TESLA K40 Card

TESLA K40 Card

Thông số kĩ thuật

Memory Size 12 GB GDDR5
Memory Interface 384-bit
Memory Bandwidth (ECC off)) 288 GB/s
CUDA Cores 2880
System Interface PCI Express 3.0 x16
Processor core clock 745 MHz
Memory clock 3.0 GHz
Cache L1 & L2
Maximum Consumption 235 W
Number of  GPUs 1 × GK110B
Energy Star Enabling Yes
Conformité Européenne (CE) Yes
Thermal Solution Ultra-quiet Active Fansink
Form Factor 110 mm (H) × 265 mm (L) – Dual Slot, Full-Height
Connectors 1 × 6-pin PCI Express power connectors

1 × 8-pin PCI Express power connectors
Dynamic Parallelism Yes
Hyper-Q Yes 
GPU Computing Applications Reservoir simulation
CAE (structural analysis)
Molecular dynamics, Numerical analytics
Computational visualization (ray tracing)
Peak double precision floating point performance 1.43 Tflops
Peak single precision floating point performance 4.29 Tflops
System Workstations
Compatible with Windows Vista, Windows 7 – 64-bit
Linux 32-bit and 64-bit
Fedora 12
RHEL 5.4 Desktop
Ubuntu 9.10 Desktop
RHEL 4.8 Desktop (64-bit only)
OpenSUSE 11.2
Available extender brackets
Long Extender with Offset
Short Extender with Offset
Flat Extender (short)
Run your most demanding scientific models on NVIDIA® Tesla® GPU Accelerators. Based on the NVIDIA Kepler™, Tesla GPUs are designed to deliver faster, more efficient compute performance. With the introduction of Tesla K40 GPU Accelerators, you can run big scientific models on its 12GB of GPU accelerator memory, capable of processing 2x larger datasets and ideal for big data analytics. It also outperforms CPUs by up to 10x with its GPUBoost feature, converting power headroom into user-controlled performance boost. Kepler based Tesla GPU Accelerators are also available for servers.

Đánh giá

Chưa có đánh giá nào.

Hãy là người đầu tiên nhận xét “TESLA K40 Card”

Email của bạn sẽ không được hiển thị công khai. Các trường bắt buộc được đánh dấu *