oneAPI Deep Neural Network Library (oneDNN) is a cross-platform open-source library for deep learning applications. The library is optimized for Intel architecture processors, Intel processor graphics, and Xe-based graphics. oneDNN has experimental support for the following architectures:
- Arm * 64-bit Architecture (AArch64)
- NVIDIA * GPU
- OpenPOWER * Power ISA (PPC64)
- IBMz * (s390x)
The binary distribution of this software is available as Intel oneAPI Deep Neural Network Library in Intel oneAPI. Binaries are pre-built for Linux, Windows and macOS.
The library is optimized for the following processors:
- Intel Atom processor with Intel SSE4.1
- 4th, 5th, 6th, 7th, and 8th generation Intel (R) Core (TM) processor
- Intel (R) Xeon (R) processor E3, E5, and E7 family (Sandy Bridge, Ivy Bridge, Haswell, Broadwell)
- Intel (R) Xeon Phi (TM) processor (Knights Landing, Knights Mill)
- Intel Xeon Scalable processor (Skylake, Cascade Lake, Cooper Lake)
- Intel Xeon Scalable processor (Sapphire Rapids)
The library is optimized for the following GPUs:
- Intel HD Graphics
- Intel UHD Graphics
- Intel Iris Plus Graphics
- Xe architecture-based Graphics (DG1 and Tiger Lake)
oneDNN accepts systems that meet the following requirements:
- Bone with Intel 64 / Arm 64 / Power / IBMz
- C ++ compiler with C ++ 11 standard support
- CMake 2.8.11 or later
- Doxygen 1.8.5 +
- Arm Compute Library for builds using Compute Library on AArch64.
Nici un comentariu inca. Fii primul!