Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Fixed the order of 2 #includes | Benoit Steiner | 2015-04-06 |
| | |||
* | Cleaned up the TensorDevice code a little bit. | Benoit Steiner | 2015-03-25 |
| | |||
* | Updated the list of include files | Benoit Steiner | 2015-01-14 |
| | |||
* | Added support for extraction of patches from images | Benoit Steiner | 2014-11-13 |
| | |||
* | Added support for static list of indices | Benoit Steiner | 2014-11-12 |
| | |||
* | Added support for tensor references | Benoit Steiner | 2014-10-28 |
| | |||
* | Made the blocking computation aware of the l3 cache | Benoit Steiner | 2014-10-15 |
| | | | | Also optimized the blocking parameters to take into account the number of threads used for a computation | ||
* | Added support for promises | Benoit Steiner | 2014-10-15 |
| | | | | Started to improve multithreaded contractions | ||
* | Misc improvements and cleanups | Benoit Steiner | 2014-10-13 |
| | |||
* | Added support for patch extraction | Benoit Steiner | 2014-10-13 |
| | |||
* | Added ability to print a tensor using an iostream. | Benoit Steiner | 2014-10-10 |
| | |||
* | Added support for tensor chips | Benoit Steiner | 2014-10-10 |
| | |||
* | Improved support for CUDA devices. | Benoit Steiner | 2014-10-03 |
| | | | | Improved contractions on GPU | ||
* | Added support for tensor reductions and concatenations | Benoit Steiner | 2014-10-01 |
| | |||
* | Added support for broadcasting | Benoit Steiner | 2014-08-20 |
| | |||
* | Added support for fast integer divisions by a constant | Benoit Steiner | 2014-08-14 |
| | | | | Sped up tensor slicing by a factor of 3 by using these fast integer divisions. | ||
* | Added support for padding, stridding, and shuffling | Benoit Steiner | 2014-08-14 |
| | |||
* | Reworked the expression evaluation mechanism in order to make it possible to ↵ | Benoit Steiner | 2014-06-13 |
| | | | | | | | | efficiently compute convolutions and contractions in the future: * The scheduling of computation is moved out the the assignment code and into a new TensorExecutor class * The assignment itself is now a regular node on the expression tree * The expression evaluators start by recursively evaluating all their subexpressions if needed | ||
* | Added support for convolution and reshaping of tensors. | Benoit Steiner | 2014-06-06 |
| | |||
* | Added support for tensor contractions | Benoit Steiner | 2014-06-04 |
| | | | | | Updated expression evaluation mechanism to also compute the size of the tensor result Misc fixes and improvements. | ||
* | Vectorized the evaluation of tensor expression (using SSE, AVX, NEON, ...) | Benoit Steiner | 2014-05-16 |
| | | | | | Added the ability to parallelize the evaluation of a tensor expression over multiple cpu cores. Added the ability to offload the evaluation of a tensor expression to a GPU. | ||
* | Added support for fixed sized tensors. | Benoit Steiner | 2014-05-06 |
| | | | | Improved support for tensor expressions. | ||
* | Extended support for Tensors: | Benoit Steiner | 2014-04-28 |
| | | | | | | * Added ability to map a region of the memory to a tensor * Added basic support for unary and binary coefficient wise expressions, such as addition or square root * Provided an emulation layer to make it possible to compile the code with compilers (such as nvcc) that don't support cxx11. | ||
* | C++11/Tensor: Fix copyright headers | Christian Seiler | 2013-11-16 |
| | |||
* | CXX11/Tensor: add simple initial tensor implementation | Christian Seiler | 2013-11-14 |
This commit adds an initial implementation of a class template Tensor that allows for the storage of objects with more than two indices. Currently, only storing data and setting the object to zero for POD data types are implemented. |