aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
* Fix a bug in TensorGenerator for 1d tensorsGravatar Eugene Zhulenev2019-03-11
|
* Fix a data race in NonBlockingThreadPoolGravatar Eugene Zhulenev2019-03-11
|
* Apply SSE's pmin/pmax fix for GCC <= 5 to AVX's pmin/pmaxGravatar Gael Guennebaud2019-03-10
|
* Change license from LGPL to MPL2 with agreement from David Harmon.Gravatar Gael Guennebaud2019-03-07
|
* Merge.Gravatar Rasmus Munk Larsen2019-03-06
|\
* | Add macro EIGEN_AVOID_THREAD_LOCAL to make it possible to manually disable ↵Gravatar Rasmus Munk Larsen2019-03-06
| | | | | | | | the use of thread_local.
| * Fix placement of "#if defined(EIGEN_GPUCC)" guard region.Gravatar Rasmus Munk Larsen2019-03-06
| |\ | | | | | | | | | | | | | | | Found with -Wundefined-func-template. Author: tkoeppe@google.com
| * | Fix placement of "#if defined(EIGEN_GPUCC)" guard region.Gravatar Rasmus Munk Larsen2019-03-06
|/ / | | | | | | | | | | Found with -Wundefined-func-template. Author: tkoeppe@google.com
| * Add missing return to NonBlockingThreadPool::LocalStealGravatar Eugene Zhulenev2019-03-06
| |
| * Remove redundant steal loopGravatar Eugene Zhulenev2019-03-06
|/
* Merged in rmlarsen/eigen_threadpool (pull request PR-606)Gravatar Rasmus Larsen2019-03-06
|\ | | | | | | | | | | | | Remove EIGEN_MPL2_ONLY guards around code re-licensed from LGPL to MPL2 in https://bitbucket.org/eigen/eigen/commits/2ca1e732398ea2c506427e9031212d63e9253b96 Approved-by: Sameer Agarwal <sameeragarwal@google.com>
* \ Merged in ezhulenev/eigen-01 (pull request PR-610)Gravatar Rasmus Larsen2019-03-06
|\ \ | | | | | | | | | Block evaluation for TensorGeneratorOp
| * | Check that inner block dimension is continuousGravatar Eugene Zhulenev2019-03-05
| | |
| * | Block evaluation for TensorGeneratorOpGravatar Eugene Zhulenev2019-03-05
| | |
* | | Merged in ezhulenev/eigen-01 (pull request PR-609)Gravatar Rasmus Larsen2019-03-05
|\| | | | | | | | | | | Tune tensor contraction threadpool heuristics
* | | bug #1689 fix used-but-marked-unused warningGravatar Gael Guennebaud2019-03-05
| | |
| * | Tune tensor contraction threadpool heuristicsGravatar Eugene Zhulenev2019-03-05
|/ /
* | Add an extra check for the RunQueue size estimateGravatar Eugene Zhulenev2019-03-05
| |
* | Do not create Tensor<const T> in cxx11_tensor_forced_eval testGravatar Eugene Zhulenev2019-03-05
| |
| * Remove EIGEN_MPL2_ONLY guards around code re-licensed from LGPL to MPL2 in ↵Gravatar Rasmus Munk Larsen2019-03-05
|/ | | | https://bitbucket.org/eigen/eigen/commits/2ca1e732398ea2c506427e9031212d63e9253b96
* Do not initialize invalid fast_strides in TensorGeneratorOpGravatar Eugene Zhulenev2019-03-04
|
* Add tiled evaluation for TensorForcedEvalOpGravatar Eugene Zhulenev2019-03-04
|
* Use fast divisors in TensorGeneratorOpGravatar Eugene Zhulenev2019-03-04
|
* Enable construction of Ref<VectorType> from a runtime vector.Gravatar Gael Guennebaud2019-03-03
|
* Fully qualify Eigen::internal::aligned_freeGravatar Sam Hasinoff2019-03-02
| | | | | | | This helps avoids a conflict on certain Windows toolchains (potentially due to some ADL name resolution bug) in the case where aligned_free is defined in the global namespace. In any case, tightening this up is harmless.
* bug #1629: fix compilation of PardisoSupport (regression introduced in ↵Gravatar Gael Guennebaud2019-03-02
| | | | | | changeset a7842daef2c82a9be200dff54d455f6d4a0b199c )
* Do not keep latex logsGravatar Bernhard M. Wiedemann2019-02-27
| | | | | to make package builds more reproducible. See https://reproducible-builds.org/ for why this is good.
