Thursday, December 15th 2011

AMD 'Bulldozer' gets an Update from Microsoft.

Today Windows updater may have brought "Bulldozer" users a little surprise. A hotfix that increases the AMD flagship processors performance. As this "hotfix" is bleeding edge news any benchmarks have yet to be seen but this confirms Windows 7 was in fact hampering “Bulldozer” from performing at 100% in all prior benches. What percentage it was previously performing at has yet to be determined. Here is a small snippet from the Hotfix release notes.
This article introduces an update that optimizes the performance of AMD Bulldozer CPUs that are used by Windows 7-based or Windows Server 2008 R2-based computers. Currently, the performance of AMD Bulldozer CPUs is slower than expected. This behavior occurs because the threading logic in Windows 7 and in Windows Server 2008 R2 is not optimized to use the Simultaneous Multithreading (SMT) scheduling feature. This feature was introduced in the Bulldozer family of AMD CPUs.
You can download the Hotfix here.
Add your own comment

139 Comments on AMD 'Bulldozer' gets an Update from Microsoft.

#1
dezz
devguy said:
This patch will try and severely reduce the occurrence of such scheduling, and hopefully schedule as few modules as possible to engage turbo core.
I hope it's NOT doing that (at least not only that), because there are much more gains from spreading f.ex. 4 threads on 4 modules (so utilizing one core per module) than from the Turbo Core! The former is up to 26% at the same clock, the latter is only 5-10%.
Posted on Reply
#2
EastCoasthandle
User Results
Some solid results in the games tested. Also take note that the dual GPU solution's usage increased as well.
Posted on Reply
#3
JustaTinkerer
http://www.overclock.net/t/1185039/the-1st-windows-7-scheduler-patch-results-are-in-have-fun
Some folks wanna test before sp1 for me I got better results.

Need to see all the action before making your mind up, check my results on page 3. The hotfix from what I see is not so hot.

Need to say, I have said I wanna test Batman :AC im £1.50 off being able to download it and test.
Hell I will re-install for a test/ no sp/with SP/ with SP and hotfix
Posted on Reply
#4
devguy
dezz said:
I hope it's NOT doing that (at least not only that), because there are much more gains from spreading f.ex. 4 threads on 4 modules (so utilizing one core per module) than from the Turbo Core! The former is up to 26% at the same clock, the latter is only 5-10%.
Well, yes and no. If the threads are related to a process (and could benefit from the sharing of the L2 cache), then it's best they are put onto the same module (threads 1a and 1b). If they have no (or next to no) relation, then they should be put on separate modules (thread 1 and thread 2).
Posted on Reply
#5
dezz
devguy said:
Well, yes and no. If the threads are related to a process (and could benefit from the sharing of the L2 cache), then it's best they are put onto the same module (threads 1a and 1b). If they have no (or next to no) relation, then they should be put on separate modules (thread 1 and thread 2).
Well, in theory. Tests show that what I've wrote is true even in case of threads of the same process. There are perhaps special cases where the benefits of sharing the cache is overweighting the impact of sharing of other resources, but I'm yet to see one.
Posted on Reply
#6
pantherx12
After playing for quite a while. skyrim doesn't seem to get any benefit from this patch XD

Well it may get an extra frame or two but nothing noticeable
Posted on Reply
#7
Fx
JustaTinkerer said:
Just yesterday I was saying this didnt exist, I need to learn to stfu, hat eating time.

I only have novabench on my PC.

What tests you wanna see done? mind no graphics stuff as Im running on a 3850 crossfire setup right now and no overclocking results as im on stock till my new water pump come in.

I have the hotfix just not installed it yet
lol, well lets just wait and see. you might not have to whip your pair out to man up if it is only an average 5% increase
Posted on Reply
#8
Over_Lord
News Editor
HossHuge said:
Bring on the reviews AGAIN!!
Re-reviews. Hoping for the best.
Posted on Reply
#9
Thefumigator
EastCoasthandle said:
User Results
Some solid results in the games tested. Also take note that the dual GPU solution's usage increased as well.
taken from the link:
CONCLUSION:
Great for gaming. It’s a free patch, and the results go from barely seen to solid gains. For those of you who have a BD, it’s a bloody MUST.

For those of you who don’t have a BD… well, it’s a cool patch, but shouldn’t be enough of an impact to make a decision of getting one or not, I believe.
Posted on Reply
#10
ShogoXT
They seemed to have taken down the patch from the Microsoft website. Perhaps they need to adjust it?
Posted on Reply
#11
n0tiert
TheMailMan78 said:
All hardware can cause a BSOD given the right circumstances. Your argument is irrelevant.
true !
Posted on Reply
#12
DrunkenMafia
ShogoXT said:
They seemed to have taken down the patch from the Microsoft website. Perhaps they need to adjust it?
It seems that way. Spewin I didn't get it in time. Maybe someone can post it up if it isn't back on MS in a couple of days. :)
Posted on Reply
#14
DrunkenMafia
yes pls. Can you zip it and rename it to .txt file and email to me. :)

Cheers
Posted on Reply
#15
DrunkenMafia
ignore my last post, didn't see your one above that. :) cheers
Posted on Reply
#17
Super XP
devguy said:
Yeah, I noticed that Asus just in this past week has released BIOSes for 9xx chipset boards that is supposed to fix the BSODs that appear when playing Source engine games (I know, weird right?). There's also some tweaks to memory stability mentioned. Initial reactions seem positive over at XS forums. I'll give BIOS 902 a whirl on my Thuban and see if I notice any differences (but I doubt it).
The new 1003 bios is also out and newer.
Posted on Reply
#18
devguy
Super XP said:
The new 1003 bios is also out and newer.
For Crosshair V, yes, but not for M5A97 Evo.
Posted on Reply
#20
LAN_deRf_HA
Update: Microsoft has apparently pulled the patch from its download servers for unspecified reasons. We'll try to post another update when we find out more.

Update II - 10:55AM: We've spoken with an industry source familiar with this situation, and it appears the release of this hotfix was either inadvertent, premature, or both. There is indeed a Bulldozer threading patch for Windows in the works, but it should come in two parts, not just one. The patch that was briefly released is only one portion of the total solution, and it may very well reduce performance if used on its own. We're hearing the full Windows update for Bulldozer performance optimization is scheduled for release in Q1 of 2012. For now, Bulldozer owners, the best thing to do is to sit tight and wait.
http://techreport.com/discussions.x/22179

Explains why it's a mixed bag for so many people.
Posted on Reply
#22
Super XP
pantherx12 said:
Reckon it's worth uninstalling then?
Are you getting an increase in performance with games? Most sites are reporting an increase in performance while others no improvement. I plan on installing the patch out of curiousity.
Posted on Reply
#23
pantherx12
Super XP said:
Are you getting an increase in performance with games? Most sites are reporting an increase in performance while others no improvement. I plan on installing the patch out of curiousity.
Nope, only thing I got an improvement on was single threaded cinebench, in fact all my multi core benches have lower scores.
Posted on Reply
#24
Super XP
pantherx12 said:
Nope, only thing I got an improvement on was single threaded cinebench, in fact all my multi core benches have lower scores.
Wow and games like L4D1/2 and Skyrim are multi-core based :eek:
Posted on Reply
#25
Daimus
pantherx12 said:
Nope, only thing I got an improvement on was single threaded cinebench, in fact all my multi core benches have lower scores.
i got the same running Cinebench. It seems this patch does not much FPS in the games, the difference is placed in accuracy.
i saw performance increase only running x264 benchmark.
Posted on Reply
Add your own comment