mirror/eigen
2
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-01-06 14:14:46 +08:00
Code Issues Packages Projects Releases Wiki Activity
9,232 Commits 11 Branches 89 Tags 168 MiB
c06861d15e
Commit Graph

908 Commits

Author SHA1 Message Date
Mehdi Goli
622805a0c5 Modifying TensorDeviceSycl.h to always create buffer of type uint8_t and convert them to the actual type at the execution on the device; adding the queue interface class to separate the lifespan of sycl queue and buffers,created for that queue, from Eigen::SyclDevice; modifying sycl tests to support the evaluation of the results for both row major and column major data layout on all different devices that are supported by Sycl{CPU; GPU; and Host}. 2016-11-18 16:20:42 +00:00
Benoit Steiner
7c30078b9f Merged eigen/eigen into default 2016-11-17 22:53:37 -08:00
Benoit Steiner
553f50b246 Added a way to detect errors generated by the opencl device from the host 2016-11-17 21:51:48 -08:00
Benoit Steiner
72a45d32e9 Cleanup 2016-11-17 21:29:15 -08:00
Benoit Steiner
4349fc640e Created a test to check that the sycl runtime can successfully report errors (like ivision by 0). 
Small cleanup
 2016-11-17 20:27:54 -08:00
Benoit Steiner
a6a3fd0703 Made TensorDeviceCuda.h compile on windows 2016-11-17 16:15:27 -08:00
Luke Iwanski
c5130dedbe Specialised basic math functions for SYCL device. 2016-11-17 11:47:13 +00:00
Benoit Steiner
b5c75351e3 Merged eigen/eigen into default 2016-11-14 15:54:44 -08:00
Rasmus Munk Larsen
32df1b1046 Reduce dispatch overhead in parallelFor by only calling thread_pool.Schedule() for one of the two recursive calls in handleRange. This avoids going through the scedule path to push both recursive calls onto another thread-queue in the binary tree, but instead executes one of them on the main thread. At the leaf level this will still activate a full complement of threads, but will save up to 50% of the overhead in Schedule (random number generation, insertion in queue which includes signaling via atomics). 2016-11-14 14:18:16 -08:00
Mehdi Goli
05e8c2a1d9 Adding extra test for non-fixed size to broadcast; Replacing stcl with sycl. 2016-11-14 18:13:53 +00:00
Mehdi Goli
f8ca893976 Adding TensorFixsize; adding sycl device memcpy; adding insial stage of slicing. 2016-11-14 17:51:57 +00:00
Mehdi Goli
a5c3f15682 Adding comment to TensorDeviceSycl.h and cleaning the code. 2016-11-11 19:06:34 +00:00
Mehdi Goli
3be3963021 Adding EIGEN_STRONG_INLINE back; using size() instead of dimensions.TotalSize() on Tensor. 2016-11-10 19:16:31 +00:00
Mehdi Goli
12387abad5 adding the missing in eigen_assert! 2016-11-10 18:58:08 +00:00
Mehdi Goli
2e704d4257 Adding Memset; optimising MecopyDeviceToHost by removing double copying; 2016-11-10 18:45:12 +00:00
Benoit Steiner
dcc14bee64 Fixed the formatting of the code 2016-11-08 14:24:46 -08:00
Luke Iwanski
912cb3d660 #if EIGEN_EXCEPTION -> #ifdef EIGEN_EXCEPTIONS. 2016-11-08 22:01:14 +00:00
Luke Iwanski
1b345b0895 Fix for SYCL queue initialisation. 2016-11-08 21:56:31 +00:00
Luke Iwanski
1b95717358 Use try/catch only when exceptions are enabled. 2016-11-08 21:08:53 +00:00
Mehdi Goli
