[email protected] for the GPU has exploded in the [email protected] crowd since it was first demonstrated that an ATi GPU was able to perform this complex number crunching significantly faster than a standard CPU.
But after introducing the world to this new marvel ATi quickly fell behind and nVidia rocketed to the forefront as the fastest GPGPU for [email protected]
Theo Valich has taken a look to see why this is and what the possible solution might be.
Hold out hope after reading this.
So, we have shown you the problem, and now the time is for the solution. ATI canft fix the performance issue on previous-gen hardware, but it will solve multitude of issues on Radeon 4800 boards. The team at Stanford is taking some necessary steps to re-do the workflow and introduce local memory share. This could take months, so realistic goal is to have a new client coming in Q109.
Once that Radeon 4870 gets fully utilized, those 800 shaders and 70% of theoretical value (700-800 GFLOPS instead of 1-1.2 TFLOPS) should be good enough for reaching the level of GTX280.