Interesting technical article, called “PhysX: Lust, Last oder Frust?” has emerged on Tom’sHardware.de today. It’s purpose is to revisit recent events in GPU PhysX (and CPU execution of PhysX effects) area – thus, basic knowledge of this topic is required.
Update: english version available
x87 vs SSE question gets updated with new CPU instructions tests of Mafia II:
(note: graph is called "vtune_metro2033", so some mistakes may take place)
As new PhysX SDK 2.8.4 with SSE2 compliler option is yet in beta, and Mafia II is based on SDK 2.8.3 – it is still relying on x87 instruction set.
Author correctly remarks, that moving from X87 to SSE usage won’t magically boost performance by 2x times, like several websites are promising, more likely 10-20 % or even less in real applications.
While fully automatic multi-threading is yet to come with PhysX SDK 3.0, Metro 2033 is used as example of good multicore-CPU optimizations for both game loop and PhysX calculations.
Sadly, developers (and Nvidia content engineers) are not bothering with optimizations of GPU PhysX effects in other games – this is rather difficult and unprofitable.
Significant part of the article is dedicated to Hybrid PhysX setups – currently, only way fot ATI/AMD users to enjoy additional GPU PhysX content with appropriate framerates.
As nice addition, PCI-E bandwidth tests are included.
Decent, but slightly biased read for anyone interested and GPU PhysX technology, applied to current games.