d57430dd73 Converting all sycl buffers to uninitialised device only buffers; adding memcpyHostToDevice and memcpyDeviceToHost on syclDevice; modifying all examples to obey the new rules; moving sycl queue creating to the device based on Benoit suggestion; removing the sycl specefic condition for returning m_result in TensorReduction.h according to Benoit suggestion. 2016-11-08 17:08:02 +00:00
Benoit Steiner
dad177be01 Added missing includes 2016-11-05 10:04:42 -07:00
Mehdi Goli
0ebe3808ca Removed the sycl include from Eigen/Core and moved it to Unsupported/Eigen/CXX11/Tensor; added TensorReduction for sycl (full reduction and partial reduction); added TensorReduction test case for sycl (full reduction and partial reduction); fixed the tile size on TensorSyclRun.h based on the device max work group size; 2016-11-04 18:18:19 +00:00
Benoit Steiner
0585b2965d Disable vectorization on device only when compiling for sycl 2016-11-02 11:44:27 -07:00
Mehdi Goli
51af6ae971 Fixed the ambiguity in callig make_tuple for sycl backend. 2016-10-31 16:35:51 +00:00
Benoit Steiner
0a9ad6fc72 Worked around Visual Studio compilation errors 2016-10-28 07:54:27 -07:00
Benoit Steiner
b0c5bfdf78 Added missing template parameters 2016-10-28 03:43:41 +00:00
Gael Guennebaud
530f20c21a Workaround MSVC issue. 2016-10-27 21:51:37 +02:00
Benoit Steiner
0a4c4d40b4 Removed a template parameter for fixed sized tensors 2016-10-26 18:47:37 -07:00
Benoit Steiner
5f2dd503ff Replaced tabs with spaces 2016-10-25 20:40:58 -07:00
Benoit Steiner
1644bafe29 Code cleanup 2016-10-25 20:36:14 -07:00
Benoit Steiner
cf20b30d65 Merge latest updates from trunk 2016-10-20 09:42:05 -07:00
Luke Iwanski
03b63e182c Added SYCL include in Tensor. 2016-10-20 15:32:44 +01:00
Benoit Steiner
d3943cd50c Fixed a few typos in the ternary tensor expressions types 2016-10-19 12:56:12 -07:00
Mehdi Goli
e36cb91c99 Fixing the code indentation in the TensorReduction.h file. 2016-10-14 18:03:00 +01:00
Luke Iwanski
e742da8b28 Merged ComputeCpp into default. 2016-10-14 13:36:51 +01:00
Mehdi Goli
524fa4c46f Reducing the code by generalising sycl backend functions/structs. 2016-10-14 12:09:55 +01:00
Benoit Steiner
7e4a6754b2 Merged eigen/eigen into default 2016-10-12 22:42:33 -07:00
Benoit Steiner
7f0599b6eb Manually define int16_t and uint16_t when compiling with Visual Studio 2016-10-08 22:56:32 -07:00
Benoit Steiner
5c68051cd7 Merge the content of the ComputeCpp branch into the default branch 2016-10-07 11:04:16 -07:00
RJ Ryan
e2e9cdd169 Fully support complex types in SumReducer and MeanReducer when building for CUDA by using scalar_sum_op and scalar_product_op instead of operator+ and operator*. 2016-10-06 10:49:48 -07:00
Benoit Steiner
ae1385c7e4 Pull the latest updates from trunk 2016-10-05 14:54:36 -07:00
Benoit Steiner
c84084c0c0 Fixed compilation warning 2016-10-05 14:15:41 -07:00
Benoit Steiner
8b69d5d730 ::rand() returns a signed integer on win32 2016-10-05 08:55:02 -07:00
Benoit Steiner
ed7a220b04 Fixed a typo that impacts windows builds 2016-10-05 08:51:31 -07:00
Benoit Steiner
ceee1c008b Silenced compilation warning 2016-10-04 18:47:53 -07:00
Benoit Steiner
6af5ac7e27 Cleanup the cuda executor code. 2016-10-04 08:52:13 -07:00
Benoit Steiner
2f6d1607c8 Cleaned up the random number generation code. 2016-10-04 08:38:23 -07:00
Benoit Steiner
