There are reports that China has a new superchip MT-3000 processor designed by the National University of Defense Technology (NUDT). The MT-3000 has general-purpose CPU cores, control cores, and matrix accelerator cores. NUDT’s MT-3000 processor features a multi-zone structure that packs 16 general-purpose CPU cores with 96 control cores and 1,536 accelerator cores. The MT-3000 …
Combining the Arm-based NVIDIA Grace CPU and Hopper GPU architectures using NVIDIA NVLink-C2C interconnect technology is the Nvidia GH200. The Nvidia GH200 is the engine behind AI and scientific supercomputing centers across the globe. GH200-powered centers represent some 200 exaflops of AI performance to drive scientific innovation. HPE Cray Supercomputers Integrate NVIDIA Grace Hopper HPE …
Isambard-AI will be built using the HPE Cray EX supercomputer, a next-generation platform architected to support unprecedented performance and scale, and consist of 5,448 NVIDIA GH200 Grace Hopper Superchips which combine NVIDIA’s Arm-based Grace CPU with a Hopper-based GPU optimized for power efficiency and giant-scale AI, along with the latest HPE Slingshot 11 interconnect, and …
Tachyum is a startup that will make Prodigy processors will enable hyperscale data centers that have 25% of the cost (4X lower cost) and will saving each hyperscale customer billions of dollars per year. First-generation Prodigy data centres will offer 3.3 EF of FP64, three times the performance of existing supercomputers, and also deliver around …
Tachyum’s first chip Prodigy has not completely finished its design but one customer will buy hundreds of thousands of Universal chips to build a 50 exaFLOPS supercomputer. Tachyum® announced that it has accepted a major purchase order from a US company to build a large-scale system, based on its 5nm Prodigy® Universal Processor chip, which …
In 2021, Intel talked reaching Zettascale in three phases. AMD CEO talked about getting to a Zettaflop in 2030-2035. AMD CEO indicated that an earlier Zettaflop supercomputer would need about 500 Megawatts of power. Exascale systems today consume 21MW of power. AMD and Intel have managed to roughly double the performance of their CPUs and …
Tesla Dojo team presented at the Hot Chip 34 conference. Tesla has made sure that the IO (input output), memory, software, power, cooling and all other aspects of the system are perfectly scalable. This will enable them to just build and add tiles to scale to the Exaflop level and beyond. About 120 compute tiles …
Purdue University has a new 5.2 petaflop AI Anvil supercomputer. It will enable new discoveries in fields ranging from hypersonics and deep learning to archeological reconstruction and bone biomechanics. Anvil was funded by a $22.5 million grant from the National Science Foundation. Early users are working on projects in key areas of research such as: …
The more compute you put into a neural network then the better result you can get. There does not seem to be a limit for neural nets to utilize more resources to get better and faster results. Tesla is motivated to develop bigger, faster computers that are precisely suited to their needs. The Google TPU …
Al Geist presented a history of the Exascale Project and How Frontier Solves the Four Exascale Challenges. This is part of the Advanced Technologies Section (ATS) series of the National Center for Computational Sciences at ORNL. Chip and Network vendors greatly improved the reliability of their systems to push this problem beyond the Exaflop scale. …
U.S. Department of Energy’s Argonne National Laboratory and Hewlett Packard Enterprise (NYSE: HPE) unveiled a new testbed supercomputer to prepare critical workloads for future exascale systems that will deliver up to four times faster performance than Argonne’s current supercomputers. Polaris will enable scientists and developers to test and optimize software codes and applications to tackle …