OpenSNAPI – Enabling open, data-centric computing architectures
The new world of data opens the door for higher degrees of scientific simulations which enable solving problems which were previously considered intractable, and for developing advanced deep learning engines that can be utilized to improve our lives. The data center architecture has evolved to support these activities. New technologies continue to be developed to support the migration of the data center architecture from the old CPU-centric concept to the data-centric concept. An important part of this transition has involved the creation of new compute options, including smart and programmable interconnect solutions, also referred to as DPUs (Data Processing Units) or IPUs (Infrastructure Processing Units).
DPUs are interconnect elements that include specialized In-Network Computing engines (engines that can participate in the application runtime and analyze application data as it being transferred within the data center) or generic compute cores. DPUs can be used to enhance supercomputing performance, offload security or virtualization functions, increase storage performance and more.
The combination of CPUs, GPUs, and DPUs, creates the next generation of data center and edge computing architectures. The OpenSNAPI project mission is to create a standard application programming interface (API) for accessing the compute cores on the network, and specifically on the DPU adapters. OpenSNAPI allows application developers to leverage the network compute cores in parallel to the host compute cores, for accelerating application run time, and to perform data operations closer to the data.
About OpenSNAPI
OpenSNAPI is a collaboration between industry, laboratories and academia with the goal to create a standard application programming interface (API) for accessing the compute engines on the network, and specifically on the smart network adapter. OpenSNAPI allows application developers to leverage the network compute cores in parallel to the host compute cores for accelerating application runtime, and to perform operations and processing closer to the data. OpenSNAPI is a project of the UCF Consortium.
Registration is required to access the project working group dashboard, mail list, and the workgroup WiKi. Access is limited to member organizations and their employees.
- Chairman: Steve Poole – Los Alamos National Laboratory
- Co-Chairman: Gil Bloch – NVIDIA
- Co-Chairman: Kshitij Sudan – Arm