2bda1b0d93 Updated the tensor sum and mean reducer to enable them to process complex numbers on cuda gpus. 2016-09-28 17:08:41 -07:00
Mehdi Goli
dd602e62c8 Converting alias template to nested struct in order to be compatible with CXX-03 2016-09-27 16:21:19 +01:00
Benoit Steiner
6565f8d60f Made the initialization of a CUDA device thread safe. 2016-09-26 11:00:32 -07:00
Benoit Steiner
f6ac51a054 Made TensorEvalTo compatible with c++0x again. 2016-09-23 16:45:17 -07:00
Benoit Steiner
00d4e65f00 Deleted unused TensorMap data member 2016-09-23 16:44:45 -07:00
Benoit Steiner
1301d744f8 Made the gaussian generator usable on GPU 2016-09-22 19:04:44 -07:00
Benoit Steiner
c3ca9b1e76 Deleted some unecessary and confusing EIGEN_DEVICE_FUNC 2016-09-19 11:33:39 -07:00
Luke Iwanski
b91e021172 Merged with default. 2016-09-19 14:03:54 +01:00
Luke Iwanski
cb81975714 Partial OpenCL support via SYCL compatible with ComputeCpp CE. 2016-09-19 12:44:13 +01:00
Gael Guennebaud
18f6e47815 Fix order of "static inline". 2016-09-16 11:32:54 +02:00
Benoit Steiner
488ad7dd1b Added missing EIGEN_DEVICE_FUNC qualifiers 2016-09-14 13:35:00 -07:00
Benoit Steiner
028e299577 Fixed a bug impacting some outer reductions on GPU 2016-09-12 18:36:52 -07:00
Benoit Steiner
8321dcce76 Merged latest updates from trunk 2016-09-12 10:33:05 -07:00
Benoit Steiner
eb6ba00cc8 Properly size the list of waiters 2016-09-12 10:31:55 -07:00
Benoit Steiner
a618094b62 Added a resize method to MaxSizeVector 2016-09-12 10:30:53 -07:00
Gael Guennebaud
471eac5399 bug #1195: move NumTraits::Div<>::Cost to internal::scalar_div_cost (with some specializations in arch/SSE and arch/AVX) 2016-09-08 08:36:27 +02:00
Benoit Steiner
13df3441ae Use MaxSizeVector instead of std::vector: xcode sometimes assumes that std::vector allocates aligned memory and therefore issues aligned instruction to initialize it. This can result in random crashes when compiling with AVX instructions enabled. 2016-09-02 19:25:47 -07:00
Benoit Steiner
cadd124d73 Pulled latest update from trunk 2016-09-02 15:30:02 -07:00
Benoit Steiner
05b0518077 Made the index type an explicit template parameter to help some compilers compile the code. 2016-09-02 15:29:34 -07:00
Benoit Steiner
adf864fec0 Merged in rmlarsen/eigen (pull request PR-222) 
Fix CUDA build broken by changes to min and max reduction.
 2016-09-02 14:11:20 -07:00
Rasmus Munk Larsen
13e93ca8b7 Fix CUDA build broken by changes to min and max reduction. 2016-09-02 13:41:36 -07:00
Benoit Steiner
c53f783705 Updated the contraction code to support constant inputs. 2016-09-01 11:41:27 -07:00
Gael Guennebaud
46475eff9a Adjust Tensor module wrt recent change in nullary functor 2016-09-01 13:40:45 +02:00
Rasmus Munk Larsen
a1e092d1e8 Fix bugs to make min- and max reducers with correctly with IEEE infinities. 2016-08-31 15:04:16 -07:00
Gael Guennebaud
35a8e94577 bug #1167: simplify installation of header files using cmake's install(DIRECTORY ...) command. 2016-08-29 10:59:37 +02:00
Gael Guennebaud
965e595f02 Add missing log1p method 2016-08-26 14:55:00 +02:00
Benoit Steiner
34ae80179a Use array_prod instead of calling TotalSize since TotalSize is only available on DSize. 2016-08-15 10:29:14 -07:00
Benoit Steiner
fe73648c98 Fixed a bug in the documentation. 2016-08-12 10:00:43 -07:00
Benoit Steiner
