Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
| * | Remove the rotating kernel. It was only useful on some ARM CPUs (Qualcomm ↵ | 2016-05-24 | ||
| | | | | | | | | Krait) that are not as ubiquitous today as they were when I introduced it. | |||
| * | Don't optimize the processing of the last rows of a matrix matrix product in ↵ | 2016-05-23 | ||
| | | | | | | | | cases that violate the assumptions made by the optimized code path. | |||
* | | Pulled latest updates from upstream | 2016-04-29 | ||
|\| | ||||
| * | Made the index type a template parameter to evaluateProductBlockingSizes | 2016-04-27 | ||
| | | | | | | | | Use numext::mini and numext::maxi instead of std::min/std::max to compute blocking sizes. | |||
| * | Deleted extraneous comma. | 2016-04-15 | ||
| | | ||||
| * | Improved the matrix multiplication blocking in the case where mr is not a ↵ | 2016-04-15 | ||
| | | | | | | | | power of 2 (e.g on Haswell CPUs). | |||
| * | Fix trmv for mixing types. | 2016-04-15 | ||
| | | ||||
| * | Added ability to access the cache sizes from the tensor devices | 2016-04-14 | ||
| | | ||||
| * | Workaround a division by zero when outerstride==0 | 2016-04-13 | ||
| | | ||||
* | | Pull latest updates from upstream | 2016-04-11 | ||
|\| | ||||
| * | Cleanup obsolete assign_scalar_eig2mkl helper. | 2016-04-11 | ||
| | | ||||
| * | Remove all references to MKL in BLAS wrappers. | 2016-04-11 | ||
| | | ||||
| * | Fix long to int conversion in BLAS API. | 2016-04-11 | ||
| | | ||||
| * | Silent unused warning. | 2016-04-11 | ||
| | | ||||
| * | Relax dependency on MKL for EIGEN_USE_BLAS | 2016-04-11 | ||
| | | ||||
| * | Removed executable bit from header files | 2016-03-23 | ||
| | | ||||
| * | bug #1161: fix division by zero for huge scalar types | 2016-02-03 | ||
| | | ||||
* | | Updated the matrix multiplication code to make it compile with AVX512 enabled. | 2016-02-01 | ||
| | | ||||
| * | Fix tri = complex * real product, and add respective unit test. | 2016-01-27 | ||
| | | ||||
| * | Remove dead code. | 2016-01-26 | ||
| | | ||||
| * | Re-enable blocking on rows in non-l3 blocking mode. | 2016-01-26 | ||
| | | ||||
| * | Make sure that micro-panel-size is smaller than blocking sizes (otherwise we ↵ | 2016-01-26 | ||
| | | | | | | | | might get a buffer overflow) | |||
| * | Make sure that block sizes are smaller than input matrix sizes. | 2016-01-26 | ||
| | | ||||
| * | bug #51: add block preallocation mechanism to selfadjoit*matrix product. | 2016-01-25 | ||
| | | ||||
| * | bug #51: make general_matrix_matrix_triangular_product use L3-blocking ↵ | 2016-01-25 | ||
| | | | | | | | | helper so that general symmetric rank-updates and general-matrix-to-triangular products do not trigger dynamic memory allocation for fixed size matrices. | |||
| * | bug #1151: remove useless critical section | 2016-01-21 | ||
| | | ||||
* | | Disabled part of the matrix matrix peeling code that's incompatible with 512 ↵ | 2015-12-21 | ||
| | | | | | | | | bit registers | |||
| * | Fix compilation of MKL support. | 2015-12-11 | ||
|/ | ||||
* | Fixes internal compiler error while compiling with VC2015 Update1 x64. | 2015-12-03 | ||
| | ||||
* | Fix degenerate cases in syrk and trsm | 2015-11-30 | ||
| | ||||
* | Use a class constructor to initialize CPU cache sizes | 2015-11-20 | ||
| | | | | | | | | Using a static instance of a class to initialize the values for the CPU cache sizes guarantees thread-safe initialization of the values when using C++11. Therefore under C++11 it is no longer necessary to call Eigen::initParallel() before calling any eigen functions on different threads. | |||
* | Avoid any openmp calls if multi-threading is explicitely disabled at runtime. | 2015-10-22 | ||
| | ||||
* | Improve numerical accuracy in LLT and triangular solve by using true scalar ↵ | 2015-10-18 | ||
| | | | | divisions (instead of x * (1/y)) | |||
* | Remove dead code in selfadjoint_matrix_vector_product | 2015-10-09 | ||
| | ||||
* | Optimize a bit complex selfadjoint * vector product. | 2015-10-09 | ||
| | ||||
* | bug #1043: Avoid integer conversion sign warning | 2015-08-19 | ||
| | ||||
* | Generalize first_aligned to take the requested alignment as a template ↵ | 2015-08-06 | ||
| | | | | parameter, and add a first_default_aligned variante calling first_aligned with the requirement of the largest packet for the given scalar type. | |||
* | Enable runtime stack alignment in gemm_blocking_space. | 2015-08-06 | ||
| | ||||
* | bug #973: update macro-level control of alignement by introducing ↵ | 2015-07-29 | ||
| | | | | user-controllable EIGEN_MAX_ALIGN_BYTES and EIGEN_MAX_STATIC_ALIGN_BYTES macros. This changeset also removes EIGEN_ALIGN (replaced by EIGEN_MAX_ALIGN_BYTES>0), EIGEN_ALIGN_STATICALLY (replaced by EIGEN_MAX_STATIC_ALIGN_BYTES>0), EIGEN_USER_ALIGN*, EIGEN_ALIGN_DEFAULT (replaced by EIGEN_ALIGN_MAX). | |||
* | bug #923: fix EIGEN_USE_BLAS mode | 2015-06-23 | ||
| | ||||
* | Remove a few deprecated internal expressions | 2015-06-19 | ||
| | ||||
* | Fix shadow warnings triggered by clang | 2015-06-09 | ||
| | ||||
* | Abandon blocking size lookup table approach. Not performing as well in real ↵ | 2015-05-19 | ||
| | | | | world as in microbenchmark. | |||
* | Improved the blocking strategy to speedup multithreaded tensor contractions. | 2015-04-09 | ||
| | ||||
* | add a note on bug #992 | 2015-04-08 | ||
| | ||||
* | bug #992: don't select a 3p GEMM path with non-vectorizable scalar types, ↵ | 2015-04-07 | ||
| | | | | this hits unsupported paths in symm/triangular products code | |||
* | Only use blocking sizes LUTs for single-thread products for now | 2015-03-31 | ||
| | ||||
* | Fix computeProductBlockingSizes with m==0, and add respective unit test. | 2015-03-31 | ||
| | ||||
* | use unsigned short instead of uint16_t which doesn't exist in c++98 | 2015-03-17 | ||
| | ||||
* | Similar to cset 3589a9c115a892ea3ca5dac74d71a1526764cb38 | 2015-03-16 | ||
| | | | | , also in 2px4 kernel: actual_panel_rows computation should always be resilient to parameters not consistent with the known L1 cache size, see comment |