• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

AMD 'Bulldozer' gets an Update from Microsoft.

I'm not sure that's right. I though this scheduler patch worked on "keeping affinity" rather than just randomly dishing out across cores.

24210663_FX-Scheduling.jpeg


I think this is where they're going with the scheduler. Now, that terrible sub-optimal case doesn't always happen, but it can happen. This patch will try and severely reduce the occurrence of such scheduling, and hopefully schedule as few modules as possible to engage turbo core.
 
It's still slower then Phenom 2 and still way way way Behind Sandy Bridge even with hot fix, It does not make BD any less of an uber failure.

And you base this off of.......
 
Not sure what you mean, but the way I read it seems you think AMDs module system works like intels hyper threading.

no i ment that this patch imho wont alter intel cpu performance as its allready been optimised for;) sorry vague

No I'm not joking. CPU and GPU is not the same thing at all. On GPUs it's completely excusable, first of all because the life cycle is 1 year, and because the best you can do is work with a bunch of game developers to try and optimize beforehand, for 20 different GPU models, for 2-3 different architectures that are made obsolete every 12 months. You also have to thread for hundreds or thousands of threads, and you have to thread and optimize for a fairly hetereogeneous computig model. Pixel shaders are not equal to vertex sahders which are not equal to texture units which are not equal to raster units, you get it.

20 GPU models, 100's games, 1000's threads, 1-2 years max to work with game developers, realistically 3 months.

vs

1 CPU, couple of OS, 8 threads, 5 years development time for both the CPU and the OS... NO EXCUSES.


i mentioned GPU's Game devs and essentially anyone making anything pc , you heard gpu and i ment they ALL release then optimise stuff, ALL simples
 
http://cdn.overclock.net/2/24/24210663_FX-Scheduling.jpeg

I think this is where they're going with the scheduler. Now, that terrible sub-optimal case doesn't always happen, but it can happen. This patch will try and severely reduce the occurrence of such scheduling, and hopefully schedule as few modules as possible to engage turbo core.

Wow. If this is true, then this is NOT an optimisation for BD microarchitecture, but rather a HACK to keep the Turbo Core boost on my maximising "core parking". NOP NOP NOP!

no i ment that this patch imho wont alter intel cpu performance as its allready been optimised for;) sorry vague
Is the scheduler already "parking" Intel cores?! If so, this is terrible, IMO. It is deliberately trying to force-OFF multithreading just to optimise the "single core multiplier" turbo. How do we break out of that box. This is NOT good IMO and will discourage rather than encourage threading of applications and games.

A small boost now, but in the long run, it knocks back development and use of multithread engines, and therefore performance.
 
I see a BD bashing starting here, look its a good processor wrongly marketed ....my noob friend love the fact I have 8 cores and 2 of them have i5-2500k. Its all in the eye of the beholder.

I do wish I had went intel again but alas I didnt, That being said my last full time CPU was a PD, hell of an upgrade
 
im gettin one, it and its mobo, fit my use and wallet fine
 
Anyway I'm just commenting to say how useless a comment like that really is and because I've seen you making similar comments plenty of times, here and on Fudzilla a couple of times iirc (or someone with the same nick anyway, but I dobt it).

Just because you have no problems does not mean problems don't exist.
With all due respect, personally I haven’t run into a BSOD without pushing the OC way upwards on all 8-cores. I haven’t had enough time to play with it, but currently running my FX-8120 at 4.40 GHz gives me absolutely no BSOD. I used to get them with a Crosshair V beta bios and I believe that may have been due to my 16GB ram. Anyhow, not sure where you are taking this but I have not suggested that Bulldozer has no issues. Every single PC and its hardware/software play an overall factor in BSOD. Sure it could be the Bulldozer CPU for some and it could be something entirely different with others.
A small boost now, but in the long run, it knocks back development and use of multithread engines, and therefore performance.
Absolutely not, I don't think this knocks back developement. This is the very first so called optimization from both AMD and MS. I am sure there will be a dump load more to come in the near future and so on.
 