64e68cbe87 Don't attempt to optimize partial reductions when the optimized implementation doesn't buy anything. 2016-08-08 19:29:59 -07:00
Benoit Steiner
ca2cee2739 Merged in ibab/eigen (pull request PR-206) 
Expose real and imag methods on Tensors
 2016-08-03 11:53:04 -07:00
Benoit Steiner
a20b58845f CUDA_ARCH isn't always defined, so avoid relying on it too much when figuring out which implementation to use for reductions. Instead rely on the device to tell us on which hardware version we're running. 2016-08-03 10:00:43 -07:00
Benoit Steiner
fd220dd8b0 Use numext::conj instead of std::conj 2016-08-01 18:16:16 -07:00
Benoit Steiner
e256acec7c Avoid unecessary object copies 2016-08-01 17:03:39 -07:00
Benoit Steiner
2693fd54bf bug #1266: half implementation has been moved to half_impl namespace 2016-07-29 13:45:56 -07:00
Benoit Steiner
3d3d34e442 Deleted dead code. 2016-07-25 08:53:37 -07:00
Gael Guennebaud
6d5daf32f5 bug #1255: comment out broken and unsused line. 2016-07-25 14:48:30 +02:00
Gael Guennebaud
9908020d36 Add minimal support for Array<string>, and fix Tensor<string> 2016-07-25 14:25:56 +02:00
Benoit Steiner
c6b0de2c21 Improved partial reductions in more cases 2016-07-22 17:18:20 -07:00
Gael Guennebaud
0f350a8b7e Fix CUDA compilation 2016-07-21 18:47:07 +02:00
Benoit Steiner
20f7ef2f89 An evalTo expression is only aligned iff both the lhs and the rhs are aligned. 2016-07-12 10:56:42 -07:00
Benoit Steiner
3a2dd352ae Improved the contraction mapper to properly support tensor products 2016-07-11 13:43:41 -07:00
Benoit Steiner
0bc020be9d Improved the detection of packet size in the tensor scan evaluator. 2016-07-11 12:14:56 -07:00
Gael Guennebaud
fd60966310 merge 2016-07-11 18:11:47 +02:00
Gael Guennebaud
194daa3048 Fix assertion (it did not make sense for static_val types) 2016-07-11 11:39:27 +02:00
Gael Guennebaud
18c35747ce Emulate _BitScanReverse64 for 32 bits builds 2016-07-11 11:38:04 +02:00
Gael Guennebaud
599f8ba617 Change runtime to compile-time conditional. 2016-07-08 11:39:43 +02:00
Gael Guennebaud
544935101a Fix warnings 2016-07-08 11:38:52 +02:00
Gael Guennebaud
2f7e2614e7 bug #1232: refactor special functions as a new SpecialFunctions module, currently in unsupported/. 2016-07-08 11:13:55 +02:00
Gael Guennebaud
179ebb88f9 Fix warning 2016-07-07 09:16:40 +02:00
Gael Guennebaud
ce9fc0ce14 fix clang compilation 2016-07-04 12:59:02 +02:00
Gael Guennebaud
440020474c Workaround compilation issue with msvc 2016-07-04 12:49:19 +02:00
Igor Babuschkin
78f37ca03c Expose real and imag methods on Tensors 2016-07-01 17:34:31 +01:00
Benoit Steiner
cb2d8b8fa6 Made it possible to compile reductions for an old cuda architecture and run them on a recent gpu. 2016-06-29 15:42:01 -07:00
Benoit Steiner
b2a47641ce Made the code compile when using CUDA architecture < 300 2016-06-29 15:32:47 -07:00
Igor Babuschkin
85699850d9 Add missing CUDA kernel to tensor scan op 
The TensorScanOp implementation was missing a CUDA kernel launch.
This adds a simple placeholder implementation.
 2016-06-29 11:54:35 +01:00
Benoit Steiner
75c333f94c Don't store the scan axis in the evaluator of the tensor scan operation since it's only used in the constructor. 
Also avoid taking references to values that may becomes stale after a copy construction.
