Maximize Possibilities with the Intel® Max Series Family
Architected for the future compute demands of HPC and AI workloads, the Intel® Max Series CPUs and GPUs are designed to accelerate science and discovery by delivering breakthrough performance and unblocking the bottlenecks for memory-bound workloads.
Maximize Bandwidth. Maximize Impact.
Introducing the Intel® Max Series CPUs and GPUs, architected for the future compute demands of HPC and AI workloads.
Intel® Xeon® Max Series CPUs
Maximize bandwidth with the Intel® Xeon® CPU Max Series, the first and only x86-based processor with high-bandwidth memory (HBM). Architected to supercharge the Intel® Xeon® architecture with HBM, Max Series CPUs deliver up to 4.8X better performance compared to competition on real-world HPC and AI workloads** and feature:
Up to 56 performance cores constructed of four tiles and connected using Intel’s embedded multi-die interconnect bridge (EMIB) technology.
64GB of ultra-high-bandwidth in-package memory plus support for PCI Express 5.0 and CXL1.1 I/O.
Up to 1.14GB of HBM capacity per core.
Intel® Data Center GPU Max Series
Maximize impact with the Intel® Data Center GPU Max Series, Intel’s highest performing, highest density, general-purpose discrete GPU, which packs over 100 billion transistors into a package and contains up to 128 Xe-HPC Cores – Intel’s foundational GPU compute building block. Intel Max Series GPUs feature:
408 MB of L2 cache based on discrete SRAM technology and 64 MB of L1 cache.
Up to 128 Ray Tracing units on each Max Series GPU for accelerating scientific visualization and animation.
AI-boosting Xe Matrix Extensions (XMX ) with deep systolic arrays enabling vector and matrix capabilities in a single device.
Max Series Product Demos
Aurora Blade for Machine Learning
First production blades for the Aurora supercomputer at Argonne National Laboratory with Max Series CPUs and GPUs.
Acceleration with High Bandwidth Memory
Performance advantages of the Intel® Xeon® CPU Max Series for the MPAS-A climate and weather simulation workload.
AI Accelerated HPC Training
Comparison of gen-to-gen performance using the DeePMD workload during training and inference phases.
Max Series Family Performance Highlights
View the Intel® Max Series Family introduction video above for a full performance overview.
Max Series Family Customer Designs
Notices and Disclaimers
*Results may vary. This offering is not approved or endorsed by OpenCFD Limited, producer and distributor of the OpenFOAM software via www.openfoam.com, and owner of the OPENFOAM® and OpenCFD® trademark. Unverified performance Gains on MLPerf™ HPC-AI v 0.7 Cosmoflow Training benchmark using optimized Tensorflow2.6 (FP32, FP16) and 2.9.1 (FP32,BP16). Result not verified by MLCommons Association. Unverified results have not been through an MLPerf™ review and may use measurement methodologies and/or workload implementations that are inconsistent with the MLPerf™ specification for verified results. The MLPerf™ name and logo are trademarks of MLCommons Association in the United States and other countries. All rights reserved. Unauthorized use strictly prohibited. See www.mlcommons.org for more information.
**Visit the SuperComputing '22 page at Performance Index site for workloads and configurations. Performance varies by use, configuration and other factors. See backup configuration for details. No product or component can be absolutely secure.
***In this sensitivity study, the 408MB L2 cache in Max series GPU is down-configured to 80MB and 32MB.