AMD Piledriver rumours ... and expert conjecture

Page 295 - Seeking answers? Join the Tom's Hardware community: where nearly two million members share solutions and discuss the latest tech.
Status
Not open for further replies.
We have had several requests for a sticky on AMD's yet to be released Piledriver architecture ... so here it is.

I want to make a few things clear though.

Post a question relevant to the topic, or information about the topic, or it will be deleted.

Post any negative personal comments about another user ... and they will be deleted.

Post flame baiting comments about the blue, red and green team and they will be deleted.

Enjoy ...
 


Well, there *shouldn't* be any penalty for using cores on a PII. As for the i7, the Windows scheduler is aware of the HTT bit and will avoid using odd numbered cores if its set (which was the fix BD/PD should have taken from the start).
 


Well, we kinda did try and tell them not to expect too much...
 


I agree there somewhat, I have posted links to MP BF3 testing also showing that cpus vary considerably.

latency IS fps

frames per second
seconds per frame

SAME THING just inversed. Longer latency = less fps. 16.7 miliseconds per frame = 60 frames per second. 32 miliseconds on one frame = an instantaneous FPS of 30 for that one frame, IE minimum FPS is the longest time between one frame. 99th percentile latency = minimum fps.
Not even close.

http://techreport.com/review/21516/inside-the-second-a-new-look-at-game-benchmarking/3

Look at this really simple example:

http://techreport.com/r.x/inside-the-second/sgpu-bc2-6870.gif
http://techreport.com/r.x/inside-th...nimum fps at the viewpoint of that one frame.
 
No, n00b; minimum FPS is subject to the same logic as average FPS.

The thing is that, the minimum FPS is not the same as "the longest time to draw a frame within a second", which is what you're confusing minimum FPS with.

But as I read, you're talking more or so, the same thing. Although, taking the statistic approach from Tech's on the frame draw times or what Tom's being doing lately by showing the frame graph, is the correct way of benching. Even though I think Tech's is more complete and specific overall.

PD's Vishera worked on FP processing, which translated directly to frame drawing speed (less time, good thing), which doesn't directly translates to higher min FPS (EDIT: well, it does have a direct impact, to be honest, haha), but a smother transition from frame to frame within the second.

Cheers!
 


Umm...no. Minimum FPS is the minimum FPS produced over a 1 second timespan. This can occur naturally due to a variety of reasons not related to CPU/GPU performance, and can give a REALLY bad impression if not understood properly. Its the frame latency that measures the time difference between two frames, which ideally would be equal to 16.67ms (or 60 FPS, over a 1 second timespan).

Secondly, there is no direct causation between Frame Latency and FPS. For example:

arkham-fps.gif


Note the average FPS (a favorite of benchmarkers everywhere) is above 60FPS for almost every CPU. That would infer frame latencies below 16.67ms, correct?

arkham-99th.gif


Mind-Blown: Not a single CPU is capable of a STEADY 60 FPS without dropping at least some frames in between. Even the i7-3770k, the top CPU, can only spit out about 52 frames before you can statistically expect one to get dropped due to latency. This, despite the AVERAGE number of frames being produced almost being 90 per second. Looking at a FX-4710 for comparison, it spits out 60 FPS on average, but with an average latency of 29.2ms. Again, this equates to expecting a frame to be dropped every 34 frames or so statistically, or about two dropped frames per second.

Is this noticeable in games? Probably not. But its another statistical measure that goes deeper then average FPS, which can be skewed for a variety of reasons (GPU bottleneck, for instance).
 


That's pretty cool i always wondered how people were able to get information off those cartridges i understand if you want to tell me here but private message me just interested on how you do that.



He always does that its rare to get any real info kinda like how he keeps saying 3-5% IPC improvements(no proof with Clock per clock comparisons) even though that number is closer to 7-10% and the clock speed advantage was only like 5-7% There's plenty benchmarks even proving this. The improvements in games is probably because of the decent improvements in the FPU on PD.

I said that to intel troll fazers.

Even so what Fazers says is true Windows 8 saw no considerable improvements on the benchmarks, They should also see if windows 8 is faster on a I5 or I7 with the new scheduler.
 


Just ignore him - he apparently doesn't realize his previous "troll" posts got deleted, as so will he if he keeps up the insults 😛..
 


