⋮    ⋮  

Watch NVIDIA’s Computex 2017 Keynote Livestream Here


Rumors emerged last week that NVIDIA would be debuting a new enthusiast Volta Titan graphics card at computex this week after photos of the alleged new card leaked out.  The company officially announced today via twitter that it's going to be holding a keynote headlined by President & CEO Jensen Huang at 8:30 PM PST 29th of May.

NVIDIA GTX 1170 Alleged Benchmark Leaked, Faster Than 1080 Ti

NVIDIA's Mysterious Volta Titan Enthusiast Graphics Card

The photograph above was allegedly leaked by an NVIDIA intern last week. It shows a black graphics card with gold accents and "TITAN" engraved on the side. The card has 8+6pin PCIE power connectors and  notably features an NVLNK interface, something unusual for a TItan graphics card and is only available on NVIDIA's professional Tesla and Quadro accelerators.

The photographed "TITAN" card has the same aesthetic look and color scheme of NVIDIA's recently announced Volta based Tesla accelerators. This has led many to believe that this card will likely join NVIDIA's new roster of Volta products as a workstation and/or enthusiast gaming card. According to the rumors surrounding this mysterious TITAN card NVIDIA is expected to introduce it at computex.

NVIDIA's graphics card fitted with NVLINK interfaces have so far all featured HBM2 rather than GDDR memory. This in addition to the fact that GDDR6, which is set to power gaming oriented Volta GeForce graphics cards, isn't currently available and won't be until next year indicates that this card features HBM2. Whether this card will in fact make its debut tomorrow or not remains to be seen, we'll know soon enough. In the mean time take these rumors with a grain of salt.
Tesla ProductTesla K40Tesla M40Tesla P100Tesla V100
GPUGK110 (Kepler)GM200 (Maxwell)GP100 (Pascal)GV100 (Volta)
FP32 Cores / SM1921286464
FP32 Cores / GPU2880307235845120
FP64 Cores / SM6443232
FP64 Cores / GPU9609617922560
Tensor Cores / SMNANANA8
Tensor Cores / GPUNANANA640
GPU Boost Clock810/875 MHz1114 MHz1480 MHz1455 MHz
Peak FP32 TFLOP/s*5.046.810.615
Peak FP64 TFLOP/s*1.682.15.37.5
Peak Tensor Core TFLOP/s*NANANA120
Texture Units240192224320
Memory Interface384-bit GDDR5384-bit GDDR54096-bit HBM24096-bit HBM2
Memory SizeUp to 12 GBUp to 24 GB16 GB16 GB
L2 Cache Size1536 KB3072 KB4096 KB6144 KB
Shared Memory Size / SM16 KB/32 KB/48 KB96 KB64 KBConfigurable up to 96 KB
Register File Size / SM256 KB256 KB256 KB256KB
Register File Size / GPU3840 KB6144 KB14336 KB20480 KB
TDP235 Watts250 Watts300 Watts300 Watts
Transistors7.1 billion8 billion15.3 billion21.1 billion
GPU Die Size551 mm²601 mm²610 mm²815 mm²
Manufacturing Process28 nm28 nm16 nm FinFET+12 nm FFN