Intel finally revealed its long-awaited product Sapphire Rapids The update to the Xeon CPU family, along with the company’s new data center GPU.
Both are now available in Max Series form, and will soon be installed in notable supercomputers, such as the Argonne National Laboratory’s Aurora.
“to guarantee no [high performance computing] With the HPC workload left behind, we need a solution that maximizes bandwidth, increases computing, increases developer productivity, and ultimately maximizes impact,” explained Jeff McPhee, Vice President of Intel’s Super Compute Group.
Intel Xeon Max Series
inside press release (Opens in a new tab) On the company’s website, Intel explains that these supercomputers play a critical role in some of the world’s biggest scientific and societal challenges, “from mitigating the effects of climate change to treating the world’s deadliest disease.”
As such, the latest chips have received a boost in all respects. The Max Series GPU is the company’s highest density processor, and now offers up to 128GB of high-bandwidth memory in the form of more than 100 billion transistors in a 128-core, 47-segment package.
The latest GPUs will be available in three variants: Max Series 1100 GPU, 1350 GPU, and 1550 GPU, each with 48GB, 96GB, and 128GB of memory respectively.
On a similar note, the 350W Xeon Max CPU packs 64GB of high-bandwidth memory across its four-tile setup with up to 56 performance cores based on the same Golden Cove miniature features as Intel 12th-Gen Core CPUs. .
The new hardware will support DDR5, PCIe 5.0, and Compute Express Link (CXL) 1.1, which will enable memory to be directly connected to the CPU via PCIe 5.0.
McPhee acknowledged the delays the company’s new supercomputing components have encountered, noting, “We’ll always push the envelope. Sometimes it causes us not to get it right, but we do it in our developer assistance service, helping the ecosystem to help solve it.” [the world’s] the biggest challenge”.
Intel now expects production of the GPU Max series of the Xeon CPU and Data Center in early 2023, when deliveries will begin to Argonne, Los Alamos National Laboratories, Kyoto University, and other supercomputing sites.