aboutsummaryrefslogtreecommitdiffhomepage
path: root/unsupported/Eigen/CXX11/src/Tensor
Commit message (Collapse)AuthorAge
* Adding TensorIndexTuple and TensorTupleReduceOP backend (ArgMax/Min) for ↵Gravatar Mehdi Goli2017-03-07
| | | | sycl; fixing the address space issue for const TensorMap; converting all discard_write to write due to data missmatch.
* Adding sycl backend for TensorCustomOp; fixing the partial lhs modification ↵Gravatar Mehdi Goli2017-02-28
| | | | issue on sycl when the rhs is TensorContraction, reduction or convolution; Fixing the partial modification for memset when sycl backend is used.
* Merged eigen/eigen into defaultGravatar Benoit Steiner2017-02-26
|\
* | Adding TensorVolumePatchOP.h for syclGravatar Mehdi Goli2017-02-24
| |
* | Converting fixed float type into template type for TensorContraction.Gravatar Mehdi Goli2017-02-24
| |
* | Adding Sycl Backend for TensorGenerator.h.Gravatar Mehdi Goli2017-02-22
| |
* | Adding Sycl backend for TensorImagePatchOP.h; adding Sycl backend for ↵Gravatar Mehdi Goli2017-02-20
| | | | | | | | TensorInflation.h.
| * Silent warning.Gravatar Gael Guennebaud2017-02-20
| |
| * Fix compilation.Gravatar Gael Guennebaud2017-02-18
| |
| * Size indices are signed.Gravatar Benoit Steiner2017-02-16
| |
* | Adding TensorLayoutSwapOp for sycl.Gravatar Mehdi Goli2017-02-15
| |
* | Adding TensorPatch.h for sycl backend.Gravatar Mehdi Goli2017-02-15
|/
* Adding TensorChippingOP for sycl backend; fixing the index value in the ↵Gravatar Mehdi Goli2017-02-13
| | | | verification operation for cxx11_tensorChipping.cpp test
* Pulled latest updates from upstreamGravatar Benoit Steiner2017-02-10
|\
* | Adding mean to TensorReductionSycl.hGravatar Mehdi Goli2017-02-07
| |
* | Fixing TensorReductionSycl for min and max.Gravatar Mehdi Goli2017-02-06
| |
* | Reducing the warnings in Sycl backend.Gravatar Mehdi Goli2017-02-02
| |
| * Silenced several compilation warningsGravatar Benoit Steiner2017-02-01
| |
* | Reducing warnings in Sycl backend.Gravatar Mehdi Goli2017-02-01
| |
* | Fixing compiler error on TensorContractionSycl.h; Silencing the compiler ↵Gravatar Mehdi Goli2017-01-31
| | | | | | | | unused parameter warning for eval_op_indices in TensorContraction.h
* | Merge latest changes from upstreamGravatar Benoit Steiner2017-01-30
|\|
* | Fixing the buffer type in memcpy.Gravatar Mehdi Goli2017-01-30
| |
| * Revert PR-292. After further investigation, the memcpy->memmove change was ↵Gravatar Rasmus Munk Larsen2017-01-26
| | | | | | | | | | | | 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.
| * Adds a fast memcpy function to Eigen. This takes advantage of the following:Gravatar Rasmus Munk Larsen2017-01-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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%
* | Allows AMD APUGravatar Luke Iwanski2017-01-23
| |
* | Reverting back to the previous TensorDeviceSycl.h as the total number of ↵Gravatar Mehdi Goli2017-01-20
| | | | | | | | buffer is not enough for tensorflow.
* | Removing unused variablesGravatar Mehdi Goli2017-01-19
| |
* | Merging with Benoit's upstream.Gravatar Mehdi Goli2017-01-19
|\ \
* | | Adding non-deferrenciable pointer track for ComputeCpp backend; Adding ↵Gravatar Mehdi Goli2017-01-19
| | | | | | | | | | | | TensorConvolutionOp for ComputeCpp; fixing typos. modifying TensorDeviceSycl to use the LegacyPointer class.
| * | Applying Benoit's comment. Embedding synchronisation inside device memcpy so ↵Gravatar Mehdi Goli2017-01-18
|/ / | | | | | | there is no need to externally call synchronise() for device memcopy.
* | Adding Tensor ReverseOp; TensorStriding; TensorConversionOp; Modifying ↵Gravatar Mehdi Goli2017-01-16
| | | | | | | | Tensor Contractsycl to be located in any place in the expression tree.
* | Fixes auto appearance in functor template argument for reduction.Gravatar Luke Iwanski2017-01-04
| |
* | Reverting asynchronous exec to Synchronous exec regarding random race condition.Gravatar Mehdi Goli2016-12-22
| |
| * Pulled latest update from trunkGravatar Benoit Steiner2016-12-21
| |\
| * | Simplified the contraction code`Gravatar Benoit Steiner2016-12-21
| | |
| | * Merged in benoitsteiner/opencl (pull request PR-279)Gravatar Benoit Steiner2016-12-21
| |/| | |/ |/| | | Fix for auto appearing in functor template argument.
| * Added support for libxsmm kernel in multithreaded contractionsGravatar Benoit Steiner2016-12-21
| |
| * Leverage libxsmm kernels within signle threaded contractionsGravatar Benoit Steiner2016-12-21
| |
* | Fix for auto appearing in functor template argument.Gravatar Luke Iwanski2016-12-21
|/
* Fixed order of initialisation in ExecExprFunctorKernel functor.Gravatar Luke Iwanski2016-12-20
|
* Matching parameters order between lambda and the functor.Gravatar Luke Iwanski2016-12-20
|
* Merged eigen/eigen into defaultGravatar Benoit Steiner2016-12-16
|\
| * Fixed memcpy, memcpyHostToDevice and memcpyDeviceToHost for Sycl.Gravatar Benoit Steiner2016-12-16
| |
* | struct -> class in order to silence compilation warning.Gravatar Luke Iwanski2016-12-16
| |
* | Converting all parallel for lambda to functor in order to prevent kernel ↵Gravatar Mehdi Goli2016-12-16
|/ | | | duplication name error; adding tensorConcatinationOp backend for sycl.
* Adding asynchandler to sycl queue as lack of it can cause undefined behaviour.Gravatar Mehdi Goli2016-12-15
|
* Avoid using #define since they can conflict with user codeGravatar Benoit Steiner2016-12-14
|
* Merged eigen/eigen into defaultGravatar Benoit Steiner2016-12-14
|\
* | Adding asynchronous execution as it improves the performance.Gravatar Mehdi Goli2016-12-14
| |
* | Adding tensor contraction operation backend for Sycl; adding test for ↵Gravatar Mehdi Goli2016-12-14
| | | | | | | | contractionOp sycl backend; adding temporary solution to prevent memory leak in buffer; cleaning up cxx11_tensor_buildins_sycl.h
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-02 04:29:54 +0000