The Intel Max Series delivers breakthrough bandwidth and memory performance in HPC and AI
The new product family offers a CPU with high-bandwidth memory, 4.8 times faster than the competition, and Intel’s highest density GPU, to solve the world’s biggest challenges.
What’s New: Ahead of Supercomputing ’22 in Dallas, Intel Corporation has introduced the Intel Max Series product family with two cutting-edge products for high performance computing (HPC) and artificial intelligence (AI): Intel® Xeon® CPU Max Series (codenamed Sapphire Rapids HBM) and the Intel® Data Center GPU Max Series (codenamed 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, featuring more than 100 billion transistors in a 47-chip package with up to 128 gigabytes (GB) of high-bandwidth memory. The oneAPI open software ecosystem provides a unique programming environment for the two new processors. Intel 2023 oneAPI and AI tools will provide capabilities to enable advanced features of Intel Max series products.
“To ensure that no HPC workload is left behind, we need a solution that maximizes bandwidth, maximizes compute, maximizes developer productivity, and ultimately maximizes impact. The product family of the Intel Max series brings high-bandwidth memory to the wider market, along with oneAPI, making it easier to share code between CPUs and GPUs and solve the world’s biggest challenges faster.
–Jeff McVeigh, corporate vice president and general manager, Intel’s Super Compute Group
Why it matters: High Performance Computing (HPC) represents the cutting edge of technology, using the most advanced innovations at scale to solve the biggest challenges in science and society, from mitigating the impacts of climate change to curing disease deadliest in the world.
Max Series products meet the needs of this community with scalable and balanced CPUs and GPUs, incorporating advances in memory bandwidth and united by oneAPI, an open, standards-based, multi-architecture programming framework. Researchers and businesses will solve problems faster and more sustainably with Max Series products.
When it arrives: The launch of the Max series products is scheduled for January 2023. To fulfill its commitments to customers, Intel is sending blades with Max series GPUs to Argonne National Laboratory to power the Aurora supercomputer and will deliver Xeon Max CPUs at Kyoto University’s Los Alamos National Laboratory. and other supercomputing sites.
What the Intel Xeon Max CPU offers: The Xeon Max CPU offers up to 56 performance cores built across four chips and connected using Intel’s Multiple Array Interconnect Bridge (EMIB) technology, in a 350-watt package. Xeon Max CPUs pack 64GB of memory into the high-bandwidth package, as well as PCI Express 5.0 and CXL1.1 I/O. Xeon Max CPUs will provide more than 1 GB of high-bandwidth memory (HBM) capacity per core, enough to accommodate the most common HPC workloads. The Max Series CPU delivers up to 4.8x better performance compared to the competition on real-world HPC workloads.1
- 68% less power than an AMD Milan-X cluster for the same HPCG performance.
- AMX extensions increase AI performance and offer up to 8x performance over AVX-512 for INT8 with INT32 accumulation operations.2
- It offers flexibility to run on different HBM and DDR memory configurations.
- Workload Benchmarks:
- Climate modeling: 2.4x faster than AMD Milan-X with MPAS-A using only HBM.
- Molecular Dynamics: In DeePMD, 2.8x performance improvement over competing products with DDR memory.
What the Intel Max Series GPU offers: Max series GPUs offer up to 128 Xe-Nuclis HPC, the new basic architecture aimed at the most demanding computing workloads. In addition, the Max Series GPU offers:
- 408MB of L2 cache, the highest in the industry, and 64MB of L1 cache for increased performance and performance.
- The only HPC/AI GPU with native ray tracing acceleration, designed to accelerate scientific visualization and animation.
- Workload Benchmarks:
- Finance: 2.4x performance gain over NVIDIA’s A100 in Riskfuel credit options pricing.
- Physics: 1.5x improvement over A100 for NekRS virtual reactor simulations.
Max Series GPUs will be available in multiple form factors to meet different customer needs:
- GPU Max Series 1100: A 300-watt double-wide PCIe card with 56 Xe cores and 48 GB of HBM2e memory. Multiple cards can be connected via Intel Xe Link bridges.
- GPU Max Series 1350: A 450-watt OAM module with 112 Xe cores and 96GB of HBM.
- GPU Max Series 1550: Intel’s highest performing 600-watt OAM module with 128 Xe cores and 128GB of HBM.
Beyond individual cards and modules, Intel will offer the Intel Data Center GPU Max series subsystem with an OAM GPU x4 backplane and Intel Xe Link to enable high-performance multi-GPU communication within the subsystem.
What the Max series products allow: 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 computing performance.3. Aurora will also be the first to showcase the power of combining GPUs and Max-series CPUs in a single system, with more than 10,000 blades, each containing six Max-series GPUs and two Xeon Max CPUs.
Prior to the SC22, Argonne and Intel introduced Sunspot, Aurora’s test development system consisting of 128 production blades. Aurora Early Science Program researchers will have access to the system from the end of 2022.
Max Series products will power several other HPC systems critical to national security and basic research, including Crossroads at Los Alamos National Laboratory, CTS-2 systems at Lawrence Livermore National Laboratory, and Sandia National Laboratory and Camphor3 in Kyoto University.
What follows: At Supercomputing ’22, Intel and its customers will showcase more than 40 upcoming system designs from 12 OEMs that use Max Series products. Attendees can explore demonstrations showcasing the performance and capability of Max Series products for a range of AI and HPC applications, as well as hear from Intel architects, customers and end users about the power of the solutions of Intel platform at Intel booth, #2428. . More information is available on Intel’s activities at SC22.
The Intel Data Center Max Series GPU, codenamed Rialto Bridge, is the successor to the Max Series GPU and is slated to arrive in 2024 with improved performance and a seamless upgrade path. Then Intel plans to release the next major architectural innovation to enable the future of HPC. The company’s next XPU, codenamed Falcon Shores, will combine Xe and x86 cores in a single package. This innovative new architecture will also have the flexibility to integrate new Intel and customer IPs, manufactured using our IDM 2.0 model.
“end of press release”