Commit Graph

945 Commits

Author SHA1 Message Date
Gael Guennebaud
f8a55cc062 Fix compilation. 2017-02-18 10:08:13 +01:00
Benoit Steiner
cfa0568ef7 Size indices are signed. 2017-02-16 10:13:34 -08:00
Mehdi Goli
91982b91c0 Adding TensorLayoutSwapOp for sycl. 2017-02-15 16:28:12 +00:00
Mehdi Goli
b1e312edd6 Adding TensorPatch.h for sycl backend. 2017-02-15 10:13:01 +00:00
Mehdi Goli
0d153ded29 Adding TensorChippingOP for sycl backend; fixing the index value in the verification operation for cxx11_tensorChipping.cpp test 2017-02-13 17:25:12 +00:00
Benoit Steiner
769208a17f Pulled latest updates from upstream 2017-02-10 13:11:40 -08:00
Mehdi Goli
0ee97b60c2 Adding mean to TensorReductionSycl.h 2017-02-07 15:43:17 +00:00
Mehdi Goli
42bd5c4e7b Fixing TensorReductionSycl for min and max. 2017-02-06 18:05:23 +00:00
Mehdi Goli
bc128f9f3b Reducing the warnings in Sycl backend. 2017-02-02 10:43:47 +00:00
Benoit Steiner
442e9cbb30 Silenced several compilation warnings 2017-02-01 15:50:58 -08:00
Mehdi Goli
bab29936a1 Reducing warnings in Sycl backend. 2017-02-01 15:29:53 +00:00
Mehdi Goli
48a20b7d95 Fixing compiler error on TensorContractionSycl.h; Silencing the compiler unused parameter warning for eval_op_indices in TensorContraction.h 2017-01-31 14:06:36 +00:00
Benoit Steiner
fbc39fd02c Merge latest changes from upstream 2017-01-30 15:25:57 -08:00
Mehdi Goli
82ce92419e Fixing the buffer type in memcpy. 2017-01-30 11:38:20 +00:00
Rasmus Munk Larsen
edaa0fc5d1 Revert PR-292. After further investigation, the memcpy->memmove change was only good for Haswell on older versions of glibc. Adding a switch for small sizes is perhaps useful for string copies, but also has an overhead for larger sizes, making it a poor trade-off for general memcpy.
This PR also removes a couple of unnecessary semi-colons in Eigen/src/Core/AssignEvaluator.h that caused compiler warning everywhere.
2017-01-26 12:46:06 -08:00
Gael Guennebaud
25a1703579 Merged in ggael/eigen-flexidexing (pull request PR-294)
generalized operator() for indexed access and slicing
2017-01-26 08:04:23 +00:00
Gael Guennebaud
607be65a03 Fix duplicates of array_size bewteen unsupported and Core 2017-01-25 22:53:58 +01:00
Rasmus Munk Larsen
e6b1020221 Adds a fast memcpy function to Eigen. This takes advantage of the following:
1. For small fixed sizes, the compiler generates inline code for memcpy, which is much faster.

2. My colleague eriche at googl dot com discovered that for large sizes, memmove is significantly faster than memcpy (at least on Linux with GCC or Clang). See benchmark numbers measured on a Haswell (HP Z440) workstation here: https://docs.google.com/a/google.com/spreadsheets/d/1jLs5bKzXwhpTySw65MhG1pZpsIwkszZqQTjwrd_n0ic/pubhtml This is of course surprising since memcpy is a less constrained version of memmove. This stackoverflow thread contains some speculation as to the causes: http://stackoverflow.com/questions/22793669/poor-memcpy-performance-on-linux

Below are numbers for copying and slicing tensors using the multithreaded TensorDevice. The numbers show significant improvements for memcpy of very small blocks and for memcpy of large blocks single threaded (we were already able to saturate memory bandwidth for >1 threads before on large blocks). The "slicingSmallPieces" benchmark also shows small consistent improvements, since memcpy cost is a fair portion of that particular computation.

The benchmarks operate on NxN matrices, and the names are of the form BM_$OP_${NUMTHREADS}T/${N}.

