The AMD Firestream setup from Aprius could be better with eight of the $1499 boards ($12000 plus some amont for the 4U box and backplane.) It will outperform the Nvidia setup and be out in about 4-6 months. Of course Nvidia could go through another rev from its current setup.
The FireStream 9270 uses a compact form-factor and can slide into both workstations and servers — anything with a PCIe 2.0 x16 slot. The new card will retail for $1,499, and will start shipping in a few weeks.
AMD demonstrated a FireStream-based expansion box at SC08, which will start shipping in early 2009. Built by newcomer Aprius Inc., the Computational Acceleration System (CA8000) is a 4U box that can hold up to eight 9270 GPU boards, yielding an aggregate performance of 9.6 Single Precision teraflops (1.9 Double Precision teraflops). Up to 4 PCIe x16 buses connect the box to host servers, using optical interconnect technology developed by Aprius. Since the connection is optical fiber, the expansion box can use the full speed of the PCIe bus over distances of up to 50
meters. It’s meant to offer a lot of compute density, along with the flexibility of a standard host connection.
NVIDIA’s strategy seems to be to stake out the middle of the market between workstations and PCs sequestered for GPU computing and full-blown Tesla-accelerated clusters, like the 170 teraflop system just announced by Tokyo Tech. The Tesla personal supers can be used as development and test platforms for Tesla clusters or as HPC production systems in their own right.
Since the NVIDIA reference platform specifies multiple GPUs, a Tesla desktop system will be much more powerful than a single-GPU workstation. The minimum configuration for a Tesla-equipped personal supercomputer includes a quad-core CPU, 3 to 4 C1060 boards (each with a 10-series GPU), and 4 GB of memory per GPU. That would yield a machine capable of 4 SP teraflops and 400 DP gigaflops. These personal systems should retail for around $10,000.
NVIDIA believes the personal super computer market is around 15 million researchers, nearly 6 million of which are in the US alone.
GPGPU versus FPGA personal supercomputer