diff options
| author |  Mehdi Goli <mehdi.goli@codeplay.com> | 2017-03-13 09:18:37 +0000 |
|---|---|---|
| committer | Mehdi Goli <mehdi.goli@codeplay.com> | 2017-03-13 09:18:37 +0000 |
| commit | f499fe9496e7c5e6f70d4bdcfb6ed9088795431a (patch) | |
| tree | 88ba4b608eb3fa92a32818c634378cbaf89fcd37 | |
| parent | 1b32a10053a942b1c6010afd719b44393b115d42 (diff) | |
Adding synchronisation to convolution kernel for sycl backend.
| -rw-r--r-- | bench/tensors/tensor_benchmarks.h | 5 | ||||
| -rw-r--r-- | unsupported/Eigen/CXX11/src/Tensor/TensorConvolutionSycl.h | 1 |
2 files changed, 6 insertions, 0 deletions
diff --git a/bench/tensors/tensor_benchmarks.h b/bench/tensors/tensor_benchmarks.h index 325026113..3a640ede4 100644 --- a/bench/tensors/tensor_benchmarks.h +++ b/bench/tensors/tensor_benchmarks.h @@ -539,6 +539,11 @@ for (int iter = 0; iter < 10; ++iter) { if (Eigen::internal::is_same<Device, Eigen::GpuDevice>::value) { device_.synchronize(); } +#elif defined(EIGEN_USE_SYCL) + if (Eigen::internal::is_same<Device, Eigen::SyclDevice>::value) { + device_.synchronize(); + } + #endif StopBenchmarkTiming(); SetBenchmarkFlopsProcessed(num_items); diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorConvolutionSycl.h b/unsupported/Eigen/CXX11/src/Tensor/TensorConvolutionSycl.h index 5db16d559..2e6021b1e 100644 --- a/unsupported/Eigen/CXX11/src/Tensor/TensorConvolutionSycl.h +++ b/unsupported/Eigen/CXX11/src/Tensor/TensorConvolutionSycl.h @@ -425,6 +425,7 @@ struct TensorEvaluator<const TensorConvolutionOp<Indices, InputArgType, KernelAr } } }); + m_device.asynchronousExec(); } EIGEN_DEVICE_FUNC EIGEN_STRONG_INLINE CoeffReturnType coeff(Index index) const |