Measured improvements in wall clock time:

Run on rmlarsen3.mtv (12 X 3501 MHz CPUs); 2017-01-20T11:26:31.493023454-08:00
CPU: Intel Haswell with HyperThreading (6 cores) dL1:32KB dL2:256KB dL3:15MB
Benchmark                          Base (ns)  New (ns) Improvement
------------------------------------------------------------------
BM_memcpy_1T/2                          3.48      2.39    +31.3%
BM_memcpy_1T/8                          12.3      6.51    +47.0%
BM_memcpy_1T/64                          371       383     -3.2%
BM_memcpy_1T/512                       66922     66720     +0.3%
BM_memcpy_1T/4k                      9892867   6849682    +30.8%
BM_memcpy_1T/5k                     14951099  10332856    +30.9%
BM_memcpy_2T/2                          3.50      2.46    +29.7%
BM_memcpy_2T/8                          12.3      7.66    +37.7%
BM_memcpy_2T/64                          371       376     -1.3%
BM_memcpy_2T/512                       66652     66788     -0.2%
BM_memcpy_2T/4k                      6145012   6117776     +0.4%
BM_memcpy_2T/5k                      9181478   9010942     +1.9%
BM_memcpy_4T/2                          3.47      2.47    +31.0%
BM_memcpy_4T/8                          12.3      6.67    +45.8
BM_memcpy_4T/64                          374       376     -0.5%
BM_memcpy_4T/512                       67833     68019     -0.3%
BM_memcpy_4T/4k                      5057425   5188253     -2.6%
BM_memcpy_4T/5k                      7555638   7779468     -3.0%
BM_memcpy_6T/2                          3.51      2.50    +28.8%
BM_memcpy_6T/8                          12.3      7.61    +38.1%
BM_memcpy_6T/64                          373       378     -1.3%
BM_memcpy_6T/512                       66871     66774     +0.1%
BM_memcpy_6T/4k                      5112975   5233502     -2.4%
BM_memcpy_6T/5k                      7614180   7772246     -2.1%
BM_memcpy_8T/2                          3.47      2.41    +30.5%
BM_memcpy_8T/8                          12.4      10.5    +15.3%
BM_memcpy_8T/64                          372       388     -4.3%
BM_memcpy_8T/512                       67373     66588     +1.2%
BM_memcpy_8T/4k                      5148462   5254897     -2.1%
BM_memcpy_8T/5k                      7660989   7799058     -1.8%
BM_memcpy_12T/2                         3.50      2.40    +31.4%
BM_memcpy_12T/8                         12.4      7.55    +39.1
BM_memcpy_12T/64                         374       378     -1.1%
BM_memcpy_12T/512                      67132     66683     +0.7%
BM_memcpy_12T/4k                     5185125   5292920     -2.1%
BM_memcpy_12T/5k                     7717284   7942684     -2.9%
BM_slicingSmallPieces_1T/2              47.3      47.5     +0.4%
BM_slicingSmallPieces_1T/8              53.6      52.3     +2.4%
BM_slicingSmallPieces_1T/64              491       476     +3.1%
BM_slicingSmallPieces_1T/512           21734     18814    +13.4%
BM_slicingSmallPieces_1T/4k           394660    396760     -0.5%
BM_slicingSmallPieces_1T/5k           218722    209244     +4.3%
BM_slicingSmallPieces_2T/2              80.7      79.9     +1.0%
BM_slicingSmallPieces_2T/8              54.2      53.1     +2.0
BM_slicingSmallPieces_2T/64              497       477     +4.0%
BM_slicingSmallPieces_2T/512           21732     18822    +13.4%
