Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
| | * | Require at least MPFR version 2.3.0, because we use mpfr_signbit. | 2010-07-19 | ||
| | | | | | | | | | | | | Code in FindMPFR.cmake is taken from FindEigen2.cmake . | |||
| | * | add support for determinant on empty matrix | 2010-07-19 | ||
| | | | ||||
| | * | add a small bench demoing the possibilities of a direct 3x3 eigen decomposition | 2010-07-18 | ||
| | | | ||||
| | * | fix compilation of ei_tridiagonalization_inplace_selector for 1x1 matrix | 2010-07-18 | ||
| | | | ||||
| | * | finish/fix level1 blas, all test pass | 2010-07-17 | ||
| | | | ||||
| | * | fix level3 blas: it now passes all computational tests | 2010-07-17 | ||
| | | | ||||
| | * | fix hemm to not use the imaginary part of the diagonal entries | 2010-07-17 | ||
| | | | ||||
| | * | fix a couple a issue with blas (new TRMM api, and enforece column major) | 2010-07-16 | ||
| | | | ||||
| | * | fix compilation of blas lib | 2010-07-16 | ||
| | | | ||||
| | * | re-enable writing to reversed objects | 2010-07-16 | ||
| | | | ||||
| | * | fix for empty matrices | 2010-07-16 | ||
| | | | ||||
| | * | disable the optimized 3x3 path for complexes which was not working at all | 2010-07-16 | ||
| | | | ||||
| | * | fix bad fuzzy comparison in 3x3 tridiagonalization | 2010-07-16 | ||
| | | | ||||
| | * | fix sum()/prod() on empty matrix making sure this does not affect fixed ↵ | 2010-07-16 | ||
| | | | | | | | | | | | | sized object, extend related unit tests including partial reduction | |||
| | * | MPRealSupport was missing | 2010-07-15 | ||
| | | | ||||
| | * | merge | 2010-07-15 | ||
| | |\ | ||||
| | * | | add support for strictly triangular matrix in trmm though it is not really ↵ | 2010-07-15 | ||
| | | | | | | | | | | | | | | | | useful | |||
| | | * | add a support module for MPFR C++ with basic unit testing | 2010-07-15 | ||
| | | | | ||||
| | | * | merge | 2010-07-15 | ||
| | | |\ | | | |/ | | |/| | ||||
| | * | | fix compilation for non trivial types | 2010-07-14 | ||
| | | | | ||||
| | * | | merge | 2010-07-14 | ||
| | |\ \ | ||||
| | * | | | use dummy_precision by default instead of 0 | 2010-07-14 | ||
| | | | | | ||||
| | * | | | fix ei_aligned_delete for null pointers and non trivial dtors | 2010-07-14 | ||
| | | | | | ||||
| | | * | | Tutorial page 4: add some text, diversify examples. | 2010-07-14 | ||
| | | | | | | | | | | | | | | | | | | | | | | | | | Use \verbinclude for output text to disable syntax highlighting. Give tables consistent look. | |||
| | | | * | add a bench for quaternion multiplication | 2010-07-13 | ||
| | | | | | ||||
| | | | * | Implemented SSE optimized double-precision Quaternion multiplication | 2010-07-12 | ||
| | | |/ | ||||
| | | * | Change EXPAND_AS_DEFINED doxygen configuration option. | 2010-07-13 | ||
| | | | | | | | | | | | | | | | | | | | | Add macros so that MatrixBase::cwiseProduct() and ArrayBase::min() are documented, and remove one macro which is no longer used. | |||
| | | * | Tutorial page 3: add more cwise operations, condense rest. | 2010-07-12 | ||
| | | | | ||||
| | | * | Tutorial page 1: Put code and output side-by-side. | 2010-07-12 | ||
| | |/ | ||||
| | * | fix doc compilation on non 32bits systems | 2010-07-11 | ||
| | | | ||||
| | * | fix unused warning | 2010-07-11 | ||
| |/ | ||||
| * | * generalize rowmajor by vector | 2010-07-10 | ||
| | | | | | | | | * fix weird compilation error when constructing a matrix with a row by matrix product | |||
| * | fix compilation: make the check_coordinates* functions const | 2010-07-10 | ||
| | | ||||
| * | let ei_pset1 use _mm_loaddup_pd. Not a significant speed improvement, but ↵ | 2010-07-09 | ||
| | | | | | | | | also not a speed regression, and replaces 3 instructions by 1 single instruction. | |||
| * | Added NEON/Complex.h, ~3.5x faster than scalar std::complex<float> | 2010-07-10 | ||
| | | | | | | | | minor fix in AltiVec Complex.h | |||
| * | disable MSVC optimization when the underlying compiler is ICC | 2010-07-09 | ||
| | | ||||
| * | move ei_conj_if to a more appropriate file | 2010-07-09 | ||
| | | ||||
| * | forgot to commit ei_p4f_FORWARD; | 2010-07-09 | ||
| | | ||||
| * | forgot to add the Complex.h include for AltiVec. | 2010-07-09 | ||
| | | ||||
| * | Altivec port of Complex.h. | 2010-07-09 | ||
| | | | | | | | | | | | | | | | | Note: For some reason g++ 4.4 is >200% slower than g++ 4.3 on altivec code. The same benchmark (bench_gemm) was tested, on the same hardware/OS (G4/Debian testing), with same CFLAGS. With some code reorganizing I managed to get some minor gain on 4.4, but I just could not reach 4.3 speed. This is most likely a bug, but I'm waiting to see if it's fixed on 4.5. I'll look into this a bit more. | |||
| * | Be consistent in how the tutorial pages link together. | 2010-07-09 | ||
| | | ||||
| * | Small changes to tutorial page 2 (matrix arithmetic): | 2010-07-09 | ||
| | | | | | | | | | | | | * slightly more extensive discussion of aliasing * layout: put example code and output side-by-side * add some links, etc | |||
| * | bench: use of Eigen/Array is deprecated + fix includes for iostream | 2010-07-09 | ||
| | | ||||
| * | Added more redux types/examples in tutorial and fixed some display issues | 2010-07-08 | ||
| | | ||||
| * | Reductions/Broadcasting/Visitor Tutorial added to index | 2010-07-08 | ||
| | | ||||
| * | Reductions/Broadcasting/Visitor Tutorial added | 2010-07-08 | ||
| | | ||||
| * | enabling aligned loads/store for complex<double> is much more tricky, | 2010-07-07 | ||
| | | | | | | | | so the temporary fix is to always perform unaligned load/store | |||
| * | mention that array = matrix is fine too | 2010-07-07 | ||
|/ | ||||
* | sync | 2010-07-07 | ||
|\ | ||||
* | | add support for complex | 2010-07-07 | ||
| | |