With all due respect, personally I haven’t run into a BSOD without pushing the OC way upwards on all 8-cores. I haven’t had enough time to play with it, but currently running my FX-8120 at 4.40 GHz gives me absolutely no BSOD. I used to get them with a Crosshair V beta bios and I believe that may have been due to my 16GB ram. Anyhow, not sure where you are taking this but I have not suggested that Bulldozer has no issues. Every single PC and its hardware/software play an overall factor in BSOD. Sure it could be the Bulldozer CPU for some and it could be something entirely different with others.

Absolutely not, I don't think this knocks back developement. This is the very first so called optimization from both AMD and MS. I am sure there will be a dump load more to come in the near future and so on.

Don't tell them that you're scoring the same as a 2600k clock for clock, you'll get flamed. :p

I have an OCed 8120, as well. No crashes whatsoever. It's rock solid.

Blaming AMD for shitty bioses is ridiculous.
 
With all due respect, personally I haven’t run into a BSOD without pushing the OC way upwards on all 8-cores. I haven’t had enough time to play with it, but currently running my FX-8120 at 4.40 GHz gives me absolutely no BSOD. I used to get them with a Crosshair V beta bios and I believe that may have been due to my 16GB ram. Anyhow, not sure where you are taking this but I have not suggested that Bulldozer has no issues. Every single PC and its hardware/software play an overall factor in BSOD. Sure it could be the Bulldozer CPU for some and it could be something entirely different with others.

You completely missed the point. It's irrelevant if you have BSODs or not. You are ony 1 person out of the hundreds of thousands using those chips, and hence your experience with it is completely irrelevant and serves no purpose. Nine out of 10 people could post they have no problem and it would be irrelevant too, because even 1 out of 10 people having continuous BSODs is a serious problem. Not saying that's the rate of BSODs or someting, like I said I have no idea, but I'm pretty sure Erocker knows what he is talking about.

Next time, just don't post something like that and you won't get a reply from me. If you don't post that you DO have a problem we can safely assume you have none. ;)
 
You completely missed the point. It's irrelevant if you have BSODs or not. You are ony 1 person out of the hundreds of thousands using those chips, and hence your experience with it is completely irrelevant and serves no purpose. Nine out of 10 people could post they have no problem and it would be irrelevant too, because even 1 out of 10 people having continuous BSODs is a serious problem. Not saying that's the rate of BSODs or someting, like I said I have no idea, but I'm pretty sure Erocker knows what he is talking about.

Next time, just don't post something like that and you won't get a reply from me. If you don't post that you DO have a problem we can safely assume you have none. ;)

All hardware can cause a BSOD given the right circumstances. Your argument is irrelevant.
 
All hardware can cause a BSOD given the right circumstances. Your argument is irrelevant.

You insist on the attitude of "I have no problem, problem does not exist."

From the many comments that Erocker has made about it, I get that the BSODs are ocurring at a much higher rate than normal.

But to add some spice, NO not all hardware causes BSODs. I have a SB and never had a BSOD and prior to that I had a Core2 and never had a BSOD. And before that I had an AMD64 X2 and never had a BSOD. What is this BSOD thing we are talking about anyway? It does not exist clearly. ;)
 
You completely missed the point. It's irrelevant if you have BSODs or not. You are ony 1 person out of the hundreds of thousands using those chips, and hence your experience with it is completely irrelevant and serves no purpose. Nine out of 10 people could post they have no problem and it would be irrelevant too, because even 1 out of 10 people having continuous BSODs is a serious problem. Not saying that's the rate of BSODs or someting, like I said I have no idea, but I'm pretty sure Erocker knows what he is talking about.

Next time, just don't post something like that and you won't get a reply from me. If you don't post that you DO have a problem we can safely assume you have none. ;)


LOL, irrelevant much.
 
Don't tell them that you're scoring the same as a 2600k clock for clock, you'll get flamed. :p

I have an OCed 8120, as well. No crashes whatsoever. It's rock solid.

Blaming AMD for shitty bioses is ridiculous.
Why not? I am scoring the same :rolleyes:
No really I wouldn't do such a thing, we know Bulldozer wins in 5 or 6 benchmarks out of what 100 :D
 
OMG, for onde I was right BD bashing thread.

from the posts Erocker has made about it, I get that the BSODs are ocurring at a much higher rate than normal.