BM_slicingSmallPieces_2T/4k           392885    390490     +0.6%
BM_slicingSmallPieces_2T/5k           221988    208678     +6.0%
BM_slicingSmallPieces_4T/2              80.8      80.1     +0.9%
BM_slicingSmallPieces_4T/8              54.1      53.2     +1.7%
BM_slicingSmallPieces_4T/64              493       476     +3.4%
BM_slicingSmallPieces_4T/512           21702     18758    +13.6%
BM_slicingSmallPieces_4T/4k           393962    404023     -2.6%
BM_slicingSmallPieces_4T/5k           249667    211732    +15.2%
BM_slicingSmallPieces_6T/2              80.5      80.1     +0.5%
BM_slicingSmallPieces_6T/8              54.4      53.4     +1.8%
BM_slicingSmallPieces_6T/64              488       478     +2.0%
BM_slicingSmallPieces_6T/512           21719     18841    +13.3%
BM_slicingSmallPieces_6T/4k           394950    397583     -0.7%
BM_slicingSmallPieces_6T/5k           223080    210148     +5.8%
BM_slicingSmallPieces_8T/2              81.2      80.4     +1.0%
BM_slicingSmallPieces_8T/8              58.1      53.5     +7.9%
BM_slicingSmallPieces_8T/64              489       480     +1.8%
BM_slicingSmallPieces_8T/512           21586     18798    +12.9%
BM_slicingSmallPieces_8T/4k           394592    400165     -1.4%
BM_slicingSmallPieces_8T/5k           219688    208301     +5.2%
BM_slicingSmallPieces_12T/2             80.2      79.8     +0.7%
BM_slicingSmallPieces_12T/8             54.4      53.4     +1.8
BM_slicingSmallPieces_12T/64             488       476     +2.5%
BM_slicingSmallPieces_12T/512          21931     18831    +14.1%
BM_slicingSmallPieces_12T/4k          393962    396541     -0.7%
BM_slicingSmallPieces_12T/5k          218803    207965     +5.0%
2017-01-24 13:55:18 -08:00
Luke Iwanski
bf44fed9b7 Allows AMD APU 2017-01-23 15:56:45 +00:00
Mehdi Goli
602f8c27f5 Reverting back to the previous TensorDeviceSycl.h as the total number of buffer is not enough for tensorflow. 2017-01-20 18:23:20 +00:00
Mehdi Goli
77cc4d06c7 Removing unused variables 2017-01-19 17:06:21 +00:00
Mehdi Goli
837fdbdcb2 Merging with Benoit's upstream. 2017-01-19 11:34:34 +00:00
Mehdi Goli
6bdd15f572 Adding non-deferrenciable pointer track for ComputeCpp backend; Adding TensorConvolutionOp for ComputeCpp; fixing typos. modifying TensorDeviceSycl to use the LegacyPointer class. 2017-01-19 11:30:59 +00:00
Mehdi Goli
c6f7b33834 Applying Benoit's comment. Embedding synchronisation inside device memcpy so there is no need to externally call synchronise() for device memcopy. 2017-01-18 10:45:28 +00:00
Mehdi Goli
e46e722381 Adding Tensor ReverseOp; TensorStriding; TensorConversionOp; Modifying Tensor Contractsycl to be located in any place in the expression tree. 2017-01-16 13:58:49 +00:00
Luke Iwanski
90c5bc8d64 Fixes auto appearance in functor template argument for reduction. 2017-01-04 22:18:44 +00:00
Mehdi Goli
8b1c2108ba Reverting asynchronous exec to Synchronous exec regarding random race condition. 2016-12-22 16:45:38 +00:00
Benoit Steiner
660da83e18 Pulled latest update from trunk 2016-12-21 16:43:27 -08:00
Benoit Steiner
4236aebe10 Simplified the contraction code` 2016-12-21 16:42:56 -08:00
Benoit Steiner
3cfa16f41d Merged in benoitsteiner/opencl (pull request PR-279)
Fix for auto appearing in functor template argument.
