Breadcrumb navigation

SX-Aurora TSUBASA VE-Card

Vector Engine

Model Overview

Ideal for AI, big data, and system embedded applications
Application fields: product inspection, medical image processing, demand forecasting, weather forecasting, radar analysis, etc.

Card image  
Model Name Type 20B-P

Basic Core Specifications

Operating frequency (GHz) 1.600
Theoretical operation performance (GFLOPS) Double precision 307
Theoretical operation performance (GFLOPS) Single precision 614

Basic Processor Specification

Number of cores/processor 8
Theoretical calculation performance (TFLOPS) Double Precision 2.45
Theoretical calculation performance (TFLOPS) Single Precision 4.91
Memory bandwidth (TB/s) 1.53
Cache capacity (MB) 16
Memory capacity (GB) 48

Form Factor

Dimensions and weight 266.46mm(W) x 111.15mm(H) x 37.77mm(Th), 0.85kg
When extender is used 311.46mm (card + straight extender)
Auxiliary power connector, connection position CPU 8pin
Card Dimensions  

Eligible server for VE installation

OS Designated version of Red Hat Linux Enterprise
new windowClick here for a list of supported OS.
Certified Server Please refer to this new windowlist of certified servers

Installation specifications

Power Consumption 300W or less
Cooling Method Air Cooling (passive)
Temperature Conditions -40°C to 70°C
Humidity Condition 10%RH to 90%RH
Temperature Condition During Operation 10°C to 35°C
Operating Humidity 5%RH to 95%RH
Certification and Safety Standards

EMIS standards
UL(c-UL) 62368-1, IEC/EN 62368-1(CE marking)


FCC, ICES-003, VCCI Class A
Accessory Information Vector Engine Card
Card extender and screws
Startup Guide
ECC Yes
Bus PCIe gen3 x16

Software

By using NEC's original compiler the vector engine is easy to use.

Standard Software Vector Engine control software and driver
Software Development Support NEC Software Development Kit for Vector Engine, NEC MPI, NEC MPI/Scalar-Vector Hybrid