For who, yet another "never BSOD" here
 
You insist on the attitude of "I have no problem, problem does not exist."

From the many comments that Erocker has made about it, I get that the BSODs are ocurring at a much higher rate than normal.

But to add some spice, NO not all hardware causes BSODs. I have a SB and never had a BSOD and prior to that I had a Core2 and never had a BSOD. And before that I had an AMD64 X2 and never had a BSOD. What is this BSOD thing we are talking about anyway? It does not exist clearly. ;)

Erocker took his chip to 5ghz. So like I said.....
All hardware can cause a BSOD given the right circumstances
 
Get back to the topic people (before this gets locked). Post some moar results BD owners.
 
OMG, for onde I was right BD bashing thread.



For who, yet another "never BSOD" here

I had a couple which I had to manually fix by disabling some event timers. There has been articles on this, reviewers and end-users have been getting them. I'm not bashing Bulldozer, I'm calling it how it is based upon my experience with it along with other user's experience with it.
 
You insist on the attitude of "I have no problem, problem does not exist."

From the many comments that Erocker has made about it, I get that the BSODs are ocurring at a much higher rate than normal.

But to add some spice, NO not all hardware causes BSODs. I have a SB and never had a BSOD and prior to that I had a Core2 and never had a BSOD. And before that I had an AMD64 X2 and never had a BSOD. What is this BSOD thing we are talking about anyway? It does not exist clearly. ;)
In my opinion, anybody suffering from BSOD's via a Bulldozer setup, I blame the Motherboard's BIOS. Like I said before, I had BSOD's with a beta bios, thank goodness ASUS came out with a improved stability for memory and compatability bios update which solved my issue.

What bios was Erocker using? The beta version is useless IMO.
 
Erocker took his chip to 5ghz. So like I said.....

Say whatever you want. Be a zealot, devil's advocate whatever you want is good, plus you are a news poster now, congrats!

I have just googled Bulldozer BSOD and it has nothing to do with overclocking, plus it's pretty widespread and happens under many different conditions and apps. It seems something clearly related to how threads are handled, so hopefully this patch fixes it.

I'm out.
 
I had a couple which I had to manually fix by disabling some event timers. There has been articles on this, reviewers and end-users have been getting them. I'm not bashing Bulldozer, I'm calling it how it is based upon my experience with it along with other user's experience with it.

Didn't mean it for you, I don't know you from Adam but you seem grounded, its what others see from your results/experience and taking it for "must be BD is that bad"

I read your results/posts, didnt stop me doing it myself.

Water block promised tomorrow, i have a chill system, lets see for myself.

EDIT: water pump not block.
 
Just to play devils advocate, I'm one of the guys that does get random BSODS and random crashes.*

Not whilst gaming or anything like that.

But rendering/benching/stress testing can cause it.

Voltage doesn't matter to much either obviously lower voltages cause it more often though :P

But increasing my voltages above what they are at the moment does not increase stability.


* The reason I call them random is because sometimes I can stress test all day with no problems, other times intel burn test will crash the pc after only 3 runs.

Same with prime mostly it lasts for ages occasionally it will just crash.
 
Say whatever you want. Be a zealot, devil's advocate whatever you want is good, plus you are a news poster now, congrats!

I have just googled Bulldozer BSOD and it has nothing to do with overclocking, plus it's pretty widespread and happens under many different conditions and apps. It seems something clearly related to how threads are handled, so hopefully this patch fixes it.

I'm out.

Ah man don't take it that way. I know many BD users that have been problem free. Any issue they had was software or setting related. I don't blame BD for this. BD is a real change from 10 years of a standard architecture. Shits gonna happen. But to blame BD is kinda lame IMO.

Thanks for the comments about me being a news poster. But don't let that hold ya back. PLEASE. I've got thick skin and as long as you dont make it personal no problem will come from me. I welcome debate and opinion! You can ask any mod on here even before I was staff I rarley reported anyone unless they were just being a jerk which I have NEVER known you to be.
 
Back
Top