2016-12-21 15:08:54 -08:00
Benoit Steiner
519d63d350 Added support for libxsmm kernel in multithreaded contractions 2016-12-21 15:06:06 -08:00
Benoit Steiner
f9eff17e91 Leverage libxsmm kernels within signle threaded contractions 2016-12-21 12:32:06 -08:00
Luke Iwanski
c55ecfd820 Fix for auto appearing in functor template argument. 2016-12-21 15:42:51 +00:00
Luke Iwanski
29186f766f Fixed order of initialisation in ExecExprFunctorKernel functor. 2016-12-20 21:32:42 +00:00
Luke Iwanski
8245851d1b Matching parameters order between lambda and the functor. 2016-12-20 16:18:15 +00:00
Benoit Steiner
70d0172f0c Merged eigen/eigen into default 2016-12-16 17:37:04 -08:00
Benoit Steiner
8910442e19 Fixed memcpy, memcpyHostToDevice and memcpyDeviceToHost for Sycl. 2016-12-16 15:45:04 -08:00
Luke Iwanski
54db66c5df struct -> class in order to silence compilation warning. 2016-12-16 20:25:20 +00:00
Mehdi Goli
35bae513a0 Converting all parallel for lambda to functor in order to prevent kernel duplication name error; adding tensorConcatinationOp backend for sycl. 2016-12-16 19:46:45 +00:00
Mehdi Goli
c5e8546306 Adding asynchandler to sycl queue as lack of it can cause undefined behaviour. 2016-12-15 16:59:57 +00:00
Benoit Steiner
2c2e218471 Avoid using #define since they can conflict with user code 2016-12-14 19:49:15 -08:00
Benoit Steiner
3beb180ee5 Don't call EnvThread::OnCancel by default since it doesn't do anything. 2016-12-14 18:33:39 -08:00
Benoit Steiner
9ff5d0f821 Merged eigen/eigen into default 2016-12-14 17:32:16 -08:00
Mehdi Goli
730eb9fe1c Adding asynchronous execution as it improves the performance. 2016-12-14 17:38:53 +00:00
Mehdi Goli
2d4a091beb Adding tensor contraction operation backend for Sycl; adding test for contractionOp sycl backend; adding temporary solution to prevent memory leak in buffer; cleaning up cxx11_tensor_buildins_sycl.h 2016-12-14 15:30:37 +00:00
Benoit Steiner
a432fc102d Moved the choice of ThreadPool to unsupported/Eigen/CXX11/ThreadPool 2016-12-12 15:24:16 -08:00
Benoit Steiner
8ae68924ed Made ThreadPoolInterface::Cancel() an optional functionality 2016-12-12 11:58:38 -08:00
Benoit Steiner
76fca22134 Use a more accurate timer to sleep on Linux systems. 2016-12-09 15:12:24 -08:00
Benoit Steiner
4deafd35b7 Introduce a portable EIGEN_SLEEP macro. 2016-12-09 14:52:15 -08:00
Benoit Steiner
aafa97f4d2 Fixed build error with MSVC 2016-12-09 14:42:32 -08:00
Benoit Steiner
2f5b7a199b Reworked the threadpool cancellation mechanism to not depend on pthread_cancel since it turns out that pthread_cancel doesn't work properly on numerous platforms. 2016-12-09 13:05:14 -08:00
Benoit Steiner
28ee8f42b2 Added a Flush method to the RunQueue 2016-12-08 14:07:56 -08:00
Benoit Steiner
69ef267a77 Added the new threadpool cancel method to the threadpool interface based class. 2016-12-08 14:03:25 -08:00
Benoit Steiner
7bfff85355 Added support for thread cancellation on Linux 2016-12-08 08:12:49 -08:00
Benoit Steiner
462c28e77a Merged in srvasude/eigen (pull request PR-265)
Add Expm1 support to Eigen.
