NVIDIA Supercomputing GPU TITAN V Unveiled

👤by Michael Pabia Comments 📅14.12.2017 11:21:51

NVIDIA reveals the TITAN V, its newest supercomputing Volta-powered GPU delivering 110 Teraflops of deep learning power which is 900% more than its predecessor. The TITAN V, powered by the new Volta architecture, sports a major redesign of the streaming multiprocessor that’s the core of the GPU. The new architecture greatly increased the energy efficiency of the GPU compared to the Pascal architecture. This enables dramatic boosts in performance in the same power envelope.

New Tensor Cores designed specifically for deep learning deliver up to 900% higher peak teraflops. With independent parallel integer and floating-point data paths, Volta is also much more efficient on workloads with a mix of computation and addressing calculations. Its new combined L1 data cache and shared memory unit significantly improve performance while also simplifying programming.

Fabricated on a new TSMC 12-nanometer FFN high-performance manufacturing process customized for NVIDIA, TITAN V also incorporates Volta’s highly tuned 12GB HBM2 memory subsystem for advanced memory bandwidth utilization.

Watch the NVIDIA TITAN V Introduction video:

NVIDIA TITAN V Specifications
Graphics Processing Clusters: 6
Streaming Multiprocessors: 80
CUDA Cores (single precision): 5120
Texture Units: 320
Base Clock (MHz): 1200
Boost Clock (MHz): 1455
Memory Clock (MHz): 850
Memory Data Rate: 1.7 Gbps
L2 Cache Size: 4608K
Total Video Memory: 12288 MB HBM2
Memory Interface: 3072-bit
Total Memory Bandwidth: 652.8 GB/s
Total Memory Bandwidth: 652.8 GB/s
Texture Rate (Bilinear): 384 GigaTexels/sec
Recommended PSU: 600 Watts

Pricing and Availability
The NVIDIA TITAN V supercomputing GPU is now available for pre-order with an MSRP of £2,700.00. Estimated shipping date starts on the 30th of December, 2017.