NVIDIA Tesla T4 GPU Accelerator
NVIDIA Cloud and Data Center GPU Product
Manufacturere Part Number:
NVIDIA (P/N: 900-2G183-0000-001) TESLA T4, Passive cooling
Features and Benefits:
The NVIDIA T4 is a single-slot, low-profile, 6.6-inch PCI Express Gen3 Universal Deep Learning Accelerator based on the TU104 NVIDIA graphics processing unit (GPU). The T4 has 16 GB GDDR6 memory and a 70 W maximum power limit. The T4 is offered as a passively cooled board that requires system air flow to operate the card within its thermal limits. NVIDIA supports x8 and x16 PCI Express for the T4.
NVIDIA T4 is a universal deep learning accelerator ideal for distributed computing environments. Powered by NVIDIA Turing™ Tensor Cores, T4 provides revolutionary multi-precision performance to accelerate deep learning and machine learning training and inference, video transcoding, and virtual desktops. As part of the NVIDIA AI Platform, T4 supports all AI frameworks and network types, delivering dramatic performance and efficiency that maximize the utility of at-scale deployments.
SPECIFICATIONS:
GPU clocks
Base: 585 MHz
Maximum Boost: 1590 MHz
VBIOS
EEPROM size: 8 Mbit
UEFI: Supported
PCI Express interface: PCI Express 3.0 ×16 x8
Thermal cooling solution: Passive
Total board power: 70 W (default)
Maximum memory clock: 5001 MHz
Memory size: 16 GB
Memory bus width: 256 bits
Peak Memory bandwidth: Up to 320 GBytes/s
Weight:
Board: 301 Grams
Full Height Bracket with screws: 17 Grams
Half Height Bracket with screws: 10 Grams
Features Tesla K80¹ Tesla K40 GPU 2x Kepler GK210 1 Kepler GK110B
Peak double precision floating
point performance 2.91 Tflops (GPU Boost Clocks)
1.87 Tflops (Base Clocks) 1.66 Tflops (GPU Boost Clocks)
1.43 Tflops (Base Clocks)
Peak single precision floating
point performance 8.74 Tflops (GPU Boost Clocks)
5.6 Tflops (Base Clocks) 5 Tflops (GPU Boost Clocks)
4.29 Tflops (Base Clocks)
Memory bandwidth (ECC off)² 480 GB/sec (240 GB/sec per GPU) 288 GB/sec
Memory size (GDDR5) 24 GB (12GB per GPU) 12 GB
CUDA cores 4992 ( 2496 per GPU) 2880 - See more at: http://www.nvidia.com/object/tesla-servers.html#sthash.ZmsPP43F.dpuf
