Vent venligst...
Varen er tilføjet indkøbskurven. Se indkøbskurv her
+45 71 745 745 salg@elitecom.dk
Tom Indkøbskurv

AMD RADEON INSTINCT MI25 IN CTLR

Forsiden Komponenter TV- & Grafikkort AMD RADEON INSTINCT MI25 IN CTLR
For at se vore priser skal du være oprettet som kunde: Er du allerede oprettet som kunde skal du logge ind.
AMD RADEON INSTINCT MI25                                  IN CTLR (100-505959)

AMD RADEON INSTINCT MI25 IN CTLR

Varenr.:
100-505959
  • GPU-familie AMD
  • GPU Radeon RX Vega 64
  • Tilslutning PCI Express x16 3.0
  • Videohukommelse 16GB
  • Videohukommelsestype HBM2
  • Hukommelsesbussbredde 2048 bit
  • DVI 0
  • VGA 0
  • HDMI 0
  • Displayport 0
  • USB-C 0
  • Profile Dual Slot
  • Køletype Passiv
Beskrivelse

The Ultimate Solution for Your Computing Needs

Machine Intelligence and Deep Learning Neural Network Training
- High performance FP16 and FP32 compute
- Open software ROCm platform for HPC-class rack scale
- Optimized MIOpen deep learning framework libraries
- Large BAR support for mGPU peer to peer
- Superior compute density and performance per node when combining AMD EPYC™ server processor and Radeon Instinct™ accelerators

HPC Heterogeneous Compute
- Outstanding compute density and performance per node
- Open software ROCm platform for HPC class rack scale
- Open source Linux drivers, HCC compiler, tools and libraries from the metal forward
- Open industry standard support of multiple architectures and industry standard interconnect technologies

- Based on cutting-edge “VEGA” GRAPHICS ARCHITECTURE built to handle big data sets and diverse compute workloads
- 64 nCU COMPUTE UNITS to accelerate demanding workloads
- Up to 12.3 TFLOPS of peak FP32 compute performance to speed up compute intensive machine intelligence
- Up to 24.6 TFLOPS of FP16 peak compute performance for deep learning training applications
- State-of-the-art memory technology: 16GB of HBM2 MEMORY with ECC2 and HIGH BANDWIDTH CACHE CONTROLLER (HBCC)
- Passively cooled, full-height, dual-slot, 300W TDP board power – designed to fit in most standard server designs
- MxGPU for Virtualized Compute Workloads – drive greater utilization and capacity in the data center
- Advanced Remote Manageability Capabilities, for simplified GPU monitoring in large scale systems

Selvom vi gør vort bedste for at give fyldestgørende information, så er billederne kun vejledende, og selve varen er ikke nødvendigvis 100% identisk med det viste billede. Produkter kan være vist med ekstraudstyr der ikke er inkluderet eller i andre form- og farvevarianter. Hvis der er forskel mellem produktoverskrift, beskrivelse og billede, så er det produktoverskriften som gælder. Hvis du er i tvivl, så kontakt os gerne. Vi tager forbehold for trykfejl, ændring af priser og specifikationer uden varsel.