Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
| | | * | | | Fixing SYCL alignment issue required by TensorFlow. | Mehdi Goli | 2017-05-22 | |
| | | | | | | ||||
| | * | | | | Fixing suported device list. | Mehdi Goli | 2017-05-22 | |
| | |/ / / | ||||
| * / / / | Add support for triSYCL | a-doumoulakis | 2017-05-05 | |
| |/ / / | | | | | | | | | | | | | | | | | | | | | Eigen is now able to use triSYCL with EIGEN_SYCL_TRISYCL and TRISYCL_INCLUDE_DIR options Fix contraction kernel with correct nd_item dimension | |||
* / / / | Use scalar_sum_op and scalar_quotient_op instead of operator+ and operator/ ↵ | RJ Ryan | 2017-04-14 | |
|/ / / | | | | | | | | | | | | | | | | | | | | | | | | | | | | in MeanReducer. Improves support for std::complex types when compiling for CUDA. Expands on e2e9cdd16970914cf0a892fea5e7c4402b3ede41 and 2bda1b0d93fb627d0c500ec48b20302d44c32cb7 . | |||
* | | | Merged in benoitsteiner/opencl (pull request PR-309) | Benoit Steiner | 2017-04-05 | |
|\ \ \ | | | | | | | | | | | | | OpenCL improvements | |||
| * | | | Deleted empty line of code | Benoit Steiner | 2017-04-04 | |
| | | | | ||||
| * | | | Guard sycl specific code under a EIGEN_USE_SYCL ifdef | Benoit Steiner | 2017-04-04 | |
| | | | | ||||
| * | | | Code cleanup | Benoit Steiner | 2017-04-04 | |
| | | | | ||||
| * | | | Guard the sycl specific code with EIGEN_USE_SYCL | Benoit Steiner | 2017-04-04 | |
| | | | | ||||
| * | | | Guard the sycl specific code with a #ifdef EIGEN_USE_SYCL | Benoit Steiner | 2017-04-04 | |
| | | | | ||||
| * | | | iGate the sycl specific code under a EIGEN_USE_SYCL define | Benoit Steiner | 2017-04-04 | |
| | | | | ||||
| * | | | Fixed compilation error when sycl is enabled. | Benoit Steiner | 2017-04-04 | |
| | | | | ||||
* | | | | fix typos in the Tensor readme | Gagan Goel | 2017-03-31 | |
| |_|/ |/| | | ||||
| * | | Restored code compatibility with compilers that dont support c++11 | Benoit Steiner | 2017-03-31 | |
| | | | | | | | | | | | | Gated more sycl code under #ifdef sycl | |||
| * | | Restore the old constructors to retain compatibility with non c++11 compilers. | Benoit Steiner | 2017-03-31 | |
| | | | ||||
| * | | Gate the sycl specific code under #ifdef sycl | Benoit Steiner | 2017-03-31 | |
| | | | ||||
| * | | Fixing TensorArgMaxSycl.h; Removing warning related to the hardcoded type of ↵ | Mehdi Goli | 2017-03-28 | |
| | | | | | | | | | | | | dims to be int in Argmax. | |||
| * | | Introduces align allocator for SYCL buffer | Luke Iwanski | 2017-03-20 | |
| | | | ||||
| * | | Merged eigen/eigen into default | Benoit Steiner | 2017-03-15 | |
| |\ \ | |/ / |/| | | ||||
* | | | Silenced compilation warning | Benoit Steiner | 2017-03-15 | |
| | | | ||||
| * | | Fixes bug in get_sycl_supported_devices() that was reporting unsupported ↵ | Luke Iwanski | 2017-03-15 | |
| | | | | | | | | | | | | Intel CPU on AMD platform - causing timeouts in that configuration | |||
* | | | Made the reduction code compile with cuda-clang | Benoit Steiner | 2017-03-14 | |
| | | | ||||
| * | | Adding synchronisation to convolution kernel for sycl backend. | Mehdi Goli | 2017-03-13 | |
| | | | ||||
* | | | Get rid of Init(). | Rasmus Munk Larsen | 2017-03-10 | |
| | | | ||||
* | | | Use C++11 ctor forwarding to simplify code a bit. | Rasmus Munk Larsen | 2017-03-10 | |
| | | | ||||
