FPO - Demo Hall

See how 3rd Gen Intel® Xeon® Scalable processors compare to the competition’s latest. The combination of our latest cores and advanced software optimization offers a competitive advantage.

3rd Gen Intel® Xeon® Scalable processors provide generational and software optimized performance gains for HPC workloads

HPC Competitive Performance

See how one line of code change, delivers leadership performance for end-to-end AI workloads on 3rd Gen Intel® Xeon® Scalable processors using Intel® oneAPI AI Analytics Toolkit. The combination of our latest cores and advanced software optimization offers a competitive advantage.

 Leadership Performance for End-to-End AI Pipelines 

Optimized Framework and Libraries for 3rd Gen Intel® Xeon® Scalable processors

Learn how DAOS can fully extract the performance advantages of Intel's latest processors and memory, demonstrating significant bandwidth and IOPS performance improvement per node. The DAOS architecture makes data-access times possible that can be several orders of magnitude faster than existing storage systems—from milliseconds to microseconds.

Make data-access times possible that can be several orders of magnitude faster than existing storage systems—from milliseconds to microseconds.

DAOS: Revolutionizing High-Performance Storage

Getting the most out of your supercomputer investment.

The visualization solution, comprised of the Intel® oneAPI Rendering Toolkit, Intel® Xeon® processors and Intel® Optane™ memory,  provides high fidelity visual detail, comprehensive compute capabilities, and massive data capacity, providing scientists a deeper understanding of real world phenomena. You will be amazed at what they have learned!

Intel® oneAPI Rendering Toolkit in Action - Implements the oneAPI Advanced Ray Tracing Specification (oneAPI ART Spec)

Advanced Ray Tracing at Massive Scale

In this demo, we showcase how to use Intel® Extension for PyTorch*, integrated inside the Intel® oneAPI AI Analytics Toolkit, in order to speed up your PyTorch code for training and inference. We will run a decathlon of medical imaging classification tasks on the 3rd Gen Intel® Xeon® Scalable processors.

Intel® Extension for PyTorch*, integrated inside the Intel® oneAPI AI Analytics Toolkit, in order to speed up your PyTorch code for training and inference.

Accelerating Deep Learning with OneAPI

Experience the traiing and inference code speed up decathlon.

Accelerating Deep Learning with Intel® OneAPI AI Analytics Toolkit

Learn how DAOS utilizes Intel’s latest processors and memory to deliver sustained performance while simultaneously running applications with differing IO patterns, a critical necessity for the Aurora supercomputer for Argonne National Laboratory, which will leverage artificial intelligence and machine learning methods to solve the nation’s most pressing scientific problems.

Learn how DAOS utilizes Intel’s latest processors and memory to deliver sustained performance.

DAOS + Optane for Heterogenous Apps​

Sustaining performance across heterogenous workloads

Learn how oneAPI keeps your application running on upcoming heterogeneous systems.  Watch a demo of an electrophysiology cardiac simulation with offload to a Ponte Vecchio card running with oneAPI.

Learn how oneAPI keeps your application running on upcoming heterogeneous systems.

Electrophysiology Simulation on Ponte Vecchio GPU

While Loving Your Heterogenous Hardware

Based on the Xe-HPC microarchitecture, Ponte Vecchio delivers industry-leading FLOPs and compute density to accelerate artificial intelligence, high performance computing and advanced analytics workloads.

Ponte Vecchio Performance Overview

With Intel® oneAPI AI Analytics toolkit

Become immersed in incredible high fidelity ever-evolving scientific visualizations showcasing the oneAPI Rendering Toolkit, Intel Xe GPU, Intel® XEON processors, Intel® Optane memory, and the Intel® Tofino™ programmable Ethernet Switch Asic, in a series of collaborative efforts with our partners. 

Extreme Vis Exascale Xe GPU

Check out our demonstration of the ease with which you can get started on the new Amazon EC2 DL1 instance platform. We’ll also show you how to run a popular computer vision model on DL1 and the results achieved with the Habana Gaudi processor. We’ll also show you the numbers behind the “up to 40% better price performance” that the new instances deliver.

Getting Started on Amazon EC2 DL1 Instances powered by Habana Gaudi Processors

See how Intel delivers leadership performance for financial services application on Intel® Xeon® Scalable processors using Intel® AVX 512 and MatLogica technology. The combination of our latest cores and Vector Accelerate library optimization offers a competitive advantage.

Leadership Performance for Financial Services

Unify and manage all your data science in one place using Intel® optimized containers with cnvrg.io. Communicate and reproduce results with interactive workspaces, dashboards, experiment tracking, and more. Simplify the process of building end to end production ready AI pipelines. 


Simplify your AI Journey on Intel® Architecture with cnvrg.io

Build and deploy AI models at scale. Easily unlock Intel AI performance.

See how Intel delivers leadership performance for end-to-end AI workloads on 3rd Gen Intel® Xeon® Scalable processors using Intel® oneAPI AI Analytics Toolkit. The combination of our latest cores and advanced software optimization offers a competitive advantage.

For detail information, please check out our session: Streamline End-to-End AI Pipelines: Preprocess, Visualize and Build AI Faster at-Scale on Intel Architecture.

Performance Optimizations for AI Pipelines

Learn about Intel’s latest HBM technology to speed-up memory bound workloads, including the three modes of operation.

Speed-up Memory Bandwidth Bound Workloads with HBM

Intel is solving industry memory issues – first with PMem and now with HBM.

Increase productivity and performance with the Intel® Neural Compressor which is an open-source python library that help developers quickly deploy low-precision inference solutions on popular deep learning frameworks.  Developers using INC can increase their productivity by up to 18x and increase performance by up to 30x when quantizing models from FP32 to INT8 numerical formats.