Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | update the product selection logic to use the Max* sizes | 2010-03-08 | |
| | |||
* | update the product selection logic to use the Max* sizes | 2010-03-08 | |
| | |||
* | add missing cmake directives for arch/Default | 2010-03-08 | |
| | |||
* | tests : fix compilation issues, adding <iostream> and removing | 2010-03-08 | |
| | | | | <Eigen/Array> | ||
* | * Fix #97 : Householder operations on 1x1 matrices | 2010-03-08 | |
| | | | | | * Fix VectorBlock on 1x1 "vectors" * remove useless makeTrivialHouseholder function | ||
* | * let a = foo() work when a is a row-vector xpr and foo() returns a ↵ | 2010-03-08 | |
| | | | | | | ReturnByValue col-vector * remove a few useless resize() in evalTo() implementations | ||
* | minor edit | 2010-03-07 | |
| | |||
* | merge | 2010-03-07 | |
|\ | |||
* | | needed different proxy return types for fwd,inv to work around static asserts | 2010-03-07 | |
| | | |||
* | | created FFT::fwd and FFT::inv with ReturnByValue | 2010-03-07 | |
| | | |||
| * | Reintroduced the if-clause for MSVC ei_ploadu via _loadu_. | 2010-03-07 | |
| | | |||
| * | fix compilation | 2010-03-07 | |
| | | |||
| * | bugcount--, this time trmm | 2010-03-06 | |
| | | |||
| * | stride() => inner/outerStride() | 2010-03-06 | |
| | | |||
| * | pff I introduced much too many bugs latey, count-- | 2010-03-06 | |
| | | |||
| * | fix symm | 2010-03-06 | |
| | | |||
| * | fix trsolve | 2010-03-06 | |
| | | |||
| * | fix issue #100 (fix syrk) | 2010-03-06 | |
| | | |||
| * | bugfix in gebp for 32bits x86 | 2010-03-06 | |
| | | |||
| * | #undef minor at the right place | 2010-03-06 | |
| | | |||
| * | remove the __ARM_NEON__ check there since Konstantinos said he removed it ↵ | 2010-03-06 | |
| | | | | | | | | but apparently didn't commit :) | ||
| * | * disable static alignment on QCC | 2010-03-06 | |
| | | | | | | | | * remove obsolete #error | ||
| * | * include Macros.h much earlier: since it takes care of the alignment ↵ | 2010-03-06 | |
| | | | | | | | | | | | | | | platform detection, it is needed before we do the vectorization stuff in Eigen/Core !! * kill EIGEN_DONT_ALIGN_HEAP option (one should use EIGEN_DONT_ALIGN) * rename EIGEN_DONT_ALIGN_STACK to EIGEN_DONT_ALIGN_STATICALLY. hope it's a better name. | ||
| * | merge | 2010-03-06 | |
| |\ | |||
| | * | introduce EIGEN_DONT_ALIGN_STACK (disables alignment attributes) and ↵ | 2010-03-06 | |
| | | | | | | | | | | | | | | | | | | EIGEN_DONT_ALIGN_HEAP (disables aligned malloc)... you can still use EIGEN_DONT_ALIGN to do both at once. | ||
| | * | fix copy pasted comment | 2010-03-05 | |
| | | | |||
| | * | Altivec brought up to date. Most tests pass and performance is better than ↵ | 2010-03-05 | |
| | | | | | | | | | | | | before too! | ||
| * | | Fixed line endings. | 2010-03-05 | |
| |/ | |||
| * | add a small program to bench all combinations of small products | 2010-03-05 | |
| | | |||
| * | clean a bit the bench_gemm files | 2010-03-05 | |
| | | |||
| * | add a FIXME | 2010-03-05 | |
| | | |||
| * | * dynamically adjust the number of threads | 2010-03-05 | |
| | | | | | | | | * disbale parallelisation if we already are in a parallel session | ||
| * | add an option to test ompenmp | 2010-03-05 | |
| | | |||
| * | fix openmp version for scalar types different than float | 2010-03-05 | |
| | | |||
| * | remove the 1D and 2D parallelizer, keep only the GEMM specialized one | 2010-03-05 | |
| | | |||
| * | minor cleaning | 2010-03-05 | |
| | | |||
| * | merge | 2010-03-05 | |
| |\ | |||
| | * | enable posix_memalign for QNX | 2010-03-05 | |
| | | | |||
| * | | merge | 2010-03-04 | |
| |\| | |||
| | * | merge | 2010-03-04 | |
| | |\ | |||
| | * | | make the number of registers easier to configure per architectures | 2010-03-04 | |
| | | | | |||
| * | | | merge with default branch | 2010-03-04 | |
| |\| | | |||
| | | * | Moved x()/y()/z() and w() access functions to DenseBase; they are now ↵ | 2010-03-04 | |
| | | | | | | | | | | | | | | | | available for Arrays as well. | ||
| | * | | add a minor FIXME | 2010-03-04 | |
| | |/ | |||
| | * | integer division is vectorizable on no SIMD platform, not just SSE. | 2010-03-04 | |
| | | | |||
| | * | arm_neon.h is a standard header file, fixed | 2010-03-03 | |
| | | | |||
| | * | minor cleanup | 2010-03-03 | |
| | | | |||
| | * | factorize default performance related settings to a single file | 2010-03-03 | |
| | | | | | | | | | | | | | | | included after the architecture specific files such that they can be adapted by each platform. | ||
| | * | Added initial NEON support, most tests pass however we had to use some ↵ | 2010-03-03 | |
| | | | | | | | | | | | | | | | | | | | | | | | | hackish workarounds as gcc on ARM (both CodeSourcery 4.4.1 used and experimental 4.5) fail to ensure proper alignment with __attribute__((aligned(16))). This has to be fixed upstream to remove the workarounds. | ||
| | * | cleanup/simplification in computation of matrix flags | 2010-03-03 | |
| | | |