[Digital Electronics] - [Computer]

ASUS official authentic ESC4000 G2 2CPU + 4GPU / cluster supercomputing server / E5-2620V2 / 8G

Product code: -37091100030
Unit price 5357.82$
Sold quantity 0
Available stock 5
Expired or Cancelled

Product parameters:

  • Memory Type: REG
  • Blade server architecture: 2U
  • Brand: Asus / ASUS
  • Model: ESC4000 G2
  • Interface type: other / other
  • Maximum number of CPUs supported: 2
  • Standard memory: 8GB
  • Hard disk capacity: other capacity
  • Processor clock speed: 2.1GHz
  • After-sales service: Genius
  • Server type: rack

The official three-site service, if you need to change the standard configuration, you can contact our customer service.

  • It comes standard with an Intel Xeon® E5-2620v2 processor (six cores, 2.1GHz, 15MB L3 cache, 7.2GT / s QPI) and can be extended to a two-way processor;
  • Standard 8GB (1x8GB) DDR3 1600 ECC REG memory;
  • Standard with no hard drive;
  • Standard SATA DVD-RW drive;
  • Standard rail

Simple specification statement;

  • CPU : Support two Intel® Xeon® E5-2600v2 Series of processors;
  • Memory: Supported 16 root DDR3 RECC Memory slots, maximum support 512GB ;
  • Memory slots: 16 memory slots (4-channel / CPU, 8-DIMM socket / CPU)
    Memory Capacity : Up to 512GB RDIMM / up to 128GB UDIMM
    Memory Type: Quad channel DDR3 1866/1600/1333/1066/800 RDIMM
    Quad channel DDR3 1866/1600/1333/1066 UDIMM
    Quad channel DDR3 1866/1600/1333/1066 LRDIMM
    Memory Specifications: 32GB, 16GB, 8GB, 4GB, 2GB, 1GB RDIMM
    8GB, 4GB, 2GB, 1GB UDIMM
    32GB, 16GB, 8GB LRDIMM

  • storage: 8 Hot-swappable 3.5 'Hard drive bit; integrated embedded SATA Controller , Intel® Rapid Storage Technology Enterprise (RSTe) (Windows only)
    (Support software RAID 0, 1, 5, 10)
    LSI® MegaRAID (Supports Linux / Windows)
    (Support software RAID 0, 1, 10)

  • Network: Integration Intel® 82574L Dual-port Gigabit server card;
  • I / O Expansion slots: eight full-length full-length PCI-Express 3.0 x16 Slot can be added GPU graphics card / super card, one PCIe Adapter card;
  • Parallel Computing Card:
    Optional NVIDIA Tesla M2050 (memory 3GB)
    Optional NVIDIA Tesla M2070 (memory 6GB)
    Optional NVIDIA Tesla M2090 (memory 6GB)
    Optional NVIDIA Tesla K10 (memory 8GB)
    Supports up to four M2050 / M2070 / M2090 / K10

  • power supply: 1620W by 80PLUS Platinum Certified Hot Plug 1+1 Redundant power supply;
  • Management software: ASWM2.0 Server Management Suite;
  • Other: Optional ASMB6-iKVM Remote management module; optional ASUS PIKE SAS Array card ( Support must be ordered PIKE Slot riser card SKU)
  • size: 750 mm x 444 mm x 88 mm

    Size: 2U rack
  • Thermal performance
    Fan: 7 8CM system fan


ESC4000 G2 supercomputer using CPU + GPU collaborative computing architecture, is ASUS for small and medium-sized cluster customers, new custom supercomputers to provide a single trillion per second computing power, specifically for life sciences, medicine, engineering, financial modeling , Electronic automation and other industries professionals design, while optimizing the cooling system not only ensures the reliability of the whole operation, more effective in reducing machine noise, providing users with a high-performance, high stability of the super-table.

    • Collaborative Computing Acceleration Architecture
      Innovative introduction of GPU computing unit, breaking the traditional single CPU-based computing model, using Intel's latest Xeon processor core and NVIDIA Tesla accelerated computing technology collaboration, so that CPU and GPU perform their duties, CPU is mainly responsible for more good The logical choice, to determine the jump and other responsibilities, and GPU is full-time computing-intensive, highly parallel computing work, making the rational allocation of computing resources, computing power is fully released, the calculation of performance from several times to several hundred times improve.

      Large - scale parallel computing processing core
      Compared to only a few threads at the same time the work of the multi-core CPU, the GPU is the characteristics of the implementation of thousands of threads at the same time, making the system can handle more information flow.Currently, Tesla K10 card has 3072 computing cores, Peak processing speed of 4.5 trillion floating-point per second computing power, through the collaborative scalable architecture, according to the computing needs can be flexible to increase the number of GPU to achieve higher computing power.

      Excellent programming environment
      The CUDA Universal Parallel Computing Architecture enables the GPU to solve complex computational problems, including the CUDA instruction set architecture and the parallel computing engine inside the CPU.C developers can now use the C language to write programs for the CUDA architecture, the C language is the most widely used A high-level programming language written to support CUDA processors with ultra-high performance.

      Computer design automation EDA: SPICE, Verilog, 3D EM and so on
      Engineering science: CAD / CAM / CAE, astrophysics, CFD and so on
      Life Sciences: Molecular Dynamics, Gene Sequencing, Protein Folding, and more
      Oil and gas: seismic data processing, reservoir simulation
      Meteorology: Weather and Ocean Modeling WRF et al