LastAi??Thursday night, Nvidia launched the monstrous, golden Titan V, a graphics card with 12GB of HBM2 memory and over a thousand more CUDA cores than the game-slaying Titan Xp.
Thousand-dollar cards are not uncommon, but Nvidia’s latest, the Titan V, costs $2,999. In return for a ridiculous amount of cash, Nvidia promises you’ll be getting “the most powerful graphics card ever created for the PC.”
For the price, though, users will see a 9x increase in raw power compared to the Titan Xp, the cardai??i??s predecessor, which retailed for ai???onlyai??? $1,299.
The Titan V includes six graphics processing clusters, 80 streaming multiprocessors, 5,120 CUDA cores, and 320 texture units. The card’s base clock speed is set at 1,200MHz with a Boost Clock of 1,455MHz coupled with 12GB of HBM2 RAM running at 850MHz. That translates to 652.8GB/s of memory bandwidth, 110 teraflops of horsepower, and a 384 GigaTexels/sec texture rate.
Itai??i??s worth noting that this isnai??i??t really Nvidiaai??i??s most powerful card yet ai??i?? that honor still belongs to the 112 teraflop Tesla V100, which tends to retail for around $10,000. It is Nvidiaai??i??s most powerful GPU for PCs, though. Both the Titan V and V100 cards seem to have quite a bit in common, including the V100 GPU at their core, though the Titan V features both less memory and a reduced memory bus width.
The launch of the Titan V came as a bit of a surprise. Nvidia CEO Jen-Hsun Huang wasnai??i??t exactly expected to announce new hardware during his keynote at the NIPS conference.
ai???Our vision for Volta was to push the outer limits of high performance computing and AI. We broke new ground with its new processor architecture, instructions, numerical formats, memory architecture and processor links,ai??? said Huang. ai???With TITAN V, we are putting Volta into the hands of researchers and scientists all over the world. I canai??i??t wait to see their breakthrough discoveries.ai???
While you could happy play PUBG with this card (itai??i??s very much a standard PCI-E video card, after all), itai??i??s very much geared toward researchers who need this kind of parallel processing power for running their scientific simulations or who want to build machine learning models (or you could just use it to mine cryptocurrencies, of course).