I was just wondering if the good people at Bakerlabs have any development using either the Nvidia Telsa or AMD Firestream HPC GPU's on the horizon. As opposed to what F@H have done with the ATI GPU's these are dedicated platforms for HPC.

500GFLOPS from one ATI Firestream 2GB card is impressive, you'd get some serious crunching going on if some dev was done for running on either the Nvidia or ATI HPC platforms.

Just a thought... not sure of its viability but seems like a better option than having to use standard GPU's and live with all the driver issues like the folks at F@H have.

AMD Delivers First Stream Processor with Double Precision Floating Point Technology

Advanced Micro Devices today announced the AMD FireStream 9170 Stream Processor and an accompanying Software Development Kit (SDK) designed to harness the massive parallel processing power of the graphics processing unit (GPU). AMD leveraged its unique collective expertise in both GPUs and CPUs to deliver the first integrated hardware and software development solution that meets the needs of the demanding high-performance computing (HPC) market. AMD plans to deliver the FireStream 9170 and supporting SDK to market in the first quarter of 2008. With this launch AMD expects to achieve another important milestone on the path to Accelerated Computing by delivering the first in a series of next-generation heterogeneous compute architectures.


“With a broad range of customer engagements underway, notably customers in the oil and gas, financial and engineering analysis industries, AMD is delivering on its vision of Accelerated Computing with breakthrough benefits for our enterprise customers,” said Rick Bergman, Senior Vice President and General Manager, Graphics Products, AMD. “Leveraging the immense graphics processing capabilities acquired from ATI and the HPC domain expertise of AMD, we are developing strong relationships with system vendors and the supporting technology eco-system to deliver processing innovation through an open platforms approach.”

AMD FireStream 9170
The AMD FireStream 9170 will be the world’s first Stream GPU with double-precision floating point technology tailored for scientific and engineering calculations. Competitively priced at an MSRP of $1999 USD, it features up to 500 GFLOPS of compute power, rivalling many of today’s supercomputers, and providing dramatic acceleration for critical algorithms. This second generation Stream Processor is built with 55 nm process technology and consumes less than 150 watts of power – delivering an exceptional performance per watt. In addition, the reduced heat dissipation allows it to function in dense design configurations. The FireStream 9170 is a single card solution with two GB of onboard GDDR3 memory to compute large datasets without CPU traffic. The asynchronous direct memory access (DMA) ensures data can flow freely without interrupting the stream processor or CPU.

“GPUs have long been known for their immense parallel processing performance but many challenges still remain in driving widespread customer adoption for general purpose compute,” said Jon Peddie, President, Jon Peddie Research. “Leveraging its unique capabilities in high-performance CPU and GPU technologies, AMD is well positioned to drive an integrated hardware and software proposition that can deliver the best of both processing worlds to its HPC customers.”

AMD FireStream SDK
The AMD FireStream SDK is designed to deliver the tools developers need to create and optimize applications on AMD Stream processors. Built using an open platforms approach, the AMD FireStream SDK allows developers to access key Application Programming Interfaces (APIs) and specifications, enabling performance tuning at the lowest level and development of third party tools. Building on AMD’s Close to the Metal (CTM) interface introduced in 2006, the Compute Abstraction Layer (CAL) provides low-level access to the GPU for development and performance tuning along with forward compatibility to future GPUs. For high-level development, AMD is announcing Brook+, a tool providing C extensions for stream computing based on the Brook project from Stanford University. In addition, AMD also plans to support the AMD Core Math Library (ACML) to provide GPU-accelerated math functions, and the COBRA video library accelerates video transcode. Also available are third-party tools from top industry partners including RapidMind and Microsoft.

In addition, AMD is now a charter participant in HP’s new HPC Accelerator Program, offering HP customers best practices and guidance for these technologies, and ensuring that accelerator hardware and software is qualified for HP servers running HPC applications.

“As innovative new HPC technologies like Stream Computing emerge, it is imperative we work with our partners to ensure an open systems approach to enable new levels of processing efficiency and performance,” said Winston Prather, vice president and general manager of HPC at HP. “As part of HP’s new HPC Accelerator program, we’re working closely with AMD and our customers to deliver an optimal mix of hardware innovation and open, collaborative development environments to ensure delivery of best-in-class HPC platforms.”

Source: Forbes


TechPowerUp

---

Yup thats what I'm talking about... so any official word as to when/if we will ever see a BOINC client developed for this platform?

Considering that my multiple posts about gaming consoles running Rosetta code have been ignored by the Project, I suspect that for even asking the question, you too will be snubbed.

Apparently the "good people at Bakerlabs" are content with the current tflop level, and have no interest in having it increased.

I was just wondering if the good people at Bakerlabs have any development using either the Nvidia Telsa or AMD Firestream HPC GPU's on the horizon.

