Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Disable usage of SSE3 _mm_hadd_ps that is extremely slow. | Gael Guennebaud | 2016-11-22 |
| | |||
* | Optimize predux<Packet4d> (AVX) | Gael Guennebaud | 2016-11-22 |
| | |||
* | Disable usage of SSE3 haddpd that is extremely slow. | Gael Guennebaud | 2016-11-22 |
| | |||
* | Enable the use of constant expressions with clang >= 3.6 | Benoit Steiner | 2016-11-20 |
| | |||
* | Fix compilation issue in mat = permutation (regression introduced in ↵ | Gael Guennebaud | 2016-11-20 |
| | | | | | | 8193ffb3d38b56c9295f204dc57dc6bac74f58aa ) | ||
* | Merged in benoitsteiner/opencl (pull request PR-253) | Benoit Steiner | 2016-11-19 |
|\ | | | | | | | OpenCL improvements | ||
* | | Enable EIGEN_HAS_C99_MATH when building with the latest version of Visual Studio | Benoit Steiner | 2016-11-18 |
| | | |||
* | | Merged in ChunW/eigen (pull request PR-252) | Gael Guennebaud | 2016-11-18 |
|\ \ | | | | | | | | | | Workaround for error in VS2012 with /clr | ||
| | * | Added isnan, isfinite and isinf for SYCL device. Plus test for that. | Luke Iwanski | 2016-11-18 |
| | | | |||
* | | | bug #1343: fix compilation regression in mat+=selfadjoint_view. | Gael Guennebaud | 2016-11-18 |
| | | | | | | | | | | | | Generic EigenBase2EigenBase assignment was incomplete. | ||
* | | | bug #1343: fix compilation regression in array = matrix_product | Gael Guennebaud | 2016-11-18 |
| | | | |||
| | * | Merged eigen/eigen into default | Benoit Steiner | 2016-11-17 |
| | |\ | |_|/ |/| | | |||
| * | | Workaround for error in VS2012 with /clr | Chun Wang | 2016-11-17 |
|/ / | |||
* | | implement float/std::complex<float> for ZVector as well, minor fixes to ZVector | Konstantinos Margaritis | 2016-11-17 |
| | | |||
| * | Specialised basic math functions for SYCL device. | Luke Iwanski | 2016-11-17 |
| | | |||
* | | bump default branch to 3.3.90 | Gael Guennebaud | 2016-11-16 |
| | | |||
* | | Optimized the computation of exp, sqrt, ceil anf floor for fp16 on Pascal GPUs | Benoit Steiner | 2016-11-16 |
|/ | |||
* | Optimize sparse<bool> && sparse<bool> to use the same path as for coeff-wise ↵ | Gael Guennebaud | 2016-11-14 |
| | | | | products. | ||
* | bump to 3.3.0 | Gael Guennebaud | 2016-11-10 |
| | |||
* | bump to 3.3-rc2 | Gael Guennebaud | 2016-11-04 |
| | |||
* | Improved AVX512 support | Benoit Steiner | 2016-11-03 |
| | |||
* | Merged eigen/eigen into default | Benoit Steiner | 2016-11-03 |
|\ | |||
| * | bug #1337: improve doc of homogeneous() and hnormalized() | Gael Guennebaud | 2016-11-03 |
| | | |||
| * | bug #1330: Cholmod supports double precision only, so let's trigger a static ↵ | Gael Guennebaud | 2016-11-03 |
| | | | | | | | | assertion if the scalar type does not match this requirement. | ||
| * | bug #1004: improve accuracy of LinSpaced for abs(low) >> abs(high). | Gael Guennebaud | 2016-11-02 |
| | | |||
| * | Add pinsertfirst function and implement pinsertlast for complex on SSE/AVX. | Gael Guennebaud | 2016-11-02 |
| | | |||
| * | Gate the code that refers to cuda fp16 primitives more thoroughly | Benoit Steiner | 2016-11-01 |
| | | |||
| * | Fix regression in X = (X*X.transpose())/s with X rectangular by deferring ↵ | Gael Guennebaud | 2016-10-26 |
| | | | | | | | | resizing of the destination after the creation of the evaluator of the source expression. | ||
| * | add a generic EIGEN_HAS_CXX11 | Gael Guennebaud | 2016-10-26 |
| | | |||
| * | Fix warning with ICC | Gael Guennebaud | 2016-10-26 |
| | | |||
