コンテンツ

  1. HOME
  2. Services
  3. Supercomputer
  4. Large-scale Supercomputer Systems
  5. System Configurations
  6. System Specification

System Specification

Contents

System Configurations

The new system is expected to consist of three types of systems based on the concept of a current system (System A, B and C), a new system equipped with an accelerator (System G), and a storage system.The CPU in systems A, B, and C are all Intel Xeon of the same generation, however there are differences in memory speed and capacity.System A is a configuration that emphasizes memory speed, System B is a configuration with a good balance between capacity and performance, and System C is a configuration that emphasizes memory capacity.

system_2022

Camphor 3 (System A)

Specifications Machine DELL PowerEdge C6620
Node 1,120
Performance 7.63 PFLOPS
Total Memory Capacity 140 TiByte
Node Performance 6.80 TFLOPS
Processor 2
Memory 128 GiByte
Memory bandwidth 3.2 TByte/sec (HBM2e Memory)
Injection Bandwidth 50 GByte/sec
Processor Processor Intel Xeon CPU Max 9480
Architecture x86-64
Clock 1.9 GHz
Number of Cores 56
Performance 3.4 TFLOPS

Laurel 3 (System B)

Specifications Machine DELL PowerEdge C6620
Node 370
Performance 2.65 PFLOPS
Total Memory Capacity 185 TiByte
Node Performance 7.17 TFLOPS
Processor 2
Memory 512 GiByte
Memory bandwidth 614 GByte/sec
Injection Bandwidth 25 GByte/sec
Processor Processor Name Intel Xeon Platinum 8480+
Architecture x86-64
Clock 1.9 GHz
Number of Cores 56
Performance 3.4 TFLOPS

Cinnamon 3(System C)

Specifications Machine DELL PowerEdge C6620
Node 16
Performance 114.6 TFLOPS
Total Memory Capacity 32 TiByte
Node Performance 7.17 TFLOPS
Processor 2
Memory 2 TiByte
Memory bandwidth 563 GByte/sec
Injection Bandwidth 25 GByte/sec
Processor Processor Name Intel Xeon Platinum 8480+
Architecture x86-64
Clock 2.0 GHz
Number of Cores 56
Performance 3.59 TFLOPS

Gardenia (System G)

Specifications Machine DELL PowerEdge XE8545
Node 16
Performance(Processor) 42.59 TFLOPS (double precision)
Memory (Processor) 8.19 TiB
Performance(Accelerator) 20.2 PFLOPS (half-precision)
Memory (Performance) 5.12 TiB
Node
Performance(Processor)
2.66 TFLOPS (double precision)
Memory(Processor) 512 GiByte
Memory Bandwidth (Processor) 409 GByte/sec
Performance(Accelerator) 78 TFLOPS or more (double precision)
1,128 TFLOPS or more (half-precision)
Memory(Accelerator) 320 GiByte
Memory Bandwidth (Accelerator) 8.15 TByte/sec
Injection Bandwidth 50 GB/sec
Processor Processor AMD EPYC 7513
Architecture x86-64
Clock 2.6 GHz
Number of Cores 32
Performance(double precision) 2.66 TFLOPS
Accelerator Accelerator NVIDIA A100 80GB SXM
Performance(double precision) 19.5 TFLOPS
Performance(half-precision) 312 TFLOPS
Memory 80 GiB
Memory Bandwidth 2,039 GB/sec

Cloud System

Specifications Node variability
Node Performance 3.45 TFLOPS
Processor 2
Memory 512 GiByte
Processor Processor Intel Xeon Gold 6354
Architecture x86-64
Clock 3.0 GHz
Number of Cores 18
Performance 1.72 TFLOPS

Storage System

    Machine DDN Exascaler
    Physical capacity 40.32 PB
    Effective capacity 31.99 PB
    Data transfer performance 280 GB/sec

    Flash Storage System

      Machine DDN Exascaler
      Physical capacity 4.06 PB
      Effective capacity 3.12 PB
      Data transfer performance 768 GB/sec

        Software

        New software stack is shown in the following figure.

        software_stack

         

        Copyright © Institute for Information Management and Communication, Kyoto University, all rights reserved.