Kepler GK110 Revision B Graphics Architecture

Technology & Specifications (Reference)

These charts tend to get a little repetitive as the GPUs are all based on the same silicon and architecture, but here we go. The GeForce GTX 780 Ti is, as stated, based on Titan which has GK110 Kepler GPU architecture, the Ti is using the revision B of GK110. The chip is big in size and based on the 28nm fabrication node. But when I say big I am not joking as it has 7.1 Billion transistors tucked away in a 45 mm × 45 mm 2397-pin S-FCBGA chip. That's a 561 mm² die size.

The GPU on that 10.5 inches / 27 CM long dual-slot GeForce GTX 780 Ti graphics card however now comes with an impressive 2880 CUDA (shader) cores and has 7,100 Million transistors.

That shader ammount is amongst the biggest differentials together with ROP and TMU count:

• GeForce GTX 780 has 2304 shader processors and 3 GB of graphics memory.
• GeForce GTX Titan has 2688 shader processors and 6 GB of graphics memory.
• GeForce GTX Ti has 2880 shader processors and 3 GB of graphics memory

The product is obviously PCI-Express 3.0 ready and has a TDP of around 250W with a typical idle power draw of 10 Watts. That TDP is a maximum overall, and on average your GPU will not consume that amount of power. But let me first show you the GK110 GPU die:
 

NVIDIA GK110 Kepler architecture GPU - you can see 15 sets of SMX clusters / 5 GPC clusters, for GeForce GTX 780 Ti all of them are enabled.

The GK110B is based off the Kepler architecture, as such you will get the standard pre-modelled SMX clusters of 192 shader processors per cluster. Out of the 15 available, there are 15 active SMX clusters for the GTX 780 Ti, times 192 shader processors which thus, offers you 2880 shader processors. Opposed to Titan however there is a distinct difference with extra double precision units, but we'll talk about that on the next page though. But to make a bold comparison, the GeForce GTX 680 which many of you guys have, have 1536 of these shader processors. We'll get more in-depth into the architecture on the next page though. As far as the memory specs of the GK110B Kepler GPU are concerned, the boards will feature a 384-bit memory bus connected to a 3 GB of GDDR5 video buffer memory, AKA VRAM AKA your framebuffer AKA graphics memory for the GTX 780 Ti. On the memory controller side of things you'll see that the reference memory clock (effective data-rate) is now set at 7 GHz / Gbps. This boils down to an exotic memory bandwidth of no less than 336 GB/s on that 384-bit memory bus.

The GeForce GTX 780 Ti is DirectX 11.2 ready. With Windows 8, 7 and Vista also being DX11.1 and 11.2 ready with game compatibility to take advantage of DirectCompute, multi-threading, hardware tessellation and the latest shader 5.0 extensions. For your reference here's a quick overview of some past generation high-end GeForce cards.

For Kepler overall, Nvidia kept their memory controllers GDDR5 compatible. Memory wise, Nvidia has nice large memory volumes available due to their architecture, we pass 2 GB as standard these days for most of Nvidia's series 600 graphics cards. The 3 GB on the GTX 780 Ti however should be plenty. The hardware engineers of Nvidia reworked the memory subs system quite a bit, enabling much higher memory clock frequency speeds compared to previous generation GeForce GPUs. The result is this memory speeds up-to 7 Gbps. Each memory partition utilizes one memory controller on the respective GPU, Titan has a total board memory of 6 GB and that's 24 pieces of 64M × 16 GDDR5, SDRAM whilst GTX 780 has a total board memory of 3 GB and that's 12 pieces of 64M × 16 GDDR5, SDRAM

• The GTX 580 has six memory controllers (6x256MB) = 1536 MB of GDDR5 memory
• The GTX 680 has four memory controllers (4x512MB) = 2048 MB of GDDR5 memory
• The GTX 780 has six memory controllers (6x512MB) = 3072 MB of GDDR5 memory
• The GTX 780 Ti has six memory controllers (6x512MB) = 3072 MB of GDDR5 memory
• The GTX Titan has six memory controllers (6x1024MB) = 6144 MB of GDDR5 memory