AMD launches FireStream 9250 with 200Gflops DP via RV770
Tuesday 17th June 2008, 10:58:00 PM, written by Rys
AMD have announced a new FireStream product based on their upcoming RV770 GPU, with some seriously impressive single and double precision peak rates.
The FireStream 9250 comes with 1GiB of GDDR3, and the 800 ALUs in the processors combine via an impressive chip clock to produce peak single precision FP32 performance of over 1Tflop, with 200Gflops double precision as a product of how the architecture used the ALUs to compute those results.
While the hardware architecture isn't as immediately amenable to being able to extract those peak rates, compared to the product's immediate competition, if you can make the computation fit then performance is undoubtedly going to be impressive. For reference, the headline DP rate is about 2x higher than the PowerXCell 8i, which was the fastest performing DP-capable processor readily available before the FireStream 9250 was announced.
Programming a FireStream 9250 will be most commonly done via Brook+ and the AMD Stream SDK, with CAL available for those with no fear of directly programming a GPU with the raw ISA. AMD have also said that they'll support OpenCL, or Open Compute Language, so FireStream support is guaranteed at some point in the future.
The announcement is midly premature, since the product won't become available until Q3 2008, but the $1000 price is very keen, and hitting the peak rates will cost you less than 150W. Single and double precision rates are therefore available with leading performance per watt figures too. AMD have clearly used a FireStream of some kind to compute their 8Gflops/watt figure, since it seems spot on.
We'll take a closer look at the non-graphics performance of the hardware after we've take a better look at the Radeon implementation of RV770.
The FireStream 9250 comes with 1GiB of GDDR3, and the 800 ALUs in the processors combine via an impressive chip clock to produce peak single precision FP32 performance of over 1Tflop, with 200Gflops double precision as a product of how the architecture used the ALUs to compute those results.
While the hardware architecture isn't as immediately amenable to being able to extract those peak rates, compared to the product's immediate competition, if you can make the computation fit then performance is undoubtedly going to be impressive. For reference, the headline DP rate is about 2x higher than the PowerXCell 8i, which was the fastest performing DP-capable processor readily available before the FireStream 9250 was announced.
Programming a FireStream 9250 will be most commonly done via Brook+ and the AMD Stream SDK, with CAL available for those with no fear of directly programming a GPU with the raw ISA. AMD have also said that they'll support OpenCL, or Open Compute Language, so FireStream support is guaranteed at some point in the future.
The announcement is midly premature, since the product won't become available until Q3 2008, but the $1000 price is very keen, and hitting the peak rates will cost you less than 150W. Single and double precision rates are therefore available with leading performance per watt figures too. AMD have clearly used a FireStream of some kind to compute their 8Gflops/watt figure, since it seems spot on.
We'll take a closer look at the non-graphics performance of the hardware after we've take a better look at the Radeon implementation of RV770.
Tagging
amd ± firestream, 9250, rv770, double, precision, 1Tflop, really, fast, gpu, zomg
Related amd News
AMD goes Asset Smart; splits into two
Beyond Programmable Shading course notes available
AMD GPGPU solutions get extra support from industry partners
AMD Phenom X3 released; reviewed
Rage3D take a look at Assassin's Creed D3D10.1 support
Stanford University release Folding@Home client for R6-family ATI GPUs
Official: AMD layoffs 10%; misses Q1 guidance.
AMD release FireGL V7700 with DisplayPort support
AMD release new Phenom X4 processors with B3 silicon
AMD RV670 price cuts & 128-bit Radeon HD3830?
Beyond Programmable Shading course notes available
AMD GPGPU solutions get extra support from industry partners
AMD Phenom X3 released; reviewed
Rage3D take a look at Assassin's Creed D3D10.1 support
Stanford University release Folding@Home client for R6-family ATI GPUs
Official: AMD layoffs 10%; misses Q1 guidance.
AMD release FireGL V7700 with DisplayPort support
AMD release new Phenom X4 processors with B3 silicon
AMD RV670 price cuts & 128-bit Radeon HD3830?


AMD Stream Processor First to Break 1 Teraflop Barrier
—Next-generation AMD FireStream™ 9250 processor accelerates scientific
and engineering calculations, efficiently delivering supercomputer performance at
up to eight gigaflops-per-watt —
The AMD FireStream 9250 stream processor includes a second-generation
double-precision floating point hardware implementation delivering
more than 200 gigaflops, building on the capabilities of the earlier
AMD FireStream™ 9170, the industry’s first GP-GPU with double-precision floating point support.
The AMD FireStream 9250’s compact size makes it ideal for small 1U servers
as well as most desktop systems, workstations, and larger servers and
it features 1GB of GDDR3 memory, enabling developers to handle large, complex problems.
AMD is also working closely with world class application and solution providers
to ensure customers can achieve optimum performance results.
Stream computing application and solution providers include CAPS entreprise,
Mercury Computer Systems, RapidMind, RogueWave and VizExperts.
Mercury Computer Systems provides high-performance computing systems
and software designed for complex image, sensor, and signal processing applications.
Its algorithm team reports that it has achieved 174 GFLOPS performance for
large 1D complex single-precision floating point FFTs on the AMD FireStream 9250