IBM用RoadRunner來demo iRT

http://gametomorrow.com/blog/ind ... boeing-777-at-sc07/







史上第一台完全用數位設計的客機，波音777。
聽說這個複雜到炸開的模型總共有350M triangle.....乘上4byte，這代表這東西光Model的vertex量就已經 1.4GB了，實際上的總模型資料量更高達29GB....然後IBM拿LLNL RoadRunner來搞real time ray tracing。

你們真是神經病XD > IBM。

http://www.sci.utah.edu/%7Ewald/ ... /download/mmshm.pdf
2006年這個demo用128 processor、256GB的1.5GHz Itanium2 SGI系統來測試，112個processor用在ray tracing。126個processor的話，1024x768勉強40fps。
因為模型實在太大了，很難用GPU處理。

在SC07上，IBM跑demo的狀況依照原文描述是：

In the IBM booth at SC07 the 350M triangle Boeing digital mockup will be rendered real-time at 1080p resolution using a hybrid cluster of Cell processor based QS21 blades and a Ridgeback (AMD Opteron) memory server.
The Ridgeback holds the 25GB digital model in its memory and services blade data request via NFS RDMA over 2GB/sec InfiniBand.
Each blade is responsible for a dynamic region of the screen and therefore only requires a fraction of the digital model to be cached in its local 2GB memory.
These regions are further subdivided among the local SPEs which DMA via software caches from the address space of the Opteron forming a memory hierarchy that's transparent to the programmer.

-----------------128GB------------ 2GB------------- 256KB
(x86 disk) -> (x86 memory) -> (Cell memory) -> (SPE local store) -> (SPE register file)
--------120MB/sec------ 2GB/sec---------- 25GB/sec---------50GB/sec

Ridgeback這個型號是4U的IBM x3755，最大頂多4顆Dual-core Opteron。(就算偷換成quad-core，也頂多16個K8 core)。
然後總之x86 Server存了25GB的總model data，然後用2GB/s的 InfiniBand 傳給QS21 CELL blade。
因為是跑iRT，主要的負擔應該都在CELL blade上，x86 server只負責管理模型和材質資料而已。