I think they either do not have the resources available or the resources available do not have the technical know how to make the jump to GPU. There have been to many questions not answered to assume (Ass U Me, I know) otherwise.

I think they either do not have the resources available or the resources available do not have the technical know how to make the jump to GPU. There have been to many questions not answered to assume (Ass U Me, I know) otherwise.

Then why where they able to do this multiproceesures rig for three hours of leased time? I think that is the article I am not sure?

---

Jmarks

I think they either do not have the resources available or the resources available do not have the technical know how to make the jump to GPU. There have been to many questions not answered to assume (Ass U Me, I know) otherwise.

Then why where they able to do this multiproceesures rig for three hours of leased time? I think that is the article I am not sure?

cause the guys of the san diego supercomputer centre helpt rewriting the rosetta code. those guys have the knowledge

... and if they were able to convert sequential code to parallel code for the supercomputer, isn't that the hardest part?

Once converted to parallel, isn't it easier to convert between supercomputer and gaming consoles if both are parallel?

Seems that the hardest part, sequential to parallel, has already been done.

I think they either do not have the resources available or the resources available do not have the technical know how to make the jump to GPU. There have been to many questions not answered to assume (Ass U Me, I know) otherwise.

Then why where they able to do this multiproceesures rig for three hours of leased time? I think that is the article I am not sure?

cause the guys of the san diego supercomputer centre helpt rewriting the rosetta code. those guys have the knowledge

Shouldn't it be relatively easier with Nvidia's CUDA?

Given the popularity of these new graphics cards, their power, and potentially their ease of programming (in C) I would have thought that it wouldn't be too hard a feat.

... and if they were able to convert sequential code to parallel code for the supercomputer, isn't that the hardest part?

Once converted to parallel, isn't it easier to convert between supercomputer and gaming consoles if both are parallel?

Seems that the hardest part, sequential to parallel, has already been done.

I think they either do not have the resources available or the resources available do not have the technical know how to make the jump to GPU. There have been to many questions not answered to assume (Ass U Me, I know) otherwise.

Then why where they able to do this multiproceesures rig for three hours of leased time? I think that is the article I am not sure?

cause the guys of the san diego supercomputer centre helpt rewriting the rosetta code. those guys have the knowledge

well to use multiple gaming consoles over the entire globe in parralel is unthinkable, cause all the cpu's need to acces the same data and results at the same time, so if all the consoles are in the US and some1 from China or Japan would join in, everything would turn into chaos because of the tremendous lag it would create.

6th post cause they like to remove my post and take away my constitutional right. so this time i wont include the words **** ** maybe it can stay now, and you should give a reason when removing post!!

sorry if i wasn't clear.

When talking about parallel processing in gaming consoles (ala Sony's PS/3), the Cell BE processor has the ability to run the 6 spe's in parallel. To run sequential code on the ppe would be a "waste" of available resources.

With the caveat that I am not very familiar with parallel programming, my understanding is that if the basic structure of code has been written for the 40,000 cpu's of a supercomputer, it "should" be easier to recode that for 6 spe's in parallel than it was to initially convert the sequential Rosetta code to parallel Rosetta code in the first place.

While one day it may be possible to link up all the gaming consoles in parallel, this is not the idea I intended to convey.

Individual gaming consoles can run wu's in parallel.

Two Boinc examples would be yoyo@home and ps3grid.

Non-Boinc example would be folding@home.

Given that Rosie code has already been ported from sequential to parallel for a supercomputer, why not take it one step further and convert the parallel for a supercomputer to parallel for a gaming console?

well to use multiple gaming consoles over the entire globe in parralel is unthinkable, cause all the cpu's need to acces the same data and results at the same time, so if all the consoles are in the US and some1 from China or Japan would join in, everything would turn into chaos because of the tremendous lag it would create.

6th post cause they like to remove my post and take away my constitutional right. so this time i wont include the words **** ** maybe it can stay now, and you should give a reason when removing post!!

I did give you a reason, when I deleted your first post. In fact I told you to repost the idea without the swearing. You refused to do that.

You have no constitutional right to shout "fire" in a crowded theater, when there is no fire. And you have no right to create posts that are not in line with the rules listed on the screen when you make a post. It's as simple as that.

---

Rosetta Moderator: Mod.Sense

6th post cause they like to remove my post and take away my constitutional right. so this time i wont include the words **** ** maybe it can stay now, and you should give a reason when removing post!!

I did give you a reason, when I deleted your first post. In fact I told you to repost the idea without the swearing. You refused to do that.

You have no constitutional right to shout "fire" in a crowded theater, when there is no fire. And you have no right to create posts that are not in line with the rules listed on the screen when you make a post. It's as simple as that.

and i replayed your email, wich dousn't notices it is an adress that shouldn't be repleyed to, that saying ***** ** isn't swearing but expressing a feeling of unhappieness in our country(the netherlands) and in much country's, even in the US.