2016-12-05 02:31:11 +00:00
Gael Guennebaud
4465d20403 Add missing generic load methods. 2016-12-03 21:25:04 +01:00
Srinivas Vasudevan
218764ee1f Added support for expm1 in Eigen. 2016-12-02 14:13:01 -08:00
Mehdi Goli
592acc5bfa Makingt default numeric_list works with sycl. 2016-12-02 17:58:30 +00:00
Mehdi Goli
79aa2b784e Adding sycl backend for TensorPadding.h; disbaling __unit128 for sycl in TensorIntDiv.h; disabling cashsize for sycl in tensorDeviceDefault.h; adding sycl backend for StrideSliceOP ; removing sycl compiler warning for creating an array of size 0 in CXX11Meta.h; cleaning up the sycl backend code. 2016-12-01 13:02:27 +00:00
Benoit Steiner
a70393fd02 Cleaned up forward declarations 2016-11-30 21:59:07 -08:00
Benoit Steiner
e073de96dc Moved the MemCopyFunctor back to TensorSyclDevice since it's the only caller and it makes TensorFlow compile again 2016-11-30 21:36:52 -08:00
Benoit Steiner
fca27350eb Added the deallocate_all() method back 2016-11-30 20:45:20 -08:00
Benoit Steiner
e633a8371f Simplified includes 2016-11-30 20:21:18 -08:00
Benoit Steiner
7cd33df4ce Improved formatting 2016-11-30 20:20:44 -08:00
Benoit Steiner
f5107010ee Udated the Sizes class to work on AMD gpus without requiring a separate implementation 2016-11-30 19:57:28 -08:00
Benoit Steiner
e37c2c52d3 Added an implementation of numeric_list that works with sycl 2016-11-30 19:55:15 -08:00
Luke Iwanski
26fff1c5b1 Added EIGEN_STRONG_INLINE to get_sycl_supported_device(). 2016-11-30 16:55:22 +00:00
Mehdi Goli
577ce78085 Adding TensorShuffling backend for sycl; adding TensorReshaping backend for sycl; cleaning up the sycl backend. 2016-11-29 15:30:42 +00:00
Benoit Steiner
02080e2b67 Merged eigen/eigen into default 2016-11-27 07:27:30 -08:00
Benoit Steiner
9fd081cddc Fixed compilation warnings 2016-11-26 20:22:25 -08:00
Benoit Steiner
9f8fbd9434 Merged eigen/eigen into default 2016-11-26 11:28:25 -08:00
Benoit Steiner
67b2c41f30 Avoided unnecessary type conversion 2016-11-26 11:27:29 -08:00
Benoit Steiner
7fe704596a Added missing array_get method for numeric_list 2016-11-26 11:26:07 -08:00
Mehdi Goli
7318daf887 Fixing LLVM error on TensorMorphingSycl.h on GPU; fixing int64_t crash for tensor_broadcast_sycl on GPU; adding get_sycl_supported_devices() on syclDevice.h. 2016-11-25 16:19:07 +00:00
Benoit Steiner
7ad37606dd Fixed the documentation of Scalar Tensors 2016-11-24 12:31:43 -08:00
Mehdi Goli
b8cc5635d5 Removing unsupported device from test case; cleaning the tensor device sycl. 2016-11-23 16:30:41 +00:00
Benoit Steiner
f11da1d83b Made the QueueInterface thread safe 2016-11-20 13:17:08 -08:00
Benoit Steiner
6d781e3e52 Merged eigen/eigen into default 2016-11-20 10:12:54 -08:00
Benoit Steiner
79a07b891b Fixed a typo 2016-11-20 07:07:41 -08:00
Benoit Steiner
81151bd474 Fixed merge conflicts 2016-11-19 19:12:59 -08:00
Benoit Steiner
9265ca707e Made it possible to check the state of a sycl device without synchronization 2016-11-19 10:56:24 -08:00
Benoit Steiner
2d1aec15a7 Added missing include 2016-11-19 08:09:54 -08:00
Benoit Steiner
1bdf1b9ce0 Merged in benoitsteiner/opencl (pull request PR-253)
OpenCL improvements
2016-11-19 04:44:43 +00:00
Benoit Steiner
dc601d79d1 Added the ability to run test exclusively OpenCL devices that are listed by sycl::device::get_devices(). 2016-11-18 16:26:50 -08:00
Benoit Steiner
110b7f8d9f Deleted unnecessary semicolons 2016-11-18 14:06:17 -08:00
Benoit Steiner
37c2c516a6 Cleaned up the sycl device code 2016-11-18 12:38:06 -08:00
Mehdi Goli
15e226d7d3 adding Benoit changes on the TensorDeviceSycl.h 2016-11-18 16:34:54 +00:00
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