Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Support manually disabling exceptionsHEADmaster | Benjamin Barenblat | 2021-07-07 |
| | | | | | Rename EIGEN_EXCEPTIONS to EIGEN_USE_EXCEPTIONS, and allow disabling exceptions with -DEIGEN_USE_EXCEPTIONS=0. | ||
* | [SYCL] Rebasing the SYCL support branch on top of the Einge upstream master ↵ | Mehdi Goli | 2019-11-28 |
| | | | | | | | | | | | | | | | | | | | | | | branch. * Unifying all loadLocalTile from lhs and rhs to an extract_block function. * Adding get_tensor operation which was missing in TensorContractionMapper. * Adding the -D method missing from cmake for Disable_Skinny Contraction operation. * Wrapping all the indices in TensorScanSycl into Scan parameter struct. * Fixing typo in Device SYCL * Unifying load to private register for tall/skinny no shared * Unifying load to vector tile for tensor-vector/vector-tensor operation * Removing all the LHS/RHS class for extracting data from global * Removing Outputfunction from TensorContractionSkinnyNoshared. * Combining the local memory version of tall/skinny and normal tensor contraction into one kernel. * Combining the no-local memory version of tall/skinny and normal tensor contraction into one kernel. * Combining General Tensor-Vector and VectorTensor contraction into one kernel. * Making double buffering optional for Tensor contraction when local memory is version is used. * Modifying benchmark to accept custom Reduction Sizes * Disabling AVX optimization for SYCL backend on the host to allow SSE optimization to the host * Adding Test for SYCL * Modifying SYCL CMake | ||
* | [SYCL] : | Mehdi Goli | 2019-07-01 |
| | | | | | | | * Modifying TensorDeviceSYCL to use `EIGEN_THROW_X`. * Modifying TensorMacro to use `EIGEN_TRY/CATCH(X)` macro. * Modifying TensorReverse.h to use `EIGEN_DEVICE_REF` instead of `&`. * Fixing the SYCL device macro in SpecialFunctionsImpl.h. | ||
* | [SYCL] This PR adds the minimum modifications to the Eigen unsupported ↵ | Mehdi Goli | 2019-06-28 |
| | | | | | | | | | | module required to run it on devices supporting SYCL. * Abstracting the pointer type so that both SYCL memory and pointer can be captured. * Converting SYCL virtual pointer to SYCL device memory in Eigen evaluator class. * Binding SYCL placeholder accessor to command group handler by using bind method in Eigen evaluator node. * Adding SYCL macro for controlling loop unrolling. * Modifying the TensorDeviceSycl.h and SYCL executor method to adopt the above changes. | ||
* | Fix typos found using codespell | Gael Guennebaud | 2018-06-07 |
| | |||
* | Changes required for new ComputeCpp CE version. | Mehdi Goli | 2017-09-18 |
| | |||
* | Merged in mehdi_goli/opencl/SYCLAlignAllocator (pull request PR-7) | Benoit Steiner | 2017-05-26 |
|\ | | | | | | | Fixing SYCL alignment issue required by TensorFlow. | ||
| * | Applying Ronnan's comments. | Mehdi Goli | 2017-05-26 |
| | | |||
| * | Applying Benoit's comment;removing dead code. | Mehdi Goli | 2017-05-25 |
| | | |||
| * | Fixing SYCL alignment issue required by TensorFlow. | Mehdi Goli | 2017-05-22 |
| | | |||
* | | Fixing suported device list. | Mehdi Goli | 2017-05-22 |
|/ | |||
* | Introduces align allocator for SYCL buffer | Luke Iwanski | 2017-03-20 |
| | |||
* | 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 | ||
* | Use name to distinguish name instead of the vendor | Luke Iwanski | 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. | ||
* | 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. | ||
* | Reducing warnings in Sycl backend. | Mehdi Goli | 2017-02-01 |
| | |||
* | Fixing the buffer type in memcpy. | Mehdi Goli | 2017-01-30 |
| | |||
* | Allows AMD APU | Luke Iwanski | 2017-01-23 |
| | |||
* | Reverting back to the previous TensorDeviceSycl.h as the total number of ↵ | Mehdi Goli | 2017-01-20 |
| | | | | buffer is not enough for tensorflow. | ||
* | Removing unused variables | Mehdi Goli | 2017-01-19 |
| | |||
