Monday, May 29th 2023
Giga Computing Goes Big with Green Computing and HPC and AI at Computex
Giga Computing, a subsidiary of GIGABYTE and an industry leader in high-performance servers, server motherboards, and workstations, today announced a major presence at Computex 2023, held May 30 to June 2, with a GIGABYTE booth that inspires while showcasing more than fifty servers that span GIGABYTE's comprehensive enterprise portfolio, including green computing solutions that feature liquid cooled servers and immersion cooling technology. The international computer expo attracts over 100,000 visitors annually and GIGABYTE will be ready with a spacious and attractive booth that will draw in curious minds, and at the same time there will be plenty of knowledgeable staff to answer questions about how our products are being utilized today.
The slogan for Computex 2023 is "Together we create." And just like parts that make a whole, GIGABYTE's slogan of "Future of COMPUTING" embodies all the distinct computing products from consumer to enterprise applications. For the enterprise business unit, there will be sections with themes: "Win Big with AI HPC," "Advance Data Centers," and "Embrace Sustainability." Each theme will show off cutting edge technologies that span x86 and ARM platforms, and great attention is placed on solutions that address challenges that come with more powerful computing.
Win Big with AI HPC
Given recent breakthroughs in how we can use data to take on new shapes such as generative AI, the "Win Big with AI HPC" display will stage the ultimate in computing performance with GPUs and dense compute innovations. The latest generation of AMD and Intel platforms will show off our systems purpose built for the x86 platform. One of the servers, GIGABYTE G593-SD0, was designed specifically for large-scale AI and HPC with NVIDIA HGX H100 as the baseboard platform, and is the first commercially available HGX H100 8 GPU server. Moving to another notable x86 server, the G293-Z43 houses the densest AI inference solution possible with sixteen AMD Alveo V70 AI Inference Accelerator cards in a 2U chassis. Sitting next to these aforementioned systems will be two new GIGABYTE servers for the exciting, new NVIDIA Grace CPU Superchip platform, which is the first NVIDIA CPU designed for the data center.
GIGABYTE Servers for Accelerated Computing
The GIGABYTE H263 series is a versatile 2U platform designed for four nodes, each of which has dual processors, and traditionally focuses on dense CPU compute. However, with the introduction of the NVIDIA Grace CPU, the four node GIGABYTE platform can reach greater levels of performance. The new H263 servers can support either the NVIDIA module with two Grace CPUs, called the NVIDIA Grace CPU Superchip, or the module with a single Grace CPU and NVIDIA H100 Hopper GPU, called the NVDIA Grace Hopper Superchip. The GIGABYTE H263-V60 is a server for the CPU module to be used on CPU-based applications such as scientific computing or data analytics; on the other hand, the GIGABYTE H263-V11 houses the CPU/GPU module for large scale, flagship AI and HPC applications. This new class of architecture is significant because the fused NVIDIA NVLink C2C allows 900 GB/s total bandwidth chip-to-chip interconnect between CPUs or between CPU and GPU, and the platform has unified memory with the onboard LPDDR5X memory. These two new GIGABYTE servers are just the beginning of superchip integration.
Advance Data Centers
Data centers come in all shapes and sizes, so GIGABYTE has servers, motherboards, and add-on cards covering the myriad of applications such as cloud, edge, storage, HPC, and more. These solutions are based on CPU platforms from partners AMD, Ampere, Intel, and NVIDIA. And this includes EIA and OCP rack specifications. Visitors can also see liquid cooled servers with DLC technology.
This month Ampere Computing announced their next gen platform, AmpereOne, and GIGABYTE will be ready with four new servers designed for this cloud native platform, and visitors can see them at our booth. The AmpereOne jumps up to a staggering 192 Arm cores per socket, and our R283-P93 and R183-P92 are designed for a dual socket design that supports 384 CPU cores, while the R263-P33 and R163-P32 are single-socket offerings. This new AmpereOne platform adds support for DDR5 memory, PCIe Gen5, and bfloat16, to name a few of their advancements.
Embrace Sustainability
GIGABYTE offers a complete end-to-end immersion cooling solution from one company. From GIGABYTE's custom tanks and immersion ready servers to leading providers of immersion coolants to immersion ready servers, GIGABYTE has the capability to help you deploy immersion smoothly. Yet, to provide better world-wide support, GIGABYTE has partnered with leading immersion tank suppliers Asperitas, GRC, and Submer to deliver greater options. At our booth, visitors can see our very own designed tanks that include a 25U EIA tank (with CDU) and a 18OU OCP tank, both of which can sustain a high degree of heat dissipation. Also, making an appearance at the GIGABYTE booth is a smaller 12U EIA tank. Immersion cooling has a great deal of potential. And this technology has proven it can provide benefits such as greater energy efficiency, high scalability, and top-tier performance.
