Jump to content

Bulldozer Win 7 patch coming?


Recommended Posts

I have been skeptical about this , but i have seen this on three separate sites as of recently:

 

from an article from Len2Fire:

 

Patch for Windows 7 to support CMT Technology

 

It’s a well known fact to all of us that Microsoft Windows 7 cannot recognize AMD Bulldozer’s very efficient CMT technology, which is supported only from Windows 8, but Windows 8 is still in developer stage. With CMT enabled, up to 10% more performance can be obtained from Bulldozer. However, AMD confirmed that it is working with Microsoft to launch a patch for Windows 7 very soon, to support CMT.

 

If it's true, it could change things significantly, but grain of salt time I suppose.

 

The balance of the article can be had here:

 

http://lenzfire.com/...ate-time-88199/

Share this post


Link to post
Share on other sites

It is not the OS thats a problem for Bulldozer, it is simply the way programs are written. Future software should perform better with bulldozer

 

5. Is anything being done from AMD's side to a.) promote the development of more true multithreaded code and b.) give guidance to developers on how to approach multithreaded code to give as good results as possible?

 

Gabe Gravning, Senior Product Marketing Manager, AMD - We are working with developers and ISVs to encourage the development of multi-threaded applications and code. This is a major focus for AMD and others in the industry. And this was the driving force for us to host our own developer summit in 2011 so we could have a conversation with developers about parallelism and heterogeneous computing. So yes, we are promoting new tools that make it easier for developers to take full advantage of an increasing number of cores on the CPU, GPU or both.

 

6. It has been stated that Bulldozer will see improvements in performance with the Windows 8 scheduler. Would you elaborate?

 

Gabe Gravning, Senior Product Marketing Manager, AMD - We worked with Microsoft to improve the way threads are scheduled with the "Bulldozer" architecture in Windows 8®. In Windows 7, workloads are simply executed sequentially across the cores. The Windows 8 scheduler is optimized for the "Bulldozer" architecture and will distribute the workload across each core pair first and then each core resulting in better threaded performance.

For example, in testing by AMD with the AMD FX-8150, we are seeing up to 10% uplift on a number of games with the Windows 8 Developer Preview compared to Windows® 7. Of course, results do vary.

We are also working with Microsoft on a scheduler update for Windows 7 that will be available soon.

Edited by Drdeath

Share this post


Link to post
Share on other sites

well it's been a contention that the windows 7 scheduler is not at all optimized for the BD architecture. they are also saying that they are seeing improvements with BD and Windows 8 (reason again being the scheduler)

 

Some sites have allegedly seen some initial results of an optimized Win 7 "patch" separate from new software using AVX and other new instruction sets.

 

I guess we'll see when or if this patch is released.

 

 

Share this post


Link to post
Share on other sites

It is not the OS thats a problem for Bulldozer, it is simply the way programs are written.

The scheduler certainly doesn't help things with the way it allocates threads to cores. Bulldozer is the problem for Bulldozer. :P Unless something is highly threaded and uses the new instruction sets it is slooooow.

Share this post


Link to post
Share on other sites

The scheduler certainly doesn't help things with the way it allocates threads to cores. Bulldozer is the problem for Bulldozer. Unless something is highly threaded and uses the new instruction sets it is slooooow.

 

Well I think I will go with those who have actually done scheduling/affinity testing with the bulldozer and got results to the contrary.

 

From The Tech Report:

 

picc-skeleton.gifpicc-morph.gif

 

picc-fourier.gifpicc-fdom.gif

 

myrimatch.gifeuler3d.gif

From the Tech report:

These results couldn't be much more definitive. In every case but one, distributing the threads one per module, and thus avoiding sharing, produces roughly 10-20% higher performance than packing the threads together on two modules. (And that one case, the FDom function in picCOLOR, shows little difference between the three affinity options.) At least for this handful of workloads, the benefits of avoiding resource sharing between two cores on a module are pretty tangible. Even though the packed config enables a higher Turbo Core frequency of 4.2GHz, the shared config is faster.

 

Our test apps, obviously, are not your typical desktop applications, and they may not be a perfect indicator of what to expect elsewhere. However, since many games and other apps are lightly threaded, with three or four threads handling the bulk of the work, we wouldn't be surprised if one-per-module thread affinities were generally a win on Bulldozer-based processors.

 

Share this post


Link to post
Share on other sites

theres no patch and most likely wont be until win8

this issue has been around and talked about since like 2008? nothing yet so i reaaally doubt 3 years down the road they are going to

Share this post


Link to post
Share on other sites

theres no patch and most likely wont be until win8

this issue has been around and talked about since like 2008? nothing yet so i reaaally doubt 3 years down the road they are going to

 

 

 

 

Yeah, hence my "grain of salt. ' The AMD rep was rather bold and insistent about there being one though. Pretty dumb move (and not a lessoned learned )after John Fruehne's "1.6 x faster than the 1100T" Campaign.

 

Although he may have been one of the 1400 relieved of their duties.

 

 

 

Share this post


Link to post
Share on other sites

Please sign in to comment

You will be able to leave a comment after signing in



Sign In Now
×
×
  • Create New...