Intel introduces GPU architecture for HPC/AI
At this week’s Intel HPC Developer Conference in Denver, Colrado, USA this week, Raja Koduri, senior vice president, chief architect, and general manager of architecture, graphics and software at Intel (pictured), introduced a new category of discrete general-purpose GPUs optimised for artificial intelligence (AI) and high performance computing (HPC) convergence.
The Ponte Vecchio general purpose GPU is based on the Xe architecture.
“HPC and AI workloads demand diverse architectures, ranging from CPUs, general-purpose GPUs and FPGAs, to more specialised deep-learning neural network processors (NNPs), which Intel demonstrated earlier this month,” said Koduri.
Ponte Vecchio is architected for HPC modeling and simulation workloads and AI training. It will be manufactured on Intel’s 7nm technology and will be Intel’s first Xe-based GPU optimised for HPC and AI workloads. Ponte Vecchio will leverage Intel’s Foveros 3D and EMIB packaging and feature high-bandwidth memory, Compute Express Link interconnect and other IP in one package.
Intel also launched the oneAPI initiative to define programming for an AI-infused, multi-architecture world. oneAPI delivers a unified and open programming experience to developers on the architecture of their choice without compromising performance and eliminating the complexity of separate code bases, multiple-programming languages, and different tools and workflows. It preserves existing software investments with support for existing languages while delivering flexibility for developers to create versatile applications.
The oneAPI specification includes a direct programming language, powerful application programming interfaces (APIs) and a low-level hardware interface. Intel’s oneAPI beta software provides developers a comprehensive portfolio of developer tools that include compilers, libraries and analysers, packaged into domain-focused toolkits. The initial oneAPI beta release targets Intel Xeon Scalable processors, Intel Core processors with integrated graphics and Intel FPGAs, with additional hardware support to follow in future releases.
Developers can download the oneAPI tools, test drive them in the Intel oneAPI DevCloud.