SC22, this year’s version of the well-known supercomputing conference, kicks off next week, but Intel jumped the line for admission this week with an announcement showing off how it is evolving its approach for addressing high-performance computing and AI needs and workloads.
Intel, after a run of lousy news that included a plan to cut $3 billion in costs over the next year, this week announced the Intel Max Series product family, which includes Intel’s first x86 CPU with high-bandwidth memory.
That would be the Xeon CPU Max Series for high-bandwidth memory (HBM) applications, which previously has been referred to as Sapphire Rapids HBM. The other star of the Max series announced this week is the Intel Data Center GPU Max Series, previously called Ponte Vecchio.
Both products will be deployed in conjunction with Argonne National Laboratory’s Aurora supercomputer, which was announced late last year and is due for completion soon. At least a dozen vendor partners are lining up to support the products, both of which are due to roll out in January 2023. The come at a time when Intel, Nvidia, AMD and other players in the sector have been holding up HPC and AI as the main use cases driving their product evolutions.
“To ensure no HPC workload is left behind, we need a solution that maximizes bandwidth, maximizes compute, maximizes developer productivity and ultimately maximizes impact,” said Jeff McVeigh, Corporate Vice President and General Manager, Super Compute Group at Intel, as he explained both the name and aim of the new processor series.
Intel described the Xeon Max CPU as offering up to 56 performance cores constructed of four tiles and connected using Intel’s embedded multi-die interconnect bridge technology, in a 350-watt envelope. It contains 64GB of high bandwidth in-package memory, as well as PCI Express 5.0 and CXL1.1 I/O, and will provide more than 1GB of HBM capacity per core, enough to fit most common HPC workloads, the company said. Intel also claimed that performance and power efficiency of the CPUs are better than that of competing CPUs.
The Xeon The Max Series GPU is Intel’s highest density processor, packing over 100 billion transistors into a 47-tile package with up to 128 gigabytes (GB) of high bandwidth memory. The oneAPI open software ecosystem provides a single programming environment for both new processors. Intel’s 2023 oneAPI and AI tools will deliver capabilities to enable the Intel Max Series products' advanced features.