* | | | Make the non-blocking threadpool more flexible and less wasteful of CPU ↵ | Rasmus Munk Larsen | 2017-03-09 | |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | cycles for high-latency use-cases. * Adds a hint to ThreadPool allowing us to turn off spin waiting. Currently each reader and record yielder op in a graph creates a threadpool with a thread that spins for 1000 iterations through the work stealing loop before yielding. This is wasteful for such ops that process I/O. * This also changes the number of iterations through the steal loop to be inversely proportional to the number of threads. Since the time of each iteration is proportional to the number of threads, this yields roughly a constant spin time. * Implement a separate worker loop for the num_threads == 1 case since there is no point in going through the expensive steal loop. Moreover, since Steal() calls PopBack() on the victim queues it might reverse the order in which ops are executed, compared to the order in which they are scheduled, which is usually counter-productive for the types of I/O workloads the single thread pools tend to be used for. * Store num_threads in a member variable for simplicity and to avoid a data race between the thread creation loop and worker threads calling threads_.size(). | |||
| * | | Use name to distinguish name instead of the vendor | Luke Iwanski | 2017-03-08 | |
| | | | ||||
* | | | bug #1401: fix compilation of "cond ? x : -x" with x an AutoDiffScalar | Gael Guennebaud | 2017-03-08 | |
| |/ |/| | ||||
| * | Adding sycl Benchmarks. | Mehdi Goli | 2017-03-08 | |
| | | ||||
| * | Fixing potential race condition on sycl device. | Mehdi Goli | 2017-03-07 | |
| | | ||||
| * | Adding TensorIndexTuple and TensorTupleReduceOP backend (ArgMax/Min) for ↵ | Mehdi Goli | 2017-03-07 | |
| | | | | | | | | sycl; fixing the address space issue for const TensorMap; converting all discard_write to write due to data missmatch. | |||
* | | Made the Tensor code compile with clang 3.9 | Benoit Steiner | 2017-03-02 | |
| | | ||||
* | | Silenced a couple of compilation warnings | Benoit Steiner | 2017-03-01 | |
| | | ||||
* | | Silenced clang compilation warning. | Benoit Steiner | 2017-02-28 | |
| | | ||||
* | | Made the TensorStorage class compile with clang 3.9 | Benoit Steiner | 2017-02-28 | |
| | | ||||
| * | Adding sycl backend for TensorCustomOp; fixing the partial lhs modification ↵ | Mehdi Goli | 2017-02-28 | |
| | | | | | | | | issue on sycl when the rhs is TensorContraction, reduction or convolution; Fixing the partial modification for memset when sycl backend is used. | |||
* | | Fix typo. | Gael Guennebaud | 2017-02-28 | |
| | | ||||
| * | Merged eigen/eigen into default | Benoit Steiner | 2017-02-26 | |
| |\ | |/ |/| | ||||
| * | Adding TensorVolumePatchOP.h for sycl | Mehdi Goli | 2017-02-24 | |
| | | ||||
| * | Converting fixed float type into template type for TensorContraction. | Mehdi Goli | 2017-02-24 | |
| | | ||||
| * | Adding Sycl Backend for TensorGenerator.h. | Mehdi Goli | 2017-02-22 | |
| | | ||||
* | | bug #1380: for Map<> as input of matrix exponential | Gael Guennebaud | 2017-02-20 | |
| | | ||||
| * | Adding Sycl backend for TensorImagePatchOP.h; adding Sycl backend for ↵ | Mehdi Goli | 2017-02-20 | |
| | | | | | | | | TensorInflation.h. | |||
* | | Silent warning. | Gael Guennebaud | 2017-02-20 | |
| | | ||||
* | | Fix compilation. | Gael Guennebaud | 2017-02-18 | |
| | | ||||
* | | Size indices are signed. | Benoit Steiner | 2017-02-16 | |
| | | ||||
| * | Adding TensorLayoutSwapOp for sycl. | Mehdi Goli | 2017-02-15 | |
| | | ||||
| * | Adding TensorPatch.h for sycl backend. | Mehdi Goli | 2017-02-15 | |
|/ | ||||
* | Adding TensorChippingOP for sycl backend; fixing the index value in the ↵ | Mehdi Goli | 2017-02-13 | |
| | | | | verification operation for cxx11_tensorChipping.cpp test | |||
* | Pulled latest updates from upstream | Benoit Steiner | 2017-02-10 | |
|\ |