- Accueil
- PNY A30 Nvidia 24 Gb High Bandwidth Memory 2 (Hbm2) – TCSA30M-PB
PNY A30 Nvidia 24 Gb High Bandwidth Memory 2 (Hbm2)
PNY A30 Nvidia 24 Gb High Bandwidth Memory 2 (Hbm2)
MPN TCSA30M-PB
Réf. W128258213
Niveau de stock
NVIDIA A30 Tensor Core GPU is the most versatile mainstream compute GPU for AI inference and mainstream enterprise workloads. Powered by NVIDIA Ampere architecture Tensor Core technology, it supports a broad range of math precisions, providing a single accelerator to speed up every workload. Built for AI inference at scale, the same compute resource can rapidly re-train AI models with TF32, as well as accelerate high-performance computing (HPC) applications using FP64 Tensor Cores. Multi-Instanc...
Lire la description complèteCaractéristiques TCSA30M-PB
Connectivité
Type d'interface
PCI Express x16 4.0
Design
Form factor
Full-Height/Full-Length (FH/FL)
Hauteur du support
Full-Height (FH)
Nombre de ports
2
Product colour
Beige
Type de refroidissement
Passif
Logistics data
Harmonized System (HS) code
84733020
Mémoire
Bande passante mémoire (max)
933 GB/s
Mémoire Bus
3072 bit
Mémoire carte graphique distincte
24 GB
Type de mémoire de l'adaptateur graphique
High Bandwidth Memory 2 (HBM2)
Package dimensions
Gross Weight (Package, kg)
1,17 kg
Power
Consommation électrique typique
165 Watt
Prises de courant supplementaires
1x 8-pin
Processeur
CUDA
Oui
FireStream
Non
Noyaux CUDA
3804
Processeur graphique
A30
Processeur graphique famille
NVIDIA
Technologie de Traitement en parallèle
Not supported
Product dimensions
Net Weight (Product, kg)
0,9 kg
Product Depth
26,77 cm
Product Height
11,12 cm
représentation / réalisation
DVI dual-link
Non
Synthoniseur TV intégré
Non
Vendor information
Brand Name
Warranty
1 Année (s)
Description
NVIDIA A30 Tensor Core GPU is the most versatile mainstream compute GPU for AI inference and mainstream enterprise workloads. Powered by NVIDIA Ampere architecture Tensor Core technology, it supports a broad range of math precisions, providing a single accelerator to speed up every workload. Built for AI inference at scale, the same compute resource can rapidly re-train AI models with TF32, as well as accelerate high-performance computing (HPC) applications using FP64 Tensor Cores. Multi-Instance GPU (MIG) and FP64 Tensor Cores combine with fast 933 gigabytes per second (GB/s) of memory bandwidth in a low 165W power envelope, all running on a PCIe card optimal for mainstream servers.
Documents
*Les données produit ci-dessus sont fournies par Icecat. A cet égard, EET ne peut être tenu responsable des erreurs.