• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD Bulldozer Finally!

d_brennen said:
Why?
Click to expand...

gareth170 said:
because i want to test it out myself
Click to expand...

d_brennen said:
Touché
Click to expand...

gareth170 said:
:confused:
Click to expand...

Interjection
touché
(fencing) An acknowledgement of a hit.
An acknowledgement of the success, appropriateness or superiority of an argument or discussion; sometimes used sarcastically to mock one's opponent's absurd logic.
Click to expand...

Don't shoot the messenger! Why not wait for a few independent reviews before ordering? Not like you haven't waited long enough already
 
Tute said:
Student loan is in so i'm good to go. Ball's in your court AMD - but then there aren't even any BD mITX motherboards yet so I might be forced to go SB.
Click to expand...

When I was assembling my current SFF PC a few months ago,the 890GX based AM3 mini-ITX motherboards had just come out. I have not seen any noise about a mini-ITX AM3+ motherboard. Supposedly,there was the AM3+ only 980G chipset with an IGP but there has been no recent information about it.

TBH,with Ivy Bridge probably being compatible with the current H67 and Z68 based mini-ITX motherboards ATM it looks better to invest in a Sandy Bridge based system. However,it increasingly looks like Trinity will be out early next year and this will work on socket FM1. This is based on the Piledriver cores and according to Phoronix they have tested a 2.5GHZ Trinity quad core under Linux and it is faster than a 2.9GHZ A8-3850.
 
Last edited:
looncraz said:
Actually, we already have such an issue known for Bulldozer, and NO bench-marked system has the patch installed!

The shared L1 cache is causing cross invalidations across threads so that the prefetch data is incorrect in too many cases and data must be fetched again. The fix is a "simple" memory alignment and (possible)tagging system in the kernel of Windows/Linux.

I reviewed the code for the Linux patch and was astonished by just how little I know of the Linux kernel... lol! In any event, it could easily cost 10% in terms of single threaded performance, possibly more than double that in multi-threaded loads on the same module due to the increased contention and randomness of accesses.

Not sure if ordained reviewers have been given access to the MS patch, but I'd imagine (and hope) so! Last I saw, the Linux kernel patch was still being worked on by AMD (publicly) and Linus was showing some distaste for the method used to address the issue. One comment questioned the performance cost but had received no replies... but you don't go re-working kernel memory mapping for anything less than 5-10%... just not worth it!
Click to expand...
Click to expand...
http://www.xtremesystems.org/forums...nally-tested&p=4969164&viewfull=1#post4969164
 
crackerman said:
What happens to the returned CPU? Is it sold as an OEM without the retail packaging?

I wouldn't want to purchase a CPU which has been tested to see how far it overclocks.
Click to expand...

I've had graphics cards and motherboards from several retailers which have obviously been opened. I suspect they just sell them on. A returned CPU would probably end up in a prebuilt PC
 
TBH I've not heard of CPU/Kernal patches being released by Microsoft since XP SP2 or before. Probably happens, just behind the scenes
 
CAT-THE-FIFTH said:
A 10% to 20% performance hit is quite large!! I wonder if the leaked AMD slides last week were for patched systems??

The Windows 8 schedulers are also meant to have upto 10% improvement in games too.
Click to expand...

Yes i read about windows 8, but i cant remember if there an improvement for current processors, im sure it was.
 
You must log in or register to reply here.
Back
Top Bottom