aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
* Add optimized version of logistic function for float. As an example, this is ↵Gravatar Rasmus Munk Larsen2018-11-12
| | | | about 50% faster than the existing version on Haswell using AVX.
* Add manual doc on STL-compatible iteratorsGravatar Gael Guennebaud2018-11-12
|
* Fix warning in c++03Gravatar Gael Guennebaud2018-11-10
|
* A few small fixes to a) prevent throwing in ctors and dtors of the threading ↵Gravatar Rasmus Munk Larsen2018-11-09
| | | | code, and b) supporting matrix exponential on platforms with 113 bits of mantissa for long doubles.
* bug #1619: fix mixing of const and non-const generic iteratorsGravatar Gael Guennebaud2018-11-09
|
* bug #1619: make const and non-const iterators compatibleGravatar Gael Guennebaud2018-11-09
|
* add missing ref to a.zeta(b)Gravatar Gael Guennebaud2018-11-09
|
* Limit the size of the tocGravatar Gael Guennebaud2018-11-09
|
* Update doxy hacks wrt doxygen 1.8.13/14Gravatar Gael Guennebaud2018-11-09
|
* Let doxygen sees lastNGravatar Gael Guennebaud2018-11-09
|
* Add and update manual pages for slicing, indexing, and reshaping.Gravatar Gael Guennebaud2018-11-09
|
* Recent xcode versions does support EIGEN_HAS_STATIC_ARRAY_TEMPLATEGravatar Gael Guennebaud2018-11-09
|
* Fix max-size in indexed-viewGravatar Gael Guennebaud2018-11-08
|
* Merged in glchaves/eigen (pull request PR-539)Gravatar Gael Guennebaud2018-11-07
|\ | | | | | | Vectorize row-by-row gebp loop iterations on 16 packets as well
* | Add option to disable plot generationGravatar Gael Guennebaud2018-11-07
| |
| * Vectorize row-by-row gebp loop iterations on 16 packets as wellGravatar Gustavo Lima Chaves2018-11-06
| | | | | | | | | | Signed-off-by: Gustavo Lima Chaves <gustavo.lima.chaves@intel.com> Signed-off-by: Mark D. Ryan <mark.d.ryan@intel.com>
* | PR 526: Speed up multiplication of small, dynamically sized matricesGravatar Mark D Ryan2018-10-12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The Packet16f, Packet8f and Packet8d types are too large to use with dynamically sized matrices typically processed by the SliceVectorizedTraversal specialization of the dense_assignment_loop. Using these types is likely to lead to little or no vectorization. Significant slowdown in the multiplication of these small matrices can be observed when building with AVX and AVX512 enabled. This patch introduces a new dense_assignment_kernel that is used when computing small products whose operands have dynamic dimensions. It ensures that the PacketSize used is no larger than 4, thereby increasing the chance that vectorized instructions will be used when computing the product. I tested all 969 possible combinations of M, K, and N that are handled by the dense_assignment_loop on x86 builds. Although a few combinations are slowed down by this patch they are far outnumbered by the cases that are sped up, as the following results demonstrate. Disabling Packed8d on AVX512 builds: Total Cases: 969 Better: 511 Worse: 85 Same: 373 Max Improvement: 169.00% (4 8 6) Max Degradation: 36.50% (8 5 3) Median Improvement: 35.46% Median Degradation: 17.41% Total FLOPs Improvement: 19.42% Disabling Packet16f and Packed8f on AVX512 builds: Total Cases: 969 Better: 658 Worse: 5 Same: 306 Max Improvement: 214.05% (8 6 5) Max Degradation: 22.26% (16 2 1) Median Improvement: 60.05% Median Degradation: 13.32% Total FLOPs Improvement: 59.58% Disabling Packed8f on AVX builds: Total Cases: 969 Better: 663 Worse: 96 Same: 210 Max Improvement: 155.29% (4 10 5) Max Degradation: 35.12% (8 3 2) Median Improvement: 34.28% Median Degradation: 15.05% Total FLOPs Improvement: 26.02%
* | Fix code formatGravatar Eugene Zhulenev2018-11-02
| |
* | Workaround nbcc+msvc compiler bugGravatar Eugene Zhulenev2018-11-02
|/
* add unit tests for bug #1619Gravatar Gael Guennebaud2018-11-01
|
* bug #1617: Fix SolveTriangular.solveInPlace crashing for empty matrix.Gravatar Matthieu Vigne2018-10-31
| | | | | This made FullPivLU.kernel() crash when used on the zero matrix. Add unit test for FullPivLU.kernel() on the zero matrix.
* bug #1618: Use different power-of-2 check to avoid MSVC warningGravatar Christoph Hertzberg2018-11-01
|
* Merged in ezhulenev/eigen-02 (pull request PR-534)Gravatar Rasmus Munk Larsen2018-10-25
|\ | | | | | | Fix cxx11_tensor_{block_access, reduction} tests
| * Fix cxx11_tensor_{block_access, reduction} testsGravatar Eugene Zhulenev2018-10-25
| |
* | Fix typo in tutorial documentation.Gravatar Halie Murray-Davis2018-10-25
| |
* | Document EIGEN_NO_IO preprocessor directiveGravatar Christoph Hertzberg2018-10-25
| |
* | Collapsed revision (based on pull request PR-325)Gravatar Christian von Schultz2018-10-22
| | | | | | | | | | | | | | * Support compiling without IO streams Add the preprocessor definition EIGEN_NO_IO which, if defined, disables all use of the IO streams part of the standard library.