* Fix specialization for conjugate on non-complex types in TensorBase.h.Gravatar Rasmus Munk Larsen2019-03-01
|
* Consistently use EIGEN_BLAS_FUNC in BLAS.Gravatar Sameer Agarwal2019-02-27
| | | | | | | | | | Previously, for a few functions, eithe BLASFUNC or, EIGEN_CAT was being used. This change uses EIGEN_BLAS_FUNC consistently everywhere. Also introduce EIGEN_BLAS_FUNC_SUFFIX, which by default is equal to "_", this allows the user to inject a new suffix as needed.
* Merged in rmlarsen/eigen_threadpool (pull request PR-596)Gravatar Rasmus Larsen2019-02-26
|\ | | | | | | | | | | Improve EventCount used by the non-blocking threadpool. Approved-by: Gael Guennebaud <g.gael@free.fr>
* \ Merged in rmlarsen/eigen (pull request PR-597)Gravatar Rasmus Larsen2019-02-25
|\ \ | | | | | | | | | | | | | | | Change licensing of OrderingMethods/Amd.h and SparseCholesky/SimplicialCholesky_impl.h from LGPL to MPL2. Approved-by: Gael Guennebaud <g.gael@free.fr>
* | | Enable SSE vectorization of Quaternion and cross3() with AVXGravatar Gael Guennebaud2019-02-23
| | |
| | * Improve EventCount used by the non-blocking threadpool.Gravatar Rasmus Munk Larsen2019-02-22
| |/ |/| | | | | | | | | | | | | | | | | The current algorithm requires threads to commit/cancel waiting in order they called Prewait. Spinning caused by that serialization can consume lots of CPU time on some workloads. Restructure the algorithm to not require that serialization and remove spin waits from Commit/CancelWait. Note: this reduces max number of threads from 2^16 to 2^14 to leave more space for ABA counter (which is now 22 bits). Implementation details are explained in comments.
* | fix alignment in ploadquadGravatar Gael Guennebaud2019-02-22
| |
| * Change licensing of OrderingMethods/Amd.h and ↵Gravatar Rasmus Munk Larsen2019-02-22
|/ | | | SparseCholesky/SimplicialCholesky_impl.h from LGPL to MPL2. Google LLC executed a license agreement with the author of the code from which these files are derived to allow the Eigen project to distribute the code and derived works under MPL2.
* update wrt recent changesGravatar Gael Guennebaud2019-02-21
|
* AVX512: implement faster ploadquad<Packet16f> thus speeding up GEMMGravatar Gael Guennebaud2019-02-21
|
* bug #1674: workaround clang fast-math aggressive optimizationsGravatar Gael Guennebaud2019-02-22
|
* Fix compilation on ARM.Gravatar Gael Guennebaud2019-02-22
|
* bug #1684: add simplified regression test for respective clang's bug (this ↵Gravatar Gael Guennebaud2019-02-22
| | | | also reveal the same bug in Apples's clang)
* Speed up col/row-wise reverse for fixed size matrices by propagating ↵Gravatar Gael Guennebaud2019-02-21
| | | | compile-time sizes.
* Add a few missing packet ops: cmp_eq for NEON. pfloor for GPU.Gravatar Rasmus Munk Larsen2019-02-21
|
* Add fully generic Vector<Type,Size> and RowVector<Type,Size> type aliases.Gravatar Gael Guennebaud2019-02-20
|
* Update documentation of Matrix and Array type aliases.Gravatar Gael Guennebaud2019-02-20
|
* Enable documentation of Array's typedefsGravatar Gael Guennebaud2019-02-20
|
* Protect c++11 type alias with Eigen's macro, and add respective unit test.Gravatar Gael Guennebaud2019-02-20
|
* Merged in ra_bauke/eigen (pull request PR-180)Gravatar Gael Guennebaud2019-02-20
|\ | | | | | | | | | | alias template for matrix and array classes, see also bug #864 Approved-by: Heiko Bauke <heiko.bauke@mail.de>
* | Fix compilation with gcc and remove TR1 stuff.Gravatar Gael Guennebaud2019-02-20
| |
* | Update documentation regarding alignment issue.Gravatar Gael Guennebaud2019-02-20
| |
* | bug #1409: make EIGEN_MAKE_ALIGNED_OPERATOR_NEW* macros empty in c++17 mode:Gravatar Gael Guennebaud2019-02-20
| | | | | | | | | | - this helps clang 5 and 6 to support alignas in STL's containers. - this makes the public API of our (and users) classes cleaner
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-03 23:01:06 +0000