GIGABYTE Unveils Next-gen HPC & AI Servers with AMD Instinct™ MI300 Series Accelerators

Leading the charge with both AMD Instinct™ MI300X GPU and MI300A APU

December 6, 2023 – Giga Computing, a subsidiary of GIGABYTE and an industry leader in high-performance servers, and IT infrastructure, today announced the GIGABYTE G383-R80 for the AMD Instinct™ MI300A APU and two GIGABYTE G593 series servers for the AMD Instinct™ MI300X GPU and AMD EPYC™ 9004 Series processor. As a testament to the performance of AMD Instinct™ MI300 Series family of products, the El Capitan supercomputer at Lawrence Livermore National Laboratory uses the MI300A APU to power exascale computing. And these new GIGABYTE servers are the ideal platform to propel discoveries in HPC & AI at exascale.⁠

Marrying of a CPU & GPU: G383-R80
For incredible advancements in HPC there is the GIGABYTE G383-R80 that houses four LGA6096 sockets for MI300A APUs. This chip integrates a CPU that has twenty-four AMD Zen4 cores with a powerful GPU built with AMD CDNA 3 GPU cores. And the chiplet design shares 128GB of unified HBM3 memory for impressive performance for large AI models. The G383 server has lots of expansion slots for networking, storage, or other accelerators, with a total of twelve PCIe Gen5 slots. And in the front of the chassis are eight 2.5” Gen5 NVMe bays to handle heavy workloads such as real-time big data analytics and latency-sensitive workloads in finance and telecom. ⁠

Powerful exascale GPU: G593 series
These compelling new GIGABYTE G593-ZX1/ZX2 servers are based around the AMD CDNA accelerator architecture achieved exascale computing, and further advancements led to CDNA 3 architecture that is poised to make significant performance gains when compared to the prior gen MI250X GPU. In these G593 servers are eight MI300X GPUs, each accelerator having 192GB of unified HBM3 memory that is ideal for large language models. Powering these MI300X based servers are dual AMD EPYC 9004 processors, with server SKU options for the additional expansions slots that use either additional PLX switches or are direct attached. These twelve expansion slots are for GPUs, networking cards, or storage devices. ⁠

“At SC23 we had a lot of visitors at our GIGABYTE booth that were eager to see our server for the MI300 series. And if their excitement is an indication of its prowess then we are in a good position because we have many MI300 GPU servers coming the market soon,” said Vincent Wang, VP of Sales at Giga Computing. “The incredible advancements in chiplet design at a viable power level will ensure our systems deliver.”

These new servers will come to the market in the first half of 2024. Interested parties are encouraged to contact our sales for in-depth information on these server designs and how to quickly deploy MI300 series systems.⁠