This is a preview release for DNNL v2.0. The release is based on DNNL v1.1 and the release notes below include incremental changes.
- SYCL API extensions and interoperability with SYCL code
- Support for Intel DPC++ compiler and runtime
- SYCL interoperability examples
- Some f32/f16 convolutions with non-square spatial shape of filters may produce incorrect results on GPU.
- Some bf16 backward convolutions with 3D spatial and negative padding may produce segfault on CPU.
- Non-Intel GPUs are not supported. The library API allows to create a DNNL engine by index (the order of devices is determined by the SYCL runtime), and there is no check for GPU devices being non-Intel. To have more control, users can create a DNNL engine passing SYCL device and context explicitly.
- RNN primitive may hang on GPU if the number of recurrent cells is bigger than 40.
- int8 RNN may produce incorrect results on GPU.
- Backward propagation of Layer Normalization primitive produces incorrect results.
- Intel Processor Graphics Gen11 is not supported.
- When running GPU kernels that take longer than a certain time (it depends on OS and system settings) you may face a situation resulting in apparent hang of the application. Configure driver to disable this timeout and avoid hanging of DPC++ or OpenCL programs, including DNNL examples.
$ sudo bash -c 'echo N > /sys/module/i915/parameters/enable_hangcheck'
On Windows increase TdrDelay and TdrDdiDelay values using registry.
dnnl_lnx_1.90.1_cpu_gomp.tgz 5.06 MB
dnnl_lnx_1.90.1_cpu_iomp.tgz 14.5 MB
dnnl_lnx_1.90.1_cpu_tbb.tgz 12.8 MB
dnnl_mac_1.90.1_cpu_tbb.tgz 11.4 MB
dnnl_win_1.90.1_cpu_iomp.zip 12.3 MB
dnnl_win_1.90.1_cpu_tbb.zip 9.49 MB