Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | bug #955 - Implement a rotating kernel alternative in the 3px4 gebp path | 2015-02-18 | |
| | | | | | | | | This is substantially faster on ARM, where it's important to minimize the number of loads. This is specific to the case where all packet types are of size 4. I made my best attempt to minimize how dirty this is... opinions welcome. Eventually one could have a generic rotated kernel, but it would take some work to get there. Also, on sandy bridge, in my experience, it's not beneficial (even about 1% slower). | ||
* | Fixed template parameter. | 2015-02-18 | |
| | |||
* | merge | 2015-02-18 | |
|\ | |||
* | | Clean a bit computeProductBlockingSizes (use Index type, remove CEIL macro) | 2015-02-18 | |
| | | |||
| * | bug #958 - Allow testing specific blocking sizes | 2015-02-18 | |
|/ | | | | | | | | | | | | | | This is only a debugging/testing patch. It allows testing specific product blocking sizes, typically to study the impact on performance. Example usage: int testk, testm, testn; #define EIGEN_TEST_SPECIFIC_BLOCKING_SIZES #define EIGEN_TEST_SPECIFIC_BLOCKING_SIZE_K testk #define EIGEN_TEST_SPECIFIC_BLOCKING_SIZE_M testm #define EIGEN_TEST_SPECIFIC_BLOCKING_SIZE_N testn #include <Eigen/Core> | ||
* | Fix a regression when using OpenMP, and fix bug #714: the number of threads ↵ | 2015-02-18 | |
| | | | | might be lower than the number of requested ones | ||
* | Fix bug #945: workaround MSVC warning | 2015-02-18 | |
| | |||
* | Add missing install directives for arch/CUDA | 2015-02-18 | |
| | |||
* | Add an internal assertion in makeCompressed to catch a possible risk of ↵ | 2015-02-18 | |
| | | | | null-pointer access. | ||
* | Remove some dead stores. | 2015-02-18 | |
| | |||
* | Fix possible usage of a null pointer in CholmodSupport | 2015-02-18 | |
| | |||
* | Big 957, workaround MSVC/ICC compilation issue | 2015-02-18 | |
| | |||
* | Packet must be passed by const reference and not by value to avoid alignment ↵ | 2015-02-17 | |
| | | | | issue. | ||
* | Suppress some remaining Index conversion warnings | 2015-02-17 | |
| | |||
* | Disable __m128* wrappers when compiling with AVX and -fabi-version=4 | 2015-02-17 | |
| | |||
* | Fix compilation with GCC/AVX (workaround __m128 and __m256 being the same ↵ | 2015-02-17 | |
| | | | | type with default ABI) | ||
* | Fix compilation of Cholmod*(matrix) ctor | 2015-02-17 | |
| | |||
* | Fix compilation of int*complex with gcc | 2015-02-16 | |
| | |||
* | Fix SparseLU::signDeterminant() method, and add a SparseLU::determinant() ↵ | 2015-02-16 | |
| | | | | method. | ||
* | Add PermutationMatrix::determinant method. | 2015-02-16 | |
| | |||
* | bug #956: Fixed bug in move constructors of DenseStorage which caused ↵ | 2015-02-16 | |
| | | | | "moved-from" objects to be in an invalid state. | ||
* | Fix unused variable warning. | 2015-02-16 | |
| | |||
* | bug #897: fix regression in BiCGSTAB(mat) ctor (an all other iterative solvers). | 2015-02-16 | |
| | | | | Add respective regression unit test. | ||
* | Remove some useless typedefs | 2015-02-16 | |
| | |||
* | Doc: explain how to free allocated memory in SparseMAtrix | 2015-02-16 | |
| | |||
* | Merged in chtz/eigen-indexconversion (pull request PR-92) | 2015-02-16 | |
