Intel puts “millions of engineering hours” into oneAPI

Intel has launched the oneAPI “industry initiative” to deliver a unified and open programming experience to developers on any architecture.

The initiative is expected to deliver this without compromising performance and eliminating the complexity of separate code bases, multiple-programming languages, and different tools and workflows.

According to the vendor, oneAPI represents millions of Intel engineering hours in software development and marks a game-changing evolution from today’s limiting, proprietary programming approaches to an open, standards-based model for cross-architecture developer engagement and innovation.

Intel claims the ability to program across diverse architecturesis critical in supporting data-centric workloads where multiple architectures are required and will become the future norm.

oneAPI includes an industry initiative based on open specifications including a direct programming language, powerful APIs and a low-level hardware interface. This includes a cross-architecture language, Data Parallel C++ (DPC++) for direct programming, together with a set of libraries for API-based programming and a low-level interface to hardware, oneAPI Level Zero.

“The oneAPI language, DPC++ and library specifications are publicly available for use by other hardware vendors, and we will encourage them to do so,” it stated.

The other side to it it’s Intel’s beta software, which provides developers with a comprehensive portfolio of developer tools with compilers, libraries, and analysers, packaged into domain-focused toolkits.

The beta release will target first Intel Xeon Scalable processors, Intel Core processors with integrated graphics and Intel FPGAs, with additional hardware support to follow in future releases, the company stated.

Developers can download the oneAPI tools, test drive them in the Intel oneAPI DevCloud, and learn more about oneAPI here.

Intel has also announced a new category of discrete general-purpose GPUs for artificial intelligence (AI) and high performance computing (HPC) convergence.

The new category of GPUs is based on Intel’s X architecture and it’s called Ponte Vecchio.

It has been built for HPC modelling and simulation workloads and AI training. It will be manufactured on Intel’s 7nm technology and will be Intel’s first X e -based GPU optimised for HPC and AI workloads.

“HPC and AI workloads demand diverse architectures, ranging from CPUs, general-purpose GPUs and FPGAs, to more specialised deep learning NNPs which Intel demonstrated earlier this month,” said Raja Koduri, senior vice president, chief architect and GM of architecture, graphics and software at Intel.

“Simplifying our customers’ ability to harness the power of diverse computing environments is paramount, and Intel is committed to taking a software-first approach that delivers a unified and scalable abstraction for heterogeneous architectures.”