Inside AMD's Phenom Architecture 191
An anonymous reader writes "InformationWeek has uncovered some documentation which provides some details amid today's hype for AMD's announcement of its upcoming Phenom quad-core (previously code-named Agena). AMD's 10h architecture will be used in both the desktop Phenom and the Barcelona (Opteron) quads. The architecture supports wider floating-point units, can fully retire three long instructions per cycle, and has virtual machine optimizations. While the design is solid, Intel will still be first to market with 45nm quads (the first AMD's will be 65nm). Do you think this architecture will help AMD regain the lead in its multicore battle with Intel?"
Support? (Score:2, Interesting)
Scalability, 64-bit, and FPU (Score:4, Interesting)
Re:Why the fuss over 45nm? (Score:3, Interesting)
Indeed, let's wait for the benchmarks. I would like some more real-world and 64-bit benchmarks: most recent reviews seems to have studiously avoided those in favor of synthetic 32-bit only benchmarks that are not very representative and are easily skewed with processor-specific optimizations.
And I'm not sure going to 45nm process will allow Intel to step back ahead. It seems process improvements have been yielding diminishing results in performance related areas. Transistor density will go up, though, so Intel can compensate by adding more cache. Also, AMD's process technology is a little advanced than Intel's at the same feature size: Intel does not do Silicon on Insulator, dual stress liners, and a few other things.
Re:Sorry what? (Score:3, Interesting)
Re:Support? (Score:3, Interesting)
Maya 3D
Or any other 3d rendering software where every CPU cycle is used to the last drop.
But other than that I can't think of anything off the top of my head, but multi-cores is very important to these types of apps. It is the different between 12 and 6 hours waiting for the project to render then people will go with the 6 hours.
Re:AMD IS Doomed to Always Be a Follower Unless... (Score:2, Interesting)
A smaller firm operating on tighter margins like AMD could easily go belly-up trying to break out with a new CPU microarchitecture. At least Intel could afford all of Itanic's failures.
Re:Sorry what? (Score:1, Interesting)
Yes, Windows Vista uses true multi-core optimization (XP SP2's scheduler does it, but Vista's does it better, according to Microsoft) so that when you're converting all your video files from MPEG TS to H.264 on a dual-core processor, you can convert two movies at once and they will end up on different cores. While Windows isn't exactly open-source, the Windows.h file and the .NET framework allow for operations that imply there is a method Windows uses to switch a thread's processor/core based on apartment state, priority and various other important things. I would imagine this operation takes quite a bit of time.
The Linux processor scheduler isn't as powerful and I cannot seem to find any documentation as to any multi-core optimizations. This isn't a huge deal, as only a few people would really see a difference (multiple number-crunching operations at once - specialty servers, video transcoders, world simulators) and it would most likely take a fundamental change to the way the scheduler works (which was just completely re-written for the 2.6 kernel).
I think both Windows and Linux could benefit from a operation for dedicating cores. When a thread is created, a function call such as
before the thread is started which would request the OS to dedicate an entire core to a thread. There may be a 5% performance boost (and that's being generous) as the processor registers do not need reloading on thread changes, but the slight increase would make somebody happy.Re:Sorry what? (Score:3, Interesting)
But the Core 2 Duo is easily 2 times as fast to render AND is far superior when previewing video with lots of color correction or lots of layers of generated media (movie credits or text overlays are particularly harsh because of all the alpha blending for each source). The P4 system struggles to play native HD footage (m2t) at 1/2 resolution while the Core 2 Duo has no problem. Remember that native HD stored in the m2t file is highly compressed so just viewing the footage is very taxing on the CPU-to-RAM bus as well as the HD.
My render app is Sony Vegas (not the cheap movie studio version) which is fully multi-core / multi-cpu aware. You can even set the # threads to take advantage of quad CPU systems. Vegas is entirely CPU dependent (unlike Edius / Avid which have hardware render assist).
But as other posts mention, aside from the multimedia creators no one will need multi cores. Well, unless they are running Aero on Vista. Good luck with that beast.
jason
Side note: most media creators cannot move to Vista yet because of how direct sound access is blocked. Sony pretty much says stay away for now.
Re:Sorry what? (Score:3, Interesting)
You can extract CPU info from the
Tom