So this is where all the rumors end, GK110 is not GeForce card, it’s brand new Tesla K20 GPU, which is coming in fourth quarter of 2012 – as announced today by NVIDIA during GTC 2012.New chip is built with 7.1 billion transistors.
NVIDIA is preparing two Tesla GPUs, one is Tesla K10, based on dual-GK104 chips, which is to be devoted to high efficient computing in oil and gas exploration and defense industry. Card is based on dual-GK104 GPUs and has a memory bandwidth of 320 GB/s.
Next is Tesla K20, the GK110 GPU which is coming in Q4 of this year. It will deliver three times more double precision performance compared to Fermi architecture-based Tesla cards.
First GK110 GPUs will be incorporated into Titan Supercomputer at the Oak Ridge National Laboratory in Tennessee and the Blue Waters system at the National Center for Supercomputing Applications a the University of Illinois.
| NVIDIA TESLA K10 | NVIDIA TESLA K20 | |
|---|---|---|
| Peak double precision floating point performance (board) | 0.19 TFlops | TBA |
| Peak single precision floating point performance (board) | 4.58 TFlops | TBA |
| Number of GPUs | 2 x GK104 | GK110 |
| CUDA Cores | 2 x 1536 | ~ 2880 |
| Memory size per board (GDDR5) | 8 GB | ~ 12 GB |
| Memory bandwidth per board (ECC off) | 320 GB/s | TBA |
| GPU Computing Applications | Seismic, Image, Signal Processing, Video analytics | CFD, CAE, Financial computing, Computational chemistry and Physics, Data analytics, Satellite imaging, Weather modeling |
| Architecture Features | SMX | SMX, Dynamic Parallelism, Hyber-Q |
| System | Servers only | Servers and Workstations |
| Avaiable | May 2012 | Q4 2012 |
New Kepler GK110 feature new technologies:
SMX
Delivers more processing performance and efficiency through this new, innovative streaming multiprocessor design that allows a greater percentage of space to be applied to processing cores versus control logic
Dynamic Parallelism
Simplifies GPU programming by allowing programmers to easily accelerate all parallel nested loops – resulting in a GPU dynamically spawning new threads on its own without going back to the CPU
Hyper-Q
Slashes CPU idle time by allowing multiple CPU cores to simultaneously utilize a single Kepler GPU, dramatically advancing programmability and efficiency
You can check more detailed information here [PDF].
“Fermi was a major step forward in computing,” said Bill Dally, chief scientist and senior vice president of research at NVIDIA. “It established GPU-accelerated computing in the top tier of high performance computing and attracted hundreds of thousands of developers to the GPU computing platform. Kepler will be equally disruptive, establishing GPUs broadly into technical computing, due to their ease of use, broad applicability and efficiency.”
NVIDIA Tesla K10
we’re announcing two products today, two kepler: Tesla K10 dedicated to seismic analysis where most valuable resource is bandwidth. it has 3x single precision of today’s fermi tesla and 1.8x the memory bandwidth
NVIDIA Tesla K20
second tesla, k20 is focused on double precision: 3x double precision of fermi, includes hyper q, dynamics parallelism, for stuff like physics, quantum chemistry, computational finance
You call follow liveblog of NVIDIA’s CEO keynote here