Sign in
LOGIN

USA
  • Česky
  • Slovenština
  • English
  • Polski
  • Hungary
USD
0
0 Your shopping cart is empty
Components Graphics cards Server GPU NVIDIA Pascal NVIDIA Tesla P100 12GB CoWoS HBM2 PCIe 3.0 - Passive Cooling, GPU-NVTP100-12

NVIDIA Tesla P100 12GB CoWoS HBM2 PCIe 3.0 - Passive Cooling, GPU-NVTP100-12

BUS: PCI-E 3.0 16x Memory size: 12 GB Stream processors: 3584 Theoretical performance: TFLOP

All NVIDIA Ampere, NVIDIA Grace Hopper, and NVIDIA Ada Lovelace GPU architectures are subject to a non-cancellable, non-returnable (NCNR) period of 52 weeks. Additionally, the product is subject to sanctions for certain countries and the end customer must be documented.

We can supply these GPU cards directly and with an individual B2B price. Contact us with your inquiry today.

Product code 214.151624
Part number GPU-NVTP100-12
EAN 672042242450
Manufacturer NVIDIA
Availability Not in stock
Warranty 24 months
Weight 1 kg
The price includes all legal fees
$ 4,978.41
pc

Detailed information

NVIDIA Tesla

Tesla products from the NVIDIA company introduce a line of computational graphics processors that are very similar to the NVIDIA Quadro series (they usually use the same chip). However, they have an isolated display interface. They're also available in passively-cooled form-factors, which are specifically appropriate for use in servers (rack-mounts).

CUDA Technology

Users of professional applications can, thanks to the CUDA architecture, use graphical CUDA stream processors. Thanks to this, it is possible to use the raw performance of a graphics card for specific calculations, which can significantly increase work speed compared to the use of a traditional processor, which are significantly limited by the lower number of cores.

Product Specifications

Stream Cores 3584 CUDA Cores
PCIe x16 Interconnect Bandwidth 32 GB/s
CoWoS HBM2 Stacked Memory Capacity 12 GB
CoWoS HBM2 Stacked Memory Bandwidth 540 GB/s
Max Memory Bandwidth 540 GB/s
Peak Double Precision floating point performance (GFLOP) 4.7 TeraFLOPS
Peak Single Precision floating point performance (GFLOP) 9.3 TeraFLOPS
Half-Precision Performance 18.7 TeraFLOPS
NVIDIA CUDA™ Technology Yes
Cooling Passive
Dual Slot Yes
Wattage 250W

Parameters

Product line Tesla
Number of stream processors 3584
Power consumption (W) 250
Architecture Pascal
Monitor output None
Interface PCI-E 3.0 16x
Gigabytes of memory 12
Cooling type Passive
Memory type HBM2
Slot count 2
Profile FH

Price development



  1. The only Supermicro integrator in Czechia, Slovakia and Poland
  2. Personal approach and tailor-made servers
  3. NBD warranties on-site
  4. Hosting, VPS and IT infrastructure
  5. Pre-sales & After-sales support