Adilaris 
Nvidia’s new Pascal architecture has been dominating charts recently with their GTX 1000 series; however the graphics company is far from done as the new version of the Titan X has been revealed and is about 60% faster.
Here’s some specs:
- 12-billion transistors
- 11 TFLOPs FP32 (32-bit floating point)
- 44 TOPS INT8 (new deep learning inferencing instruction)
- 3,584 CUDA cores at 1.53GHz (versus 3,072 CUDA cores at 1.08GHz in previous TITAN X)
- High performance engineering for maximum overclocking
- 12GB of GDDR5X memory (480GB/s)
A point to note is that this also uses GDDR5X rather than HBM2 as the supply for the new memory type is still out of reach sadly; but should start popping up next year.
Now while as much as any of us would love to own one of these babies; it comes at a whopping cost of $1,200. Obviously, this isn’t really meant for the average gamer as it’s main market is 3d rendering studios. Still, it’s amazing to see a single-core chip that can pump out 11 Teraflops.
