Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Re-add executable flags to minimize changeset. | Ville Kallioniemi | 2016-01-22 |
| | |||
* | Update to latest default branch | Ville Kallioniemi | 2016-01-21 |
|\ | |||
* \ | Make use of 32 bit ints explicit and remove executable bit from headers. | Ville Kallioniemi | 2016-01-21 |
|\ \ | |||
| | * | Pulled latest updates from trunk | Benoit Steiner | 2016-01-21 |
| | |\ | |||
| | * | | Fixed a constness bug | Benoit Steiner | 2016-01-21 |
| | | | | |||
| | | * | bug #977: avoid division by 0 in normalize() and normalized(). | Gael Guennebaud | 2016-01-21 |
| | | | | |||
| | | * | Fix compilation on old gcc+AVX | Gael Guennebaud | 2016-01-21 |
| | | | | |||
| | | * | Add numext::sqrt function to enable custom optimized implementation. | Gael Guennebaud | 2016-01-21 |
| | |/ | | | | | | | | | | | | | | | | | | | | | | This changeset add two specializations for float/double on SSE. Those are mostly usefull with GCC for which std::sqrt add an extra and costly check on the result of _mm_sqrt_*. Clang does not add this burden. In this changeset, only DenseBase::norm() makes use of it. | ||
| | * | bug #1151: remove useless critical section | Gael Guennebaud | 2016-01-21 |
| | | | |||
| | * | fix clang warnings | Jan Prach | 2016-01-20 |
| | | | | | | | | | | | | "braces around scalar initializer" | ||
| | * | Pulled latest updates from the trunk | Benoit Steiner | 2016-01-20 |
| | |\ | |||
| | * | | Small cleanup and small fix to the contraction of row major tensors | Benoit Steiner | 2016-01-20 |
| | | | | |||
| | | * | add upper|lower case in incomplete_cholesky unit test | Gael Guennebaud | 2016-01-21 |
| | | | | |||
| | * | | Reduce the register pressure exerted by the tensor mappers whenever ↵ | Benoit Steiner | 2016-01-20 |
| | |/ | | | | | | | | | | possible. This improves the performance of the contraction of a matrix with a vector by about 35%. | ||
| | * | Pulled latest updates from trunk | Benoit Steiner | 2016-01-20 |
| | |\ | |||
| | * | | bug #1149: fix Pastix*::*parm() | Gael Guennebaud | 2016-01-20 |
| | | | | |||
| | * | | bug #1148: silent Pastix by default | Gael Guennebaud | 2016-01-20 |
| | | | | |||
| | * | | bug #1145: fix PastixSupport LLT/LDLT wrappers (missing resize prior to ↵ | Gael Guennebaud | 2016-01-20 |
| | | | | | | | | | | | | | | | | calls to selfAdjointView) | ||
| | * | | bug #1147: fix compilation of PastixSupport | Gael Guennebaud | 2016-01-20 |
| | | | | |||
| | * | | Add static assertion to y(), z(), w() accessors | Gael Guennebaud | 2016-01-20 |
| | | | | |||
| * | | | Remove executable bit from header files | Ville Kallioniemi | 2016-01-19 |
| | | | | |||
| * | | | Use explicitly 32 bit integer types in constructors. | Ville Kallioniemi | 2016-01-19 |
|/ / / | |||
| | * | Improved the formatting of the code | Benoit Steiner | 2016-01-19 |
| |/ | |||
| * | Moved the contraction mapping code to its own file to make the code more ↵ | Benoit Steiner | 2016-01-19 |
| | | | | | | | | manageable. | ||
| * | Improved code indentation | Benoit Steiner | 2016-01-19 |
| | | |||
| * | Record whether the underlying tensor storage can be accessed directly during ↵ | Benoit Steiner | 2016-01-19 |
| | | | | | | | | the evaluation of an expression. | ||
* | | Add ctor for long | Ville Kallioniemi | 2016-01-17 |
| | | |||
| * | Fixed a race condition that could affect some reductions on CUDA devices. | Benoit Steiner | 2016-01-15 |
| | | |||
| * | Made it possible to compare tensor dimensions inside a CUDA kernel. | Benoit Steiner | 2016-01-15 |
| | | |||
| * | Use warp shuffles instead of shared memory access to speedup the inner ↵ | Benoit Steiner | 2016-01-14 |
| | | | | | | | | reduction kernel. | ||
| * | Fixed a boundary condition bug in the outer reduction kernel | Benoit Steiner | 2016-01-14 |
| | | |||
| * | Properly record the rank of reduced tensors in the tensor traits. | Benoit Steiner | 2016-01-13 |
| | | |||
| * | Trigger the optimized matrix vector path more conservatively. | Benoit Steiner | 2016-01-12 |
| | | |||
| * | Improved the performance of the contraction of a 2d tensor with a 1d tensor ↵ | Benoit Steiner | 2016-01-12 |
| | | | | | | | | by a factor of 3 or more. This helps speedup LSTM neural networks. | ||
| * | Reverted a previous change that tripped nvcc when compiling in debug mode. | Benoit Steiner | 2016-01-11 |
| | | |||
| * | Made the blas utils usable from within a cuda kernel | Benoit Steiner | 2016-01-11 |
| | | |||
| * | Silenced a few compilation warnings. | Benoit Steiner | 2016-01-11 |
| | | |||
| * | Updated the tensor traits: the alignment is not part of the Flags enum anymore | Benoit Steiner | 2016-01-11 |
| | | |||
| * | Enabled the use of fixed dimensions from within a cuda kernel. | Benoit Steiner | 2016-01-11 |
| | | |||
| * | Deleted unused variable. | Benoit Steiner | 2016-01-11 |
| | | |||
| * | Silenced a nvcc compilation warning | Benoit Steiner | 2016-01-11 |
| | | |||
| * | Silenced several compilation warnings triggered by nvcc. | Benoit Steiner | 2016-01-11 |
| | | |||
| * | Merged in jeremy_barnes/eigen/shader-model-3.0 (pull request PR-152) | Benoit Steiner | 2016-01-11 |
| |\ | | | | | | | | | | Alternative way of forcing instantiation of device kernels without causing warnings or requiring device to device kernel invocations. | ||
| * | | Fixed a bug in the dispatch of optimized reduction kernels. | Benoit Steiner | 2016-01-11 |
| | | | |||
| * | | Re-enabled the optimized reduction CUDA code. | Benoit Steiner | 2016-01-11 |
| | | | |||
| | * | Cleaned up double-defined macro from last commit | Jeremy Barnes | 2016-01-10 |
| | | | |||
| | * | Alternative way of forcing instantiation of device kernels without | Jeremy Barnes | 2016-01-10 |
| |/ | | | | | | | | | | | causing warnings or requiring device to device kernel invocations. This allows Tensorflow to work on SM 3.0 (ie, Amazon EC2) machines. | ||
| * | merge | Gael Guennebaud | 2016-01-09 |
| |\ | |||
| * | | bug #1144: fix regression in x=y+A*x (aliasing), and move ↵ | Gael Guennebaud | 2016-01-09 |
| | | | | | | | | | | | | evaluator_traits::AssumeAliasing to evaluator_assume_aliasing. | ||
| | * | Simplified the dispatch code. | Benoit Steiner | 2016-01-08 |
| | | |