Comments on: 800 TFLOPS chip for ray tracing http://insidehpc.com/2009/07/06/800-tflops-chip-for-ray-tracing/ HPC News Without the Noise for Supercomputing Professionals | insideHPC Sun, 09 Jun 2013 01:54:13 +0000 hourly 1 http://wordpress.org/?v=3.1.1 By: Toyota Motors to compete against Caustic ? | VizWorld.com http://insidehpc.com/2009/07/06/800-tflops-chip-for-ray-tracing/#comment-172118 Toyota Motors to compete against Caustic ? | VizWorld.com Mon, 06 Jul 2009 17:46:05 +0000 http://insidehpc.com/?p=6040#comment-172118 [...] Multicore IC for Realtime RayTracing via insideHPC.com. AKPC_IDS += "5839,"; Share this [...] [...] Multicore IC for Realtime RayTracing via insideHPC.com. AKPC_IDS += “5839,”; Share this [...]

]]> By: Anon http://insidehpc.com/2009/07/06/800-tflops-chip-for-ray-tracing/#comment-172094 Anon Mon, 06 Jul 2009 14:32:16 +0000 http://insidehpc.com/?p=6040#comment-172094 App-specific it may be, but that's still near a PF ina desk-side unit for 1kW. The text & figure suggests fixed point rather than DP floating point. Of course, ray tracing lends itself to tasks other than optical image generation too - e.g. non specular reflections, electromagnetic wavelengths other than light, target scattering, etc. App-specific it may be, but that’s still near a PF ina desk-side unit for 1kW. The text & figure suggests fixed point rather than DP floating point. Of course, ray tracing lends itself to tasks other than optical image generation too – e.g. non specular reflections, electromagnetic wavelengths other than light, target scattering, etc.

]]> By: Dairsie Latimer http://insidehpc.com/2009/07/06/800-tflops-chip-for-ray-tracing/#comment-172089 Dairsie Latimer Mon, 06 Jul 2009 14:09:02 +0000 http://insidehpc.com/?p=6040#comment-172089 As exciting as the title is it is a bit misleading! It's actually the total system performance that is aiming to be 800 TFLOPS (presumably sufficient to meet their visualisation/performance requirements). Each on of the nine dedicated devices, is specified to produce 88 TFLOPS and each is comprised of numerous cooperating clusters of very specialised cores (with limited amounts of local memory). Think of this as the ray-tracing equivalent of the MD-GRAPE machines! I struggle to see the economic case for this system. Is it only going to be used by Toyota's Motor division or more likely the they hope to find interested users elsewhere to help defray the NRE's involved in making such a specialised processor. If so they'd better have an interesting software interface to go with it. I've seen several HW accelerated systems for ray tracing over the years (ArtVPS being the most notable) but we also have Caustic Graphics doing something related today. As exciting as the title is it is a bit misleading! It’s actually the total system performance that is aiming to be 800 TFLOPS (presumably sufficient to meet their visualisation/performance requirements).

Each on of the nine dedicated devices, is specified to produce 88 TFLOPS and each is comprised of numerous cooperating clusters of very specialised cores (with limited amounts of local memory). Think of this as the ray-tracing equivalent of the MD-GRAPE machines!

I struggle to see the economic case for this system. Is it only going to be used by Toyota’s Motor division or more likely the they hope to find interested users elsewhere to help defray the NRE’s involved in making such a specialised processor. If so they’d better have an interesting software interface to go with it. I’ve seen several HW accelerated systems for ray tracing over the years (ArtVPS being the most notable) but we also have Caustic Graphics doing something related today.

]]>