* | Do not rely on the compiler generating __device__ functions for constexpr in ↵Gravatar Rasmus Munk Larsen2018-10-22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Cuda (via EIGEN_CONSTEXPR_ARE_DEVICE_FUNC. This breaks several target in the TensorFlow Cuda build, e.g., INFO: From Compiling tensorflow/core/kernels/maxpooling_op_gpu.cu.cc: /b/f/w/run/external/eigen_archive/Eigen/src/Core/arch/GPU/Half.h(197): error: calling a __host__ function("std::equal_to<float> ::operator () const") from a __global__ function("tensorflow::_NV_ANON_NAMESPACE::MaxPoolGradBackwardNoMaskNHWC< ::Eigen::half> ") is not allowed /b/f/w/run/external/eigen_archive/Eigen/src/Core/arch/GPU/Half.h(197): error: identifier "std::equal_to<float> ::operator () const" is undefined in device code" /b/f/w/run/external/eigen_archive/Eigen/src/Core/arch/GPU/Half.h(197): error: calling a __host__ function("std::equal_to<float> ::operator () const") from a __global__ function("tensorflow::_NV_ANON_NAMESPACE::MaxPoolGradBackwardNoMaskNCHW< ::Eigen::half> ") is not allowed /b/f/w/run/external/eigen_archive/Eigen/src/Core/arch/GPU/Half.h(197): error: identifier "std::equal_to<float> ::operator () const" is undefined in device code 4 errors detected in the compilation of "/tmp/tmpxft_00000011_00000000-6_maxpooling_op_gpu.cu.cpp1.ii". ERROR: /tmpfs/tensor_flow/tensorflow/core/kernels/BUILD:3753:1: output 'tensorflow/core/kernels/_objs/pooling_ops_gpu/maxpooling_op_gpu.cu.pic.o' was not created ERROR: /tmpfs/tensor_flow/tensorflow/core/kernels/BUILD:3753:1: Couldn't build file tensorflow/core/kernels/_objs/pooling_ops_gpu/maxpooling_op_gpu.cu.pic.o: not all outputs were created or valid
* | Suppress compiler warning about unused global variable.Gravatar Rasmus Munk Larsen2018-10-22
| |
* | Merged in rmlarsen/eigen (pull request PR-532)Gravatar Rasmus Munk Larsen2018-10-19
|\ \ | | | | | | | | | Only set EIGEN_CONSTEXPR_ARE_DEVICE_FUNC for clang++ if cxx_relaxed_constexpr is available.
* | | Fix most Doxygen warnings. Also add links to stable documentation from ↵Gravatar Christoph Hertzberg2018-10-19
| | | | | | | | | | | | | | | | | | | | | unsupported modules (by using the corresponding Doxytags file). Manually grafted from d107a371c61b764c73fd1570b1f3ed1c6400dd7e
| * | Merged eigen/eigen into defaultGravatar Rasmus Munk Larsen2018-10-19
| |\ \ | |/ / |/| |
* | | bug #1606: Explicitly set the standard before ↵Gravatar Christoph Hertzberg2018-10-19
| | | | | | | | | | | | | | | | | | | | | find_package(StandardMathLibrary). Also replace EIGEN_COMPILER_SUPPORT_CXX11 in favor of EIGEN_COMPILER_SUPPORT_CPP11. Grafted manually from a4afa90d161faab385a77f0e2764fb13ff3b9484
| * | Only set EIGEN_CONSTEXPR_ARE_DEVICE_FUNC for clang++ if ↵Gravatar Rasmus Munk Larsen2018-10-18
|/ / | | | | | | cxx_relaxed_constexpr is available.
* / Fix GPU build due to gpu_assert not always being defined.Gravatar Rasmus Munk Larsen2018-10-18
|/
* fix typo in docGravatar Gael Guennebaud2018-10-17
|
* Move from rvalue arguments in ThreadPool enqueue* methodsGravatar Eugene Zhulenev2018-10-16
|
* Reduce thread scheduling overhead in parallelForGravatar Eugene Zhulenev2018-10-16
|
* Merged in ezhulenev/eigen-02 (pull request PR-528)Gravatar Rasmus Munk Larsen2018-10-16
|\ | | | | | | | | | | [TensorBlockIO] Check if it's allowed to squeeze inner dimensions Approved-by: Rasmus Munk Larsen <rmlarsen@google.com>
* | Fix float-to-double warningGravatar Gael Guennebaud2018-10-16
| |
| * Check if it's allowed to squueze inner dimensions in TensorBlockIOGravatar Eugene Zhulenev2018-10-15
| |
* | bug #1612: fix regression in "outer-vectorization" of partial reductions for ↵Gravatar Gael Guennebaud2018-10-16
| | | | | | | | PacketSize==1 (aka complex<double>)
* | Show call stack in case of failing sparse solving.Gravatar Gael Guennebaud2018-10-16
| |
* | Remove useless (and broken) resizeGravatar Gael Guennebaud2018-10-16
| |
* | Iterative solvers: unify and fix handling of multiple rhs.Gravatar Gael Guennebaud2018-10-15
| | | | | | | | m_info was not properly computed and the logic was repeated in several places.
* | DGMRES: fix null rhs, fix restart, fix m_isDeflInitialized for multiple solveGravatar Gael Guennebaud2018-10-15
|/
* relax number of iterations checks to avoid false negativesGravatar Gael Guennebaud2018-10-15
|
* mergeGravatar Gael Guennebaud2018-10-15
|\
| * Suppress unused variable compiler warning in sparse subtest 3.Gravatar Rasmus Munk Larsen2018-10-12
| |
| * Explicitly convert 0 to Scalar for custom typesGravatar Christoph Hertzberg2018-10-12
| |
generated by cgit v1.2.3 (git 2.39.1) at 2024-09-30 14:10:54 +0000