* | Adding non-deferrenciable pointer track for ComputeCpp backend; Adding ↵ | Mehdi Goli | 2017-01-19 |
| | | | | TensorConvolutionOp for ComputeCpp; fixing typos. modifying TensorDeviceSycl to use the LegacyPointer class. | ||
* | Reverting asynchronous exec to Synchronous exec regarding random race condition. | Mehdi Goli | 2016-12-22 |
| | |||
* | Merged eigen/eigen into default | Benoit Steiner | 2016-12-16 |
|\ | |||
| * | Fixed memcpy, memcpyHostToDevice and memcpyDeviceToHost for Sycl. | Benoit Steiner | 2016-12-16 |
| | | |||
* | | Converting all parallel for lambda to functor in order to prevent kernel ↵ | Mehdi Goli | 2016-12-16 |
|/ | | | | duplication name error; adding tensorConcatinationOp backend for sycl. | ||
* | Adding asynchandler to sycl queue as lack of it can cause undefined behaviour. | Mehdi Goli | 2016-12-15 |
| | |||
* | Adding asynchronous execution as it improves the performance. | Mehdi Goli | 2016-12-14 |
| | |||
* | Adding tensor contraction operation backend for Sycl; adding test for ↵ | Mehdi Goli | 2016-12-14 |
| | | | | contractionOp sycl backend; adding temporary solution to prevent memory leak in buffer; cleaning up cxx11_tensor_buildins_sycl.h | ||
* | Adding sycl backend for TensorPadding.h; disbaling __unit128 for sycl in ↵ | Mehdi Goli | 2016-12-01 |
| | | | | TensorIntDiv.h; disabling cashsize for sycl in tensorDeviceDefault.h; adding sycl backend for StrideSliceOP ; removing sycl compiler warning for creating an array of size 0 in CXX11Meta.h; cleaning up the sycl backend code. | ||
* | Moved the MemCopyFunctor back to TensorSyclDevice since it's the only caller ↵ | Benoit Steiner | 2016-11-30 |
| | | | | and it makes TensorFlow compile again | ||
* | Added the deallocate_all() method back | Benoit Steiner | 2016-11-30 |
| | |||
* | Added EIGEN_STRONG_INLINE to get_sycl_supported_device(). | Luke Iwanski | 2016-11-30 |
| | |||
* | Adding TensorShuffling backend for sycl; adding TensorReshaping backend for ↵ | Mehdi Goli | 2016-11-29 |
| | | | | sycl; cleaning up the sycl backend. | ||
* | Fixing LLVM error on TensorMorphingSycl.h on GPU; fixing int64_t crash for ↵ | Mehdi Goli | 2016-11-25 |
| | | | | tensor_broadcast_sycl on GPU; adding get_sycl_supported_devices() on syclDevice.h. | ||
* | Removing unsupported device from test case; cleaning the tensor device sycl. | Mehdi Goli | 2016-11-23 |
| | |||
* | Made the QueueInterface thread safe | Benoit Steiner | 2016-11-20 |
| | |||
* | Merged eigen/eigen into default | Benoit Steiner | 2016-11-20 |
|\ | |||
| * | Fixed a typo | Benoit Steiner | 2016-11-20 |
| | | |||
| * | Fixed merge conflicts | Benoit Steiner | 2016-11-19 |
| | | |||
* | | Made it possible to check the state of a sycl device without synchronization | Benoit Steiner | 2016-11-19 |
|/ | |||
* | Added the ability to run test exclusively OpenCL devices that are listed by ↵ | Benoit Steiner | 2016-11-18 |
| | | | | sycl::device::get_devices(). | ||
* | Cleaned up the sycl device code | Benoit Steiner | 2016-11-18 |
| | |||
* | adding Benoit changes on the TensorDeviceSycl.h | Mehdi Goli | 2016-11-18 |
| | |||
* | Modifying TensorDeviceSycl.h to always create buffer of type uint8_t and ↵ | Mehdi Goli | 2016-11-18 |
| | | | | convert them to the actual type at the execution on the device; adding the queue interface class to separate the lifespan of sycl queue and buffers,created for that queue, from Eigen::SyclDevice; modifying sycl tests to support the evaluation of the results for both row major and column major data layout on all different devices that are supported by Sycl{CPU; GPU; and Host}. | ||
* | Added a way to detect errors generated by the opencl device from the host | Benoit Steiner | 2016-11-17 |
| | |||
* | Cleanup | Benoit Steiner | 2016-11-17 |
| | |||
* | Created a test to check that the sycl runtime can successfully report errors ↵ | Benoit Steiner | 2016-11-17 |
| | | | | | | (like ivision by 0). Small cleanup |