Intel unveils Max Series GPUs for high-performance computing and AI

Intel has unveiled its Intel Max Series graphics processing units (GPUs) for high-performance computing and AI applications.

The company made the announcement ahead of the Supercomputing 22 (SC22) event in Dallas this week. It also unveiled the Intel Xeon CPU Max Series (code-named Sapphire Rapids HBM) and Intel
Data Center GPU Max Series (code-named Ponte Vecchio).

The new products will power the upcoming Aurora supercomputer at Argonne National Laboratory, with updates on its deployment shared today. The Xeon Max CPU is the first and only x86-based processor with high bandwidth memory, accelerating many HPC workloads without the need for code changes.

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.

“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 of the Super Compute Group at Intel, in a statement. “The Intel Max Series product family brings high bandwidth memory to the broader market, along with oneAPI, making it easy
to share code between CPUs and GPUs and solve the world’s biggest challenges faster.”

Why It matters

High-performance computing (HPC) represents the vanguard of technology, employing the most advanced innovations at scale to solve science and society’s biggest challenges, from mitigating the impacts of climate change to curing the world’s deadliest diseases, Intel said.

The Max Series products targets this community with scalable, balanced CPUs and GPUs, incorporating memory bandwidth breakthroughs and united by oneAPI, an open, standards-based, cross-architecture programming framework. Researchers and businesses will solve problems faster and more sustainably using Max Series products.

The Max Series products are slated to launch in January 2023. Intel is shipping blades with Max Series GPUs to Argonne National Laboratory to power the Aurora supercomputer and will deliver Xeon Max CPUs to Los Alamos National Laboratory, Kyoto University and other supercomputing sites.

The Xeon Max CPU offers up to 56 performance cores constructed of four tiles and connected using Intel’s embedded multi-die interconnect bridge (EMIB) technology, in a 350-watt envelope. Xeon Max CPUs contain 64GB of high bandwidth in-package memory, as well as PCI Express 5.0 and CXL1.1 I/O.

Xeon Max CPUs will provide more than 1GB of high bandwidth memory (HBM) capacity per core, enough to fit most common HPC workloads. The Max Series CPU provides up to 4.8 times better performance compared to competition on real-world HPC workloads, Intel said.

The company said it uses 68% less power usage than an AMD Milan-X cluster for the same HCPG performance. And it said AMX extensions boost AI performance and deliver eight times peak throughput over AVX-512 for INT8 with INT32 accumulation operations.

For climate modeling, Intel said the Max CPUs are 2.4 times faster than AMD Milan-X on MPAS-A using only HBM. With molecular dynamics, Intel said has 2.8 times performance on DeePMD against competing
products with DDR memory.

The Intel Max Series GPU delivers up to 128 Xe-HPC cores, the new foundational architecture targeted at the most demanding computing workloads. Additionally, the Max Series GPU features 408MB of L2 cache – the highest in the industry – and 64MB of L1 cache to increase throughput and performance, Intel said.

In 2023, the Aurora supercomputer, currently under construction at Argonne National Laboratory, is expected to become the first supercomputer to exceed 2 exaflops of peak double-precision compute performance. Aurora will also be the first to showcase the power of pairing Max Series GPUs and CPUs in a single system, with more than 10,000 blades, each containing six Max Series GPUs and two Xeon Max CPUs.

The Intel Data Center Max Series GPU, code-named Rialto Bridge, is the successor to the Max Series GPU
and is intended to arrive in 2024 with improved performance and a seamless path to upgrade. Intel is
then planning to release the next major architecture innovation to enable the future of HPC.

The company’s upcoming XPU, code-named Falcon Shores, will combine Xe and x86 cores on a single
package. This groundbreaking new architecture will also have the flexibility to integrate new IPs from
Intel and customers, manufactured using a IDM 2.0 model.