Artificial Intelligence (AI)
Discuss current events in AI and technological innovations with Intel® employees
413 Discussions

AI and HPC DevSummit 2022 Keynote: AI Software and Hardware Acceleration

1 0 2,628

AI developers and data scientists face common obstacles to quickly move AI projects from pilot to deployment due to the diversity of data, models and deployment targets. But how do you move through the AI pipeline quickly?

According to keynote presenter Andres Rodriquez from Intel, it takes a combination of software optimization and hardware acceleration. Software optimization, through oneAPI, provides optimized data processing and distributes machine learning and deep learning workloads across multiple hardware architectures. Hardware acceleration is required to achieve higher performance and throughput, lower latency, and enable AI inference at edge. Rodriquez discusses multiple case studies whereby companies are leveraging Intel’s software and hardware to achieve faster results for tasks such as search, speech synthesis, and reinforcement learning.

He introduces the 4th Gen Intel® Xeon® Scalable processor and its specialized hardware for AI acceleration that makes it feasible to run both training and inference on an Intel Xeon CPU for many AI based applications. Acceleration of classical machine learning and deep learning workloads with the 4th Gen Intel Xeon Scalable processor is attainable because of the Intel® Advanced Matrix Extensions (Intel® AMX) in every core. Intel AMX stores bigger chunks of data in each core and an accelerator engine contains instructions to compute larger matrices in a single operation.

Watch the keynote below to learn how Intel’s oneAPI-powered AI software and tools along with hardware architectures are improving AI application performance and developer productivity.

See the video: AI Software and Hardware Acceleration


We encourage you to check out Intel’s other AI Tools and Framework optimizations and learn about the unified, open, standards-based oneAPI programming model that forms the foundation of Intel’s AI Software Portfolio.

For more details about the new 4th Gen Intel Xeon Scalable processor, visit AI Platform where you can learn about how Intel is empowering developers to run end-to-end AI pipelines with Intel Xeon Scalable processors.

About our experts

Andres Rodriguez, Intel Fellow and Chief AI Architect

Andres is an Intel Fellow and Chief AI Architect. He designs deep learning solutions for Intel’s data center customers and provides technical leadership across Intel for deep learning hardware and software products. He was the lead instructor in the Coursera course An Introduction to Practical Deep Learning to over 20K students and is the author of the popular book Deep Learning Systems: Algorithms, Compilers, and Processors for Large-Scale Production. He has been an invited speaker for several AI events and a university lecturer.