Source:
Gigabyte
The slogan for Computex 2023 is "Together we create." And just like parts that make a whole, GIGABYTE's slogan of "Future of COMPUTING" embodies all the distinct computing products from consumer to enterprise applications. For the enterprise business unit, there will be sections with themes: "Win Big with AI HPC," "Advance Data Centers," and "Embrace Sustainability." Each theme will show off cutting edge technologies that span x86 and ARM platforms, and great attention is placed on solutions that address challenges that come with more powerful computing.
Given recent breakthroughs in how we can use data to take on new shapes such as generative AI, the "Win Big with AI HPC" display will stage the ultimate in computing performance with GPUs and dense compute innovations. The latest generation of AMD and Intel platforms will show off our systems purpose built for the x86 platform. One of the servers, GIGABYTE G593-SD0, was designed specifically for large-scale AI and HPC with NVIDIA HGX H100 as the baseboard platform, and is the first commercially available HGX H100 8 GPU server. Moving to another notable x86 server, the G293-Z43 houses the densest AI inference solution possible with sixteen AMD Alveo V70 AI Inference Accelerator cards in a 2U chassis. Sitting next to these aforementioned systems will be two new GIGABYTE servers for the exciting, new NVIDIA Grace CPU Superchip platform, which is the first NVIDIA CPU designed for the data center.
GIGABYTE Servers for Accelerated Computing
The GIGABYTE H263 series is a versatile 2U platform designed for four nodes, each of which has dual processors, and traditionally focuses on dense CPU compute. However, with the introduction of the NVIDIA Grace CPU, the four node GIGABYTE platform can reach greater levels of performance. The new H263 servers can support either the NVIDIA module with two Grace CPUs, called the NVIDIA Grace CPU Superchip, or the module with a single Grace CPU and NVIDIA H100 Hopper GPU, called the NVDIA Grace Hopper Superchip. The GIGABYTE H263-V60 is a server for the CPU module to be used on CPU-based applications such as scientific computing or data analytics; on the other hand, the GIGABYTE H263-V11 houses the CPU/GPU module for large scale, flagship AI and HPC applications. This new class of architecture is significant because the fused NVIDIA NVLink C2C allows 900 GB/s total bandwidth chip-to-chip interconnect between CPUs or between CPU and GPU, and the platform has unified memory with the onboard LPDDR5X memory. These two new GIGABYTE servers are just the beginning of superchip integration.
Advance Data Centers
Data centers come in all shapes and sizes, so GIGABYTE has servers, motherboards, and add-on cards covering the myriad of applications such as cloud, edge, storage, HPC, and more. These solutions are based on CPU platforms from partners AMD, Ampere, Intel, and NVIDIA. And this includes EIA and OCP rack specifications. Visitors can also see liquid cooled servers with DLC technology.
This month Ampere Computing announced their next gen platform, AmpereOne, and GIGABYTE will be ready with four new servers designed for this cloud native platform, and visitors can see them at our booth. The AmpereOne jumps up to a staggering 192 Arm cores per socket, and our R283-P93 and R183-P92 are designed for a dual socket design that supports 384 CPU cores, while the R263-P33 and R163-P32 are single-socket offerings. This new AmpereOne platform adds support for DDR5 memory, PCIe Gen5, and bfloat16, to name a few of their advancements.
Embrace Sustainability
GIGABYTE offers a complete end-to-end immersion cooling solution from one company. From GIGABYTE's custom tanks and immersion ready servers to leading providers of immersion coolants to immersion ready servers, GIGABYTE has the capability to help you deploy immersion smoothly. Yet, to provide better world-wide support, GIGABYTE has partnered with leading immersion tank suppliers Asperitas, GRC, and Submer to deliver greater options. At our booth, visitors can see our very own designed tanks that include a 25U EIA tank (with CDU) and a 18OU OCP tank, both of which can sustain a high degree of heat dissipation. Also, making an appearance at the GIGABYTE booth is a smaller 12U EIA tank. Immersion cooling has a great deal of potential. And this technology has proven it can provide benefits such as greater energy efficiency, high scalability, and top-tier performance.
Comments on Giga Computing Goes Big with Green Computing and HPC and AI at Computex
There are no comments yet.