Not sure about that specific case, but its not THAT uncommon for patches to fix some problems while introducing others. DICE is notorious for releasing buggy azz games and then releasing gigs of patches that solve majority of bugs and introduce others, they overnerf and overbuff weapons all day. I guess microsoft is prone too :/
 



Trolls are so common that it is no longer an insult, just a description 😛
 


Baron(with some others) the one who convinced me Bulldozer was going to be some 50% faster, Its ok he can stay at Amdzone.
 


He has made a recent appearance in The Tech Report comments, extolling the virtues of a $1,100+ Fujitsu tablet using Hondo.(I kid you not).
 




So if the above is true, what does that say about the knowledge of "Joe Six-Pack"?

Often I hear people say that as most people never read review sites, people would go on things like Core Count and Clock Speed.

How is it that these tech un-savy people know that Bulldozer wasn't performing as well as the i5's and i7's?

Do these tech un-savy people pretty much turn to the "computer expert" in their family/circle of friends for advice, before buying, thus making review sites and possibly the forums at places like Tom's Hardware, important afterall?

 



hmmmm interesting question. I suppose you are right, they consult before spending $400-1000 on a computer. That's what I did many years ago when shopping for a new PC. It has been my personal experiences that big stores around here sell mostly Intel powered computers too, plus many buy macs which are also powered by intel CPU's.
 


They do turn to "computer experts" at my school, those esteemed few who seem to know what they're talking about.

There's a variety of them:
1 - A certain someone who claims that he owns a 7Ghz Pentium 4 laptop and loves nothing more than claiming extreme overclocks as computers he runs 24/7 and loves doing the "3Ghz x 4 cores = 12GHz CPU" trick. It is no surprise that he buys AMD Bulldozer.
2 - A certain someone who goes about showing off his latest feat of tech expertise (but actually is about the easy as clicking a button) like building a Hackintosh or Minecraft server.
3 - A certain someone who goes about insulting AMD and claiming that his Intel Core i5-2500K is superior gaming computer to the computer of yours truly despite playing games with the IGP and a 19" 4:3 screen.
4 - A special someone who's never built a computer in his life but just likes to show off. He claims that he knows everything about software and hardware right after person 2 made his computer for him after your truly picked out the parts for him. Has nothing better to do than to ask people in they know what a kernel or etc. is and asking them to define it after memorising the definition off Wikipedia. His biggest claim to "understanding exactly how software works" is installing Windows. As I'm sure that's really difficult...

And no, nobody listens to me.

I'm a girl after all.

What would I know about computers?
 


If I'm dealing with a tech savvy enough person, I'll direct them to what I regard as the big 3 in review sites(i.e. Tom's, AnandTech and The Tech Report).

 


I would totally come back at you with a sexist comment/joke, but those are old fashioned and not hip n' cool anymore, hahaha.

Anyway... Yes, tech sites are important to get more information about products and services, but not very "regular joe" friendly, since you can not avoid being technical about things; using non-quantified things will become subjective (terms like "oh, this is fast!" without numbers to back it up are very subjective, for instance). Regular advice for those looking for info is to don't stick to only one (at least for reviews) site and try to get all sides of the story if you can to get a fair assessment of what you're looking for. And just like a big fancy commercial ad alters the mind of "regular joe", biased reviews alter the mind of regular "enthusiast kiddos"; we gotta fight those and set some records straight. Also, you're entitled to be wrong about stuff and learn from that, so you don't make the same mistake in your assumptions and such; but just make sure you're conscious about mistakes and try not to be a mr know-it-all. It's annoying, hahaha.

All in all, we help make the not-so-tech-savvy folks spend their hard earned money as wisely as possible. It's like we're doing a service to humanity, damn!

Well, regarding PD... Vishera has turned out to be better than Zambezi and we can actually recommend it in some scenarios; that'll keep competition going for a while in some price points. And Trinity is also a very good product, but hard to recommend, since most people are good with low GPU power and have great alternatives in the respective price points for each APU that can pull a regular screen for Excel and Facebook.

Cheers!
 


looooooooooooooooooooooooooool
 


Rule 37 of the Internets: there r no grlz on teh interwebz!
 
Status
Not open for further replies.

TRENDING THREADS