make it simpler to compare a tensor to a scalar. 2015-10-21 11:28:28 -07:00
Benoit Steiner
0af63493fd Disable SFINAE for versions of gcc older than 4.8 2015-10-20 11:53:30 -07:00
Benoit Steiner
73b8e719ae Removed bogus assertion 2015-10-20 11:42:34 -07:00
Benoit Steiner
eaf4b98180 Added support for boolean reductions (ie 'and' & 'or' reductions) 2015-10-20 11:41:22 -07:00
Benoit Steiner
f5c1587e4e Fixed a bug in the tensor conversion op 2015-10-20 11:37:44 -07:00
Benoit Steiner
de1e9f29f4 Updated the custom indexing code: we can now use any container that provides the [] operator to index a tensor. Added unit tests to validate the use of std::map and a few more types as valid custom index containers 2015-10-15 14:58:49 -07:00
Benoit Steiner
6585efc553 Tightened the definition of isOfNormalIndex to take into account integer types in addition to arrays of indices
Only compile the custom index code  when EIGEN_HAS_SFINAE is defined. For the time beeing, EIGEN_HAS_SFINAE is a synonym for EIGEN_HAS_VARIADIC_TEMPLATES, but this might evolve in the future.
Moved some code around.
2015-10-14 09:31:37 -07:00
Gabriel Nützi
fc7478c04d name changes 2
user: Gabriel Nützi <gnuetzi@gmx.ch>
branch 'default'
changed unsupported/Eigen/CXX11/src/Tensor/Tensor.h
changed unsupported/Eigen/CXX11/src/Tensor/TensorMeta.h
2015-10-09 19:10:08 +02:00
Gabriel Nützi
7b34834f64 name changes
user: Gabriel Nützi <gnuetzi@gmx.ch>
branch 'default'
changed unsupported/Eigen/CXX11/src/Tensor/Tensor.h
2015-10-09 19:08:14 +02:00
Gabriel Nützi
6edae2d30d added CustomIndex capability only to Tensor and not yet to TensorBase.
using Sfinae and is_base_of to select correct template which converts to array<Index,NumIndices>


 user: Gabriel Nützi <gnuetzi@gmx.ch>
 branch 'default'
 added unsupported/Eigen/CXX11/src/Tensor/TensorMetaMacros.h
 added unsupported/test/cxx11_tensor_customIndex.cpp
 changed unsupported/Eigen/CXX11/Tensor
 changed unsupported/Eigen/CXX11/src/Tensor/Tensor.h
 changed unsupported/Eigen/CXX11/src/Tensor/TensorMeta.h
 changed unsupported/test/CMakeLists.txt
2015-10-09 18:52:48 +02:00
Benoit Steiner
31afdcb4c2 Fix return type for TensorEvaluator<TensorSlicingOp>::data 2015-09-17 09:40:21 -07:00
Benoit Steiner
f41831e445 Added support for argmax/argmin 2015-08-31 08:18:53 -07:00
Benoit Steiner
2ab603316a Use numext::mini/numext::maxi instead of std::min/std::max in the tensor code 2015-08-28 08:14:15 -07:00
Christoph Hertzberg
1bdd06a199 Fix some trivial warnings 2015-08-19 21:38:18 +02:00