|\ | | | | | | | | | | | | | | | | | | | | | | | bug #877, bug #572: Get rid of Index conversion warnings, summary of changes: - Introduce a global typedef Eigen::Index making Eigen::DenseIndex and AnyExpr<>::Index deprecated (default is std::ptrdiff_t). - Eigen::Index is used throughout the API to represent indices, offsets, and sizes. - Classes storing an array of indices uses the type StorageIndex to store them. This is a template parameter of the class. Default is int. - Methods that *explicitly* set or return an element of such an array take or return a StorageIndex type. In all other cases, the Index type is used. | ||
| * | The usage of DenseIndex is deprecated, so let's replace DenseIndex by Index | 2015-02-16 | |
| | | |||
| * | Remove deprecated usage of expr::Index. | 2015-02-16 | |
| | | |||
| * | Fix many long to int conversion warnings: | 2015-02-16 | |
| | | | | | | | | | | | | - fix usage of Index (API) versus StorageIndex (when multiple indexes are stored) - use StorageIndex(val) when the input has already been check - use internal::convert_index<StorageIndex>(val) when val is potentially unsafe (directly comes from user input) | ||
* | | bug #952: Missing \endcode made doxygen fail to build ColPivHouseholderQR | 2015-02-15 | |
| | | |||
* | | Pulled latest updates from trunk | 2015-02-13 | |
|\ \ | |||
* | | | Optimized version of the sin(), exp(), log() and sqrt() function for AVX | 2015-02-13 | |
| | | | |||
| * | | bug #953 - Fix prefetches in 3px4 product kernel | 2015-02-13 | |
| | | | | | | | | | | | | This gives a 10% speedup on nexus 4 and on nexus 5. | ||
| | * | Index refactoring: StorageIndex must be used for storage only (and locally ↵ | 2015-02-13 | |
| | | | | | | | | | | | | when it make sense). In all other cases use the global Index type. | ||
| | * | Merge Index-refactoring branch with default, fix PastixSupport, remove some ↵ | 2015-02-13 | |
| | |\ | | |/ | |/| | | | | useless typedefs | ||
| * | | merge Tensor module within Eigen/unsupported and update gemv BLAS wrapper | 2015-02-12 | |
| |\ \ | |||
| * | | | update EIGEN_FAST_MATH documentation | 2015-02-12 | |
|/ / / | |||
| * | | Marked a few functions as EIGEN_DEVICE_FUNC to enable the use of tensors in ↵ | 2015-02-10 | |
| | | | | | | | | | | | | cuda kernels. | ||
* | | | merge | 2015-02-10 | |
|\ \ \ | |||
* | | | | FMA has been wrongly disabled | 2015-02-10 | |
| | | | | |||
| * | | | Added vectorized implementation of the exponential function for ARM/NEON | 2015-02-10 | |
|/ / / | |||
* | | | Fix bug #733: step by step solving is not a good example for solveWithGuess | 2015-02-10 | |
| | | | |||
* | | | Allows Lower|Upper as a template argument of CG and MINRES: in this case the ↵ | 2015-02-10 | |
| | | | | | | | | | | | | full matrix will be considered. | ||
* | | | bug #897: makes iterative sparse solvers use a Ref<SparseMatrix> instead of ↵ | 2015-02-09 | |
| | | | | | | | | | | | | a SparseMatrix pointer. This fixes usage of iterative solvers with a Map<SparseMatrix>. | ||
* | | | Make Block<SparseMatrix> inherit SparseCompressedBase in the case of an ↵ | 2015-02-09 | |
| | | | | | | | | | | | | inner-panels and fix valuePtr() innerIndexPtr() | ||
* | | | Cleaning and add more unit tests for Ref<SparseMatrix> and Map<SparseMatrix> | 2015-02-09 | |
| | | | |||
* | | | Add a Ref<SparseMatrix> specialization. | 2015-02-07 | |
| | | | |||
* | | | Add a Map<SparseMatrix> specialization. | 2015-02-07 | |
| | | | |||
* | | | Make SparseTranspose inherit SparseCompressBase when possible | 2015-02-07 | |
| | | | |||
* | | | Add a SparseCompressedBase class providing (un)compressed accessors (like ↵ | 2015-02-07 | |
| | | | | | | | | | | | | | | | | | | data()/*Stride() for dense matrices), and a CompressedAccessBit flag (similar to DirectAccessBit for dense matrices). |