Introducing oneAPI: A Unified, Cross-Architecture Performance Programming Model

The drive for compute innovation is as old as computing itself, with each advancement built upon what came before. In 2019 and 2020, a primary focus of next-gen compute innovation is enabling increasingly complex workloads to run on multiple architectures. CPUs and GPUs for sure. But also FPGAs and a myriad of AI accelerators.

The biggest challenge? Programming.

Because historically, writing and deploying code for CPUs and accelerators has required different languages, libraries, and tools. Meaning each hardware platform required a separate software investment of time, resources, and/or money.

The oneAPI initiative was created to solve this problem.

Join Kent Moffat, software specialist and Intel senior product manager, to find out how, including:

  • An overview of oneAPI Beta—what it is, what it includes, and why it was created
  • How this Intel-driven initiative simplifies development through a common toolset that enables more code reuse
  • How developers can immediately take advantage of oneAPI Beta in their development, from free toolkits to the Intel® DevCloud environment

 

Resources

Kent Moffat, Senior Product Manager, Intel Corporation

Kent Moffat is a senior product line manager responsible for marketing and driving adoption of software development and data science tools. His software expertise spans machine/deep learning, high performance computing, cloud computing, and IoT. Prior to joining Intel in 2008, Kent held several strategic sales and marketing roles in technology, including Mentor Graphics and MathStar.

Kent holds a Bachelor of Science in electrical engineering from Stanford University and a Bachelor of Art in physics from Willamette University.

For more complete information about compiler optimizations, see our Optimization Notice.