Nvidia

GIGABYTE Releases Supercharged Arm-Based CPU Server for NVIDIA HGX

GIGABYTE Releases Supercharged Arm-Based CPU Server for NVIDIA HGX

May 19, 2022 — GIGABYTE Technology, (TWSE: 2376), an industry leader in high-performance servers and workstations, today announced a new supercharged and scalable server, G492-PD0, which supports an Ampere Altra Max or Altra processor with NVIDIA HGX A100 Tensor Core GPUs for the best performance in cloud infrastructure, HPC, AI, and more. Leveraging Ampere’s Altra Max processor with high core count, up to 128 Armv8.2 cores per socket with Arm’s M1 core, the G492-PD0 delivers high performance efficiently and with total cost. of possession minimized.

GIGABYTE has developed the G492-PD0 in response to a request for high-performance platform choices beyond x86, namely Ampère’s Arm-based processor. This new G492 server was designed to handle the performance of NVIDIA’s motherboard accelerator without compromising or throttling CPU or GPU performance. This server joins the existing line of GIGABYTE G492 servers that support the NVIDIA HGX A100 8-GPU baseboard on the AMD EPYC platform (G492-ZL2, G492-ZD2, G492-ZD0) and Intel Xeon Scalable (G492-ID0).

The G492 server line uses a new cooling solution that dedicates a cooling chamber for NVIDIA accelerators and GPUs used in network expansion slots, ensuring the highest possible airflow to cool high-performance components. Above the 3U GPU chamber is a 1U server that houses the processor, memory, storage, and front-facing expansion slots. Due to the high efficiency of Ampere’s processors, the slim 1U server is able to maintain peak performance, including filling all Gen4 U.2 NVMe drive bays and two additional expansion slots on the front of the chassis without compromise.

The inclusion and choices of the NVIDIA HGX A100 platform in the new GIGABYTE server is significant, as new NVIDIA Magnum IO GPUDirect technologies promote faster throughput while offloading CPU workloads to achieve noticeable performance gains. The HGX platform supports NVIDIA GPUDirect RDMA for direct data exchange between GPUs and third-party devices such as network cards or storage adapters. And there’s support for GPUDirect Storage for a direct data path to move data from storage to GPU memory while offloading the CPU, resulting in higher bandwidth and lower latency. For high-speed interconnects, the four NVIDIA A100 servers incorporate NVIDIA NVLink, while the eight NVIDIA A100 servers use NVSwitch and NVLink to enable 600 Gb/s GPU peer-to-peer communication.

GIGABYTE will continue to pursue the most prolific line of servers on the market for all enterprise workloads. Building Arm-based servers is not new to GIGABYTE as we have been developing solutions for nearly a decade. And future platforms will be created based on market demand, including more liquid cooling solutions.

Remote and multi-server management

As part of GIGABYTE’s value proposition, GIGABYTE provides the GIGABYTE Management Console (GMC) for managing BMC Server through a web browser-based platform. Additionally, GIGABYTE Server Management (GSM) software is available for download on the product pages. This software can monitor and manage multiple servers without requiring additional license fees. GMC and GSM deliver great value while reducing TCO and customer maintenance costs.


Source: GIGABYTE