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

AMD FX 8150 Looks Core i7-980X and Core i7 2600K in the Eye: AMD Benchmarks

@ cada wow.... aggro much? dude... less coffee in the AM :)
 
erocker said:
Tomato, tomatoe. I don't really care the differences between "FULL RETAIL RELEASE" and release. But okay, wait. :)
Click to expand...

Like I said, they can launch in the US all they want. Doesn't mean shit to me when I am not located in the US.

Comprende?

:roll:

Ahhzz said:
@ cada wow.... aggro much? dude... less coffee in the AM :)
Click to expand...


What you don't know is that erocker and I talk on TS nearly every day. That's just me, and how I talk; I don't mean nothing by it. It's aggressive, because I'm an agressive, over-confident dude. I'm sorry if it makes you feel uncomfortable, but you know, I'm actually laughing.

EDIT: And actually, I don't drink coffee any more. Gave that up a few weeks ago in preparation for my shoulder surgery. :D
 
Last edited:
Mexican is not a language. Its a type of food.
 
Last edited:
The mobo used (according to what the guy says in the post) is M5A99X with 1333MHz RAM me thinks too; CPU-Z lists the CPU as OR-B2 revision & not ES but as full blown FX-8120; how the f*** he got this CPU in a first place? Smells like either BS or some countries already get the CPU earlier; WTF? :laugh:

P.S. Looked @ SuperPI score (1M) - i think mine is lower, albeit it is OC'd; 25.xxx sec for 3.1GHz: is it good or not? 48.3fps in RE5 with 1280x720 res? So it is CPU score or GPU (HD 5870)? Other than that - you right: budget PC & actually strict budget one. :toast:
 
I would have liked to have seen memory performance with the NB overclocked. IMC performance is where Intel is lightyears ahead. While a 2200 Mhz stock NB is nice, for an AMD cpu, NB overclock performance is more interesting.

Edit:
Those are nice +15% and +25%, memory read and memory write performance bumps over what I've got @ 20% overclock.
 
Last edited:
TheLaughingMan said:
Mexican is not a language. Its a type of food.
Click to expand...

How many Mexicans do you know personally? I grew up in a town full of migrant camps. My first girlfriend was Mexican as a matter of fact. They speak a form of Spanish but make no mistake Mexicans have their own way of talking that is unique to Mexico. Its a language.

Chingate culero!
 
file.php


original
 
TheMailMan78 said:
How many Mexicans do you know personally? I grew up in a town full of migrant camps. My first girlfriend was Mexican as a matter of fact. They speak a form of Spanish but make no mistake Mexicans have their own way of talking that is unique to Mexico. Its a language.

Chingate culero!
Click to expand...

several dialects, its the same about being in Dixieland too.
 
Sourthern aint not no danged a lauguage, its etts!
 
you makin fun of where i come from?
 
Saw this linked over on the S|A forms. Don't know the validity of the claim, just thought it was interesting because I've read a couple times about people mentioning a software patch needed for best performance.

link
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...
 
We speak American:)....My God:eek: ...how do others actually translate their native language to ours... it like first you must learn proper English and then forget 75% of that and then ....the rest is a mystery:confused:
 
I don't anticipate BD being much faster if at all faster than SB CPU's.
 
mastrdrver said:
Saw this linked over on the S|A forms. Don't know the validity of the claim, just thought it was interesting because I've read a couple times about people mentioning a software patch needed for best performance.

link
Quote:
Originally Posted by looncraz
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...

Looks like the Linux patch was being hammered out July/August:
http://comments.gmane.org/gmane.linux.kernel/1170214

Here's the last message in the chain, at the bottom of the page:

Re: [PATCH] x86, AMD: Correct F15h IC aliasing issue

On Wed, Jul 27, 2011 at 11:57:45AM -0400, Avi Kivity wrote:
> Out of curiosity, what's the performance impact if the workaround is
> not enabled?

Up to 3% for a CPU-intensive style benchmark, and it can vary highly in
a microbenchmark depending on workload and compiler.
Click to expand...

Interesting.
 
xenocide said:
I don't anticipate BD being much faster if at all faster than SB CPU's.
Click to expand...
If not faster, then equal we hope. Both are completely different in design, its going to be very interesting indead.
 
left hook!

Few hours more....then well know for sure. Wanna believe bd will be a contender. Few more hour til a major sucker punch to intel....... or to us.
 
if BD is actually powerful, this thread is going to make a fool out of a lot of people.
 
Mussels said:
if BD is actually powerful, this thread is going to make a fool out of a lot of people.
Click to expand...
Powerful is so subjective. T-minus what, 15 hours??? :p

There will be people, no matter what performance, say this thing is the best CPU since sliced bread. And if it does spank SB, there will be the other side spewing hate. Man, I have been around waaaaay too many product releases and forums over the past 10 years.

Predictable. People are predictable.

PS - Wanna take a bet on 'powerful'? :p
 
Last edited:
Wonderful, my baby is almost released I hope. Come on Bulldozy we await you my grace :D
 
You must log in or register to reply here.
Back
Top