 2016-06-27 10:32:38 -07:00
Benoit Steiner
7944d4431f Made the cost model cwiseMax and cwiseMin methods consts to help the PowerPC cuda compiler compile this code. 2016-08-18 13:46:36 -07:00
Benoit Steiner
647a51b426 Force the inlining of a simple accessor. 2016-08-18 12:31:02 -07:00
Benoit Steiner
a452dedb4f Merged in ibab/eigen/double-tensor-reduction (pull request PR-216) 
Enable efficient Tensor reduction for doubles on the GPU (continued)
 2016-08-18 12:29:54 -07:00
Igor Babuschkin
18c67df31c Fix remaining CUDA >= 300 checks 2016-08-18 17:18:30 +01:00
Igor Babuschkin
1569a7d7ab Add the necessary CUDA >= 300 checks back 2016-08-18 17:15:12 +01:00
Benoit Steiner
2b17f34574 Properly detect the type of the result of a contraction. 2016-08-16 16:00:30 -07:00
Igor Babuschkin
841e075154 Remove CUDA >= 300 checks and enable outer reductin for doubles 2016-08-06 18:07:50 +01:00
Igor Babuschkin
0425118e2a Merge upstream changes 2016-08-05 14:34:57 +01:00
Igor Babuschkin
9537e8b118 Make use of atomicExch for atomicExchCustom 2016-08-05 14:29:58 +01:00
Igor Babuschkin
eeb0d880ee Enable efficient Tensor reduction for doubles 2016-07-01 19:08:26 +01:00
Rasmus Munk Larsen
a9c1e4d7b7 Return -1 from CurrentThreadId when called by thread outside the pool. 2016-06-23 16:40:07 -07:00
Rasmus Munk Larsen
d39df320d2 Resolve merge. 2016-06-23 15:08:03 -07:00
Gael Guennebaud
360a743a10 bug #1241: does not emmit anything for empty tensors 2016-06-23 18:47:31 +02:00
Gael Guennebaud
7c6561485a merge PR 194 2016-06-23 15:29:57 +02:00
Benoit Steiner
a29a2cb4ff Silenced a couple of compilation warnings generated by xcode 2016-06-22 16:43:02 -07:00
Benoit Steiner
f8fcd6b32d Turned the constructor of the PerThread struct into what is effectively a constant expression to make the code compatible with a wider range of compilers 2016-06-22 16:03:11 -07:00
Benoit Steiner
c58df31747 Handle empty tensors in the print functions 2016-06-21 09:22:43 -07:00
Benoit Steiner
de32f8d656 Fixed the printing of rank-0 tensors 2016-06-20 10:46:45 -07:00
Benoit Steiner
7d495d890a Merged in ibab/eigen (pull request PR-197) 
Implement exclusive scan option for Tensor library
 2016-06-14 17:54:59 -07:00
Benoit Steiner
aedc5be1d6 Avoid generating pseudo random numbers that are multiple of 5: this helps 
spread the load over multiple cpus without havind to rely on work stealing.
 2016-06-14 17:51:47 -07:00
Igor Babuschkin
c4d10e921f Implement exclusive scan option 2016-06-14 19:44:07 +01:00
Gael Guennebaud
76236cdea4 merge 2016-06-14 15:33:47 +02:00
Gael Guennebaud
5d38203735 Update Tensor module to use bind1st_op and bind2nd_op 2016-06-14 15:06:03 +02:00
Benoit Steiner
65d33e5898 Merged in ibab/eigen (pull request PR-195) 
Add small fixes to TensorScanOp
 2016-06-10 19:31:17 -07:00
Benoit Steiner
a05607875a Don't refer to the half2 type unless it's been defined 2016-06-10 11:53:56 -07:00
Igor Babuschkin
86aedc9282 Add small fixes to TensorScanOp 2016-06-07 20:06:38 +01:00
Benoit Steiner
84b2060a9e Fixed compilation error with gcc 4.4 2016-06-06 17:16:19 -07:00
Benoit Steiner
7ef9f47b58 Misc small improvements to the reduction code. 2016-06-06 14:09:46 -07:00
Benoit Steiner
9137f560f0 Moved assertions to the constructor to make the code more portable 2016-06-06 07:26:48 -07:00
Rasmus Munk Larsen
f1f2ff8208 size_t -> int 2016-06-03 18:06:37 -07:00
Rasmus Munk Larsen
76308e7fd2 Add CurrentThreadId and NumThreads methods to Eigen threadpools and TensorDeviceThreadPool. 2016-06-03 16:28:58 -07:00
