Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Fix regression introduced by the previous fix for AVX512. | 2018-09-20 | |
| | | | | It brokes the complex-complex case on SSE. | ||
* | Fix gebp kernel for real+complex in case only reals are vectorized (e.g., ↵ | 2018-09-20 | |
| | | | | | | AVX512). This commit also removes "half-packet" from data-mappers: it was not used and conceptually broken anyways. | ||
* | Revert vec/y to vec*(1/y) in row-major TRSM: | 2016-12-06 | |
| | | | | | | - div is extremely costly - this is consistent with the column-major case - this is consistent with all other BLAS implementations | ||
* | Workaround a division by zero when outerstride==0 | 2016-04-13 | |
| | |||
* | Improve numerical accuracy in LLT and triangular solve by using true scalar ↵ | 2015-10-18 | |
| | | | | divisions (instead of x * (1/y)) | ||
* | Fix shadow warnings triggered by clang | 2015-06-09 | |
| | |||
* | Made the blocking computation aware of the l3 cache | 2014-10-15 | |
| | | | | Also optimized the blocking parameters to take into account the number of threads used for a computation | ||
* | Generalized the gebp apis | 2014-10-02 | |
| | |||
* | Improved the efficiency if the block-panel matrix multiplication code: the ↵ | 2014-01-02 | |
| | | | | change reduces the pressure on the L1 cache by removing the calls to gebp_traits::unpackRhs(). Instead the packetization of the rhs blocks is done on the fly in gebp_traits::loadRhs(). This adds numerous calls to pset1<ResPacket> (since we're packetizing on the fly in the inner loop) but this is more than compensated by the fact that we're decreasing the memory transfers by a factor RhsPacketSize. | ||
* | Fix "routine is both "inline" and "noinline"" warnings | 2013-02-28 | |
| | |||
* | Automatic relicensing to MPL2 using Keirs script. Manual fixup follows. | 2012-07-13 | |
| | |||
* | avoid dynamic allocation for fixed size triangular solving | 2012-06-12 | |
| | |||
* | Get rid of include directives inside namespace blocks (bug #339). | 2012-04-15 | |
| | |||
* | bug #352:properly cast constants | 2011-12-09 | |
| | |||
* | protect calls to min and max with parentheses to make Eigen compatible with ↵ | 2011-07-21 | |
| | | | | | | | default windows.h (transplanted from 49b6e9143e1d74441924c0c313536e263e12a55c ) | ||
* | improve computation of the sub panel width | 2011-03-24 | |
| | |||
* | improve performance of trsm | 2011-03-24 | |
| | |||
* | fix memory leak when a custom scalar throw an exception | 2011-03-19 | |
| | |||
* | bug #86 : use internal:: namespace instead of ei_ prefix | 2010-10-25 | |
| | |||
* | fix declaration of pack_lhs in trsm | 2010-07-20 | |
| | |||
* | fix lhs packing in the case of real * complex products | 2010-07-19 | |
| | |||
* | * fix a couple of remaining issues with previous commit, | 2010-07-19 | |
| | | | | * merge ei_product_blocking_traits into ei_gepb_traits | ||
* | matrix product: move the alpha factor to gebp instead of the packing, | 2010-07-12 | |
| | | | | clean some temporaries, etc. | ||
* | compilation fix | 2010-07-08 | |
| | |||
* | support for real * complex matrix product - step 1 (works for some special ↵ | 2010-07-07 | |
| | | | | cases) | ||
* | add support for vectorized conjugated products | 2010-07-06 | |
| | |||
* | email change | 2010-06-24 | |
| | |||
* | fix computation of blocking sizes for small triangular matrices | 2010-06-24 | |
| | |||
* | * makes all product use the new API to set the blocking sizes | 2010-06-22 | |
| | | | | * fix an issue preventing multithreading (now Dynamic = -1 ...) | ||
* | change the value of Dynamic to -1, since the index type is now configurable. | 2010-06-11 | |
| | | | | remove EIGEN_ENUM_MIN/MAX, implement new macros instead | ||
* | the Index types change. | 2010-05-30 | |
| | | | | As discussed on the list (too long to explain here). | ||
* | fix trsolve | 2010-03-06 | |
| | |||
* | significant speedup in the matrix-matrix products | 2010-02-23 | |
| | |||
* | remove the Triangular suffix to Upper, Lower, UnitLower, etc, | 2010-01-07 | |
| | | | | and remove the respective bit flags | ||
* | faster trsm kernel and fix a couple of issues | 2009-07-31 | |
| | |||
* | add explicit "on the right" triangular solving, | 2009-07-30 | |
| | | | | => no temporary when the rhs/unknows is row major | ||
* | trmm is now working in all storage order configurations | 2009-07-27 | |
| | |||
* | finalize trsm: works in all situations, and it is now used by solve() and ↵ | 2009-07-26 | |
| | | | | solveInPlace() | ||
* | ok, now trsm works very well for upper triangular matrices | 2009-07-26 | |
| | | | | | | TODO: link it with the meta triangular_solve_selector and handle the case where the rhs is row major by copying it to a col-major temporary + handle right solving: X = B * M^-1 | ||
* | The new trsm is working very very well (read very fast) for | 2009-07-25 | |
| | | | | | lower triangular matrix and row or col major lhs. TODO: handle upper triangular and row major rhs cases | ||
* | add WIP trsm | 2009-07-24 | |