GPU Server
과학 연산, 데이터 분석, 머신러닝 추론, 비디오 트크랜스코딩과 같은 난이도 높은 연산 처리가 부각되면서 데이터를 신속/정확하게 산출하여 다변화된 비즈니스 환경에 대응이 가능한 컴퓨팅 자원으로 2개의 GPU부터 10개 GPU까지 병렬 서버로 연결하는 최고의 자원을 선택할 수 있습니다.


GNR4-ADG12L8U10G


| HPC Server

| 4U DP 10 x Gen4 GPU Server ( Broadcom solution)

| Application: AI , AI Training , AI Inference & HPC


  • ● Up to 10 x PCIe Gen4 GPU cards
  • ● AMD EPYC™ 7003 processors with AMD 3D V-Cache™ Technology
  • ● AMD EPYC™ 7003 series processor family
  • ● 8-Channel RDIMM/LRDIMM DDR4 per processor, 32 x DIMMs
  • ● Dual ROM Architecture supported
  • ● 2 x 1Gb/s LAN ports (Intel® I350-AM2)
  • ● 1 x dedicated management port
  • ● 4 x Gen4 NVMe hot-swappable HDD/SSD bays
  • ● 4 x Gen4 NVMe/SATA/SAS hot-swappable HDD/SSD bays
  • ● 4 x SATA/SAS hot-swappable HDD/SSD bays
  • ● 10 x FHFL Gen4 expansion slots for GPU cards
  • ● 3 x low profile PCIe Gen4 expansion slots
  • ● 1 x OCP 3.0 Gen4 x16 mezzanine slot in rear side
  • ● 3 x 80 PLUS Platinum 2200W (240V) redundant PSU

Nothing Stacks Up To EPYC™


AMD EPYC™ 7003 Processors with AMD 3D V-Cache™

AMD EPYC 7003 Series Processors with AMD 3D V-Cache™ technology are raising the bar once more for breakthrough performance on targeted technical computing workloads like Electronic Design Automation, Computational Fluid Dynamics, and Finite Element Analysis software and solutions. Delivering breakthrough performance per core and performance per watt, the Zen 3 architecture maintains leadership in number of cores – up to 64, amount of L3 cache – 768MB, and 128 PCIe 4.0 lanes, while maintaining socket compatibility with existing 3rd Gen AMD EPYC platforms.

ArchitectureL3 Cache Per Socket“ZEN 3” CoresPCIe 4.0 Lanes
Zen3768MBUP To 64128

Architecture
for Modern Data Centers


AMD EPYC™ 7003 Series Processors

GIGABYTE servers and AMD EPYC 7003 Series Processors deliver the highest possible I/O throughput to pave the way for fast communication between CPU and accelerator in HPC and data analytics.

Product Overview

System Block Diagram

High Performance


Support Various Computing Accelerators

GIGABYTE servers have been tested and validated across a range of workloads with various computing accelerators designed to deliver high levels of performance for 3D rendering, deep learning and high-performance computing, which enables content creators, data scientists, researchers, and engineers to tackle challenges that were once impossible.


AMD
GPU Accelerator
NVIDIA
GPU Accelerator
XILINX
FPGA Accelerator
Qualcomm
ASIC Accelerator

Max Memory Speed Even
at 2 DPC


With GIGABYTE unique solution, maximum memory speed is now supported, even when using 2 DIMMS per channel*. GIGABYTE’s server platforms give you the performance edge, with more memory capacity at faster speeds.

* Enabled via BIOS setting (“UMC Common Options”  “DDR4 Common Options”  Configure “Enforce POR” setting). Please follow product QVL. Please consult your GIGABYTE sales or technical representative for more information.


Hardware Security


Optional TPM 2.0 Module

For hardware-based authentication, the passwords, encryption keys, and digital certificates are stored in a TPM module to prevent unwanted users from gaining access to your data. GIGABYTE TPM modules come in either a Serial Peripheral Interface or Low Pin Count bus.


Power Efficiency


Automatic Fan Speed Control

GIGABYTE servers are enabled with Automatic Fan Speed Control to achieve the best cooling and power efficiency. Individual fan speeds will be automatically adjusted according to temperature sensors strategically placed in the servers.


High Availability


Smart Crises Management and Protection (SCMP)

SCMP is a GIGABYTE patented feature which is deployed in servers with non-fully redundant PSU design. With SCMP, in the event of faulty PSU or overheated system, the system will force the CPU into an ultra-low power mode that reduces the power load, which prevents the system from unexpected shutdown and avoids component damage or data loss.


Dual ROM Architecture

If the ROM that stores the BMC and BIOS fails to boot, the system will reboot with the backup BMC and/or BIOS replacing the primary. Once the primary BMC is updated, the ROM of the backup BMC will automatically update the backup through synchronization. For the BIOS, it can be updated based on user's choice of firmware version.


Smart Ride Through (SmaRT)

To prevent server downtime and data loss as a result of loss of AC power, GIGABYTE implements SmaRT in all our server platforms. When such an event occurs, the system will throttle while maintaining availability and reducing power load. Capacitors within the power supply can supply power for 10-20ms, which is enough time to transition to a backup power source for continued operation.