Benoit Steiner
37638dafd7 Simplified the code that dispatches vectorized reductions on GPU 2016-06-09 10:29:52 -07:00
Benoit Steiner
66796e843d Fixed definition of some of the reducer_traits 2016-06-09 08:50:01 -07:00
Benoit Steiner
14a112ee15 Use signed integers more consistently to encode the number of threads to use to evaluate a tensor expression. 2016-06-09 08:25:22 -07:00
Benoit Steiner
8f92c26319 Improved code formatting 2016-06-09 08:23:42 -07:00
Benoit Steiner
aa33446dac Improved support for vectorization of 16-bit floats 2016-06-09 08:22:27 -07:00
Benoit Steiner
d6d39c7ddb Added missing EIGEN_DEVICE_FUNC 2016-06-07 14:35:08 -07:00
Benoit Steiner
c3c8ad8046 Align the first element of the Waiter struct instead of padding it. This reduces its memory footprint a bit while achieving the goal of preventing false sharing 2016-06-02 21:17:41 -07:00
Eugene Brevdo
39baff850c Add TernaryFunctors and the betainc SpecialFunction. 
TernaryFunctors and their executors allow operations on 3-tuples of inputs.
API fully implemented for Arrays and Tensors based on binary functors.

Ported the cephes betainc function (regularized incomplete beta
integral) to Eigen, with support for CPU and GPU, floats, doubles, and
half types.

Added unit tests in array.cpp and cxx11_tensor_cuda.cu


Collapsed revision
* Merged helper methods for betainc across floats and doubles.
* Added TensorGlobalFunctions with betainc().  Removed betainc() from TensorBase.
* Clean up CwiseTernaryOp checks, change igamma_helper to cephes_helper.
* betainc: merge incbcf and incbd into incbeta_cfe.  and more cleanup.
* Update TernaryOp and SpecialFunctions (betainc) based on review comments.
 2016-06-02 17:04:19 -07:00
Benoit Steiner
c21eaedce6 Use array_prod to compute the number of elements contained in the input tensor expression 2016-06-04 07:47:04 -07:00
Benoit Steiner
36a4500822 Merged in ibab/eigen (pull request PR-192) 
Add generic scan method
 2016-06-03 17:28:33 -07:00
Benoit Steiner
c2a102345f Improved the performance of full reductions. 
AFTER:
BM_fullReduction/10        4541       4543     154017  21.0M items/s
BM_fullReduction/64        5191       5193     100000  752.5M items/s
BM_fullReduction/512       9588       9588      71361  25.5G items/s
BM_fullReduction/4k      244314     244281       2863  64.0G items/s
BM_fullReduction/5k      359382     359363       1946  64.8G items/s

BEFORE:
BM_fullReduction/10        9085       9087      74395  10.5M items/s
BM_fullReduction/64        9478       9478      72014  412.1M items/s
BM_fullReduction/512      14643      14646      46902  16.7G items/s
BM_fullReduction/4k      260338     260384       2678  60.0G items/s
BM_fullReduction/5k      385076     385178       1818  60.5G items/s
 2016-06-03 17:27:08 -07:00
Igor Babuschkin
dc03b8f3a1 Add generic scan method 2016-06-03 17:37:04 +01:00
Rasmus Munk Larsen
811aadbe00 Add syntactic sugar to Eigen tensors to allow more natural syntax. 
Specifically, this enables expressions involving:

scalar + tensor
scalar * tensor
scalar / tensor
scalar - tensor
 2016-06-02 12:41:28 -07:00
Igor Babuschkin
fbd7ed6ff7 Add tensor scan op 
This is the initial implementation a generic scan operation.
Based on this, cumsum and cumprod method have been added to TensorBase.
 2016-06-02 13:35:47 +01:00
Benoit Steiner
0ed08fd281 Use a single PacketSize variable 2016-06-01 21:19:05 -07:00
Benoit Steiner
8f6fedc55f Fixed compilation warning 2016-06-01 21:14:46 -07:00