| * | Fix ICC warnings | Gael Guennebaud | 2016-10-25 |
| | | |||
| * | Add missing inline keywords | Gael Guennebaud | 2016-10-25 |
| | | |||
| * | Fixed a typo | Benoit Steiner | 2016-10-25 |
| | | |||
| * | bug #1004: one more rewrite of LinSpaced for floating point numbers to ↵ | Gael Guennebaud | 2016-10-25 |
| | | | | | | | | | | | | | | | | guarantee both interpolation and monotonicity. This version simply does low+i*step plus a branch to return high if i==size-1. Vectorization is accomplished with a branch and the help of pinsertlast. Some quick benchmark revealed that the overhead is really marginal, even when filling small vectors. | ||
| * | Add a pinsertlast function replacing the last entry of a packet by a scalar. | Gael Guennebaud | 2016-10-25 |
| | | | | | | | | (useful to vectorize LinSpaced) | ||
| * | bug #1333: fix bad usage of const_cast_derived. Better use .data() for that ↵ | Gael Guennebaud | 2016-10-24 |
| | | | | | | | | purpose. | ||
| * | Cleanup ArrayWrapper and MatrixWrapper by removing redundant accessors. | Gael Guennebaud | 2016-10-24 |
| | | |||
| * | bug #1004: remove the inaccurate "sequential" path for LinSpaced, mark ↵ | Gael Guennebaud | 2016-10-24 |
| | | | | | | | | | | | | respective function as deprecated, and enforce strict interpolation of the higher range using a correction term. Now, even with floating point precision, both the 'low' and 'high' bounds are exactly reproduced at i=0 and i=size-1 respectively. | ||
| * | bug #698: rewrite LinSpaced for integer scalar types to avoid overflow and ↵ | Gael Guennebaud | 2016-10-24 |
| | | | | | | | | | | | | | | guarantee an even spacing when possible. Otherwise, the "high" bound is implicitly lowered to the largest value allowing for an even distribution. This changeset also disable vectorization for this integer path. | ||
| * | bug #1328: workaround a compilation issue with gcc 4.2 | Gael Guennebaud | 2016-10-20 |
| | | |||
| * | Fix previous merge. | Gael Guennebaud | 2016-10-14 |
| | | |||
| * | Merged in rmlarsen/eigen2 (pull request PR-232) | Gael Guennebaud | 2016-10-14 |
| |\ | | | | | | | | | | Improve performance of parallelized matrix multiply for rectangular matrices | ||
| * \ | Merged in lukier/eigen (pull request PR-234) | Benoit Steiner | 2016-10-13 |
| |\ \ | | | | | | | | | | | | | Enabling CUDA in Geometry | ||
| | * | | Fixes for min and abs after Benoit's comments, switched to numext. | Robert Lukierski | 2016-10-13 |
| | | | | |||
| * | | | Patch to allow VS2015 & CUDA 8.0 to compile with Eigen included. I'm not sure | Avi Ginsburg | 2016-10-13 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | whether to limit the check to this compiler combination (` || (EIGEN_COMP_MSVC == 1900 && __CUDACC_VER__) `) or to leave it as it is. I also don't know if this will have any affect on including Eigen in device code (I'm not in my current project). | ||
* | | | | Deleted redundant implementation of predux | Benoit Steiner | 2016-10-12 |
| | | | | |||
* | | | | Merged eigen/eigen into default | Benoit Steiner | 2016-10-12 |
|\| | | | |||
* | | | | Take advantage of AVX512 instructions whenever possible to speedup the ↵ | Benoit Steiner | 2016-10-12 |
| | | | | | | | | | | | | | | | | processing of 16 bit floats. | ||
| | * | | Fixes min() warnings. | Robert Lukierski | 2016-10-12 |
| | | | | |||
| * | | | Merged in rmlarsen/eigen (pull request PR-230) | Gael Guennebaud | 2016-10-12 |
| |\ \ \ | | | | | | | | | | | | | | | | Fix a bug in psqrt for SSE and AVX when EIGEN_FAST_MATH=1 |