Bookmark and Share


Nvidia Corp. this week formally announced its next-generation Tesla solutions for high-performance computing markets based on code-named Fermi architecture. The company will only be able to start shipments of Tesla 20-series in the second quarter of next year, which further emphasizes that the new Fermi-G300 chip is dramatically late-to-market.

The family of Tesla 20-series solution includes:

  • Tesla C2050 and C2070 GPU computing processors:
    • Single GPU PCI Express 2.0 cards for workstation configurations;
    • Up to 3GB and 6GB (respectively) on-board GDDR5 memory. With ECC enabled, user available memory will be 2.625GB for a C2050 and to 5.25GB for a C2070;
    • Double precision performance in the range of 520GFlops – 630GFlops.
  • Tesla S2050 & S2070 GPU computing systems:
    • Four Tesla GPUs in a 1U system product for cluster and datacenter deployments;
    • Up to 12 GB and 24 GB (respectively) total system memory on board GDDR5 memory. With ECC enabled, user available memory will be 10.5GB for an S2050 and 21GB for an S2070;
    • Double precision performance in the range of 2.1TFlops – 2.5TFlops.

The Tesla C2050 and C2070 products will retail for $2499 and $3999 and the Tesla S2050 and S2070 will retail for $12 995 and $18 995. Products will be available in Q2 2010. For more information about the new Tesla 20-series products, visit the Tesla product pages.

The flagship Fermi graphics processor will feature 512 stream processing engines (which are organized as 16 streaming multi-processors with 32 cores in each) that support a type of multi-threading technology to maximize utilization of cores and deliver extreme computing power. Each stream processor has a fully pipelined integer arithmetic logic unit (ALU) and floating point unit (FPU). The top-of-the-range chip contains 3 billion of transistors, features 384-bit memory GDDR5 memory controller with ECC and features rather unprecedented 768KB unified level-two cache as well as rather complex cache hierarchy in general. Naturally, the Fermi family is compatible with DirectX 11, OpenGL 3.x and OpenCL 1.x application programming interfaces (APIs). The new chips will be made using 40nm process technology at TSMC.

It is interesting to note that Nvidia has always claimed that its new graphics processor – which is known under G300, GT300 and NV60 code-names – was due to be released commercially already in Q4 2010. However, first Nvidia chief executive officer said that the company would only ramp up production of Fermi graphics processing units (GPUs) in the first quarter of the company’s fiscal year 2011, and then this week Nvidia said that “as previously announced, the first Fermi-based consumer (GeForce) products are expected to be available first quarter 2010”.

There is a clear reason why Nvidia is announcing the new Tesla solutions up to six month before actual shipments: the company needs to attract maximum attention to its high-performance computing options. Both Advanced Micro Devices and Intel Corp. – the companies which processors power the vast majority of super computers now – are either readying or offering GPUs for HPC market segment and they may potentially have a number of advantages over Nvidia.

Despite of the fact that Nvidia is generally a newbie on the market of super computers, it does have followers.

“Nvidia has deployed a highly attractive architecture in Fermi, with a feature set that opens the technology up to the entire computing industry,” said Jack Dongarra, director of the Innovative Computing Laboratory at the University of Tennessee and co-author of LINPACK and LAPACK.

Tags: Nvidia, Tesla, Fermi, GT300, GPGPU


Comments currently: 7
Discussion started: 11/17/09 05:24:30 PM
Latest comment: 11/19/09 12:07:53 PM
Expand all threads | Collapse all threads


I keep on hearing this "Nvidia's L2 cache is a novel concept" line. I'm pretty sure it's out of a press release because it's there verbatim on every Nvidia plug I see. Just for the record, it isn't novel. ATI's 4800 series has 128 KB of L2 and their 5800 series has 256 KB. Furthermore cache isn't very important in a GPU, as GPU's work mainly on large data sets. That's why a GPU's speed is, in part, so dependent on the memory speed.
PS I thought you guys were experts?
0 0 [Posted by: siuol11  | Date: 11/17/09 05:24:30 PM]

The nvidias fermi L2 cache is unified for all shader clusters while ati-s L2 cache is divided to 4 for all shader clusters (and its much smaler) for your expertise.
And without cache with several hundred GB/s agregated bandwith the shaders would stall hundreds of clock cycles with just memory acces. Those large datasets are computed paralel trough each pixel many times.
0 0 [Posted by: Zool  | Date: 11/18/09 07:02:12 AM]

I'm aware Zool. My point is that a) Nvidia's cache hierarchy may be unified, but having L2 isn't unique to their designs, and b) although cache is important, increased cache sizes won't necessarily lead to increased performance... You still need a high-speed memory link.
Also, I think you mean "for your information"
0 0 [Posted by: siuol11  | Date: 11/18/09 08:03:15 AM]

Actualy the unified L2 cache will be very efective in GPUGP for tesla cards where on 768KB data all shader cores can work equaly.
But it seems it wont be even near the agregated bandwith of the divided L2 cache in ATI cards becouse of this. And for graphics paralel nature of work trough each pixel the unified or divided cache should give litle advantage. Mainly bandwith counts there.
Thats the reason why all gpus for graphic usualy worked quite well without unified cache. (gpu-s used caches all the time)
Also 512 shaders accesing one 768KB L2 cache is quite more complicated than ati-s or previous nvidias designs.
0 0 [Posted by: Zool  | Date: 11/18/09 08:13:34 AM]

So, basically you just proved that it's not novel concept after all.
0 0 [Posted by: CPUGuy  | Date: 11/18/09 08:52:05 AM]
- collapse thread

Still the unified L2 cache in gpu is novel concept with its pros and cons and no other gpu has it.
0 0 [Posted by: Zool  | Date: 11/18/09 11:20:26 AM]
Someone gets it! thank you!
0 0 [Posted by: siuol11  | Date: 11/19/09 12:07:53 PM]


Add your Comment

Related news

Latest News

Wednesday, November 5, 2014

10:48 pm | LG’s Unique Ultra-Wide Curved 34” Display Finally Hits the Market. LG 34UC97 Available in the U.S. and the U.K.

Wednesday, October 8, 2014

12:52 pm | Lisa Su Appointed as New CEO of Advanced Micro Devices. Rory Read Steps Down, Lisa Su Becomes New CEO of AMD

Thursday, August 28, 2014

4:22 am | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

Wednesday, August 27, 2014

1:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

10:41 am | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture