ICC is a faster compiler for AMD as well, but it's something like 5-7% for intel it's a little over 20% more efficient. That was the grounds for a lawsuit that AMD won, and intel has still not complied to the terms...3 years later.
intel has complied, albeit in their own way. they provide a switch according to court order. it's up to developers to use the switch or leave it as is. this comes down to amd having strong relationship with isvs. this has been discussed to death before.
8350rocks :
It's not really a drastic advantage, but it is an advantage none the less.
is that a roundabout, begrudging admission of fx being worse?
8350rocks :
FX8350 is $189 on outlet PC and i7-3770k is $309. $120 is 63% of $189.
what the heck is an outlet pc and why does it look like a hardware shop with an online outlet? why does web of trust give it lower credibility score than newegg? doesn't look better than newegg. anyway, in terms of price, fx8350 and core i7 aren't even in the same class. if you're gonna find some store that sells cheap cpus, why not go all the way to microcenter? fx8350 goes even cheaper - $180. core i5 3570k goes for $190 and core i7 3770k goes for $230.
8350rocks :
No one who buys an intel with onboard graphics for a desktop actually uses them...if you can afford $300 for a CPU, you can certainly afford $100 minimum for a 200% improvement in graphics over intel's iGPU...if anything...you have to count that as a negative for intel, because they might cost less without that rubbish built onto the chip.
after all that bragging about fx8350's 'advantages' you resort to this excuse. you were comparing cpu performance only, remember? actually a lot of people (if not majority of users) use only igpu, especially in office number crunchers.
what's the point of running benches if you can't see them? that's where fx falls flat on it's face. you don't need a $100 discreet gfx card to see how cpu benches turned out, just enough to see the results, so even a rubbish igpu will do just fine. it's still huge drawback for fx.
8350rocks :
Besides FX8350 + HD 7750 costs less than i7-3770k by itself, and you get nearly equal CPU performance and 100% better graphics...so your cost argument is unjustified. Sure, you could talk about the i5-3570k, but the FX8350 is a better CPU to begin with, so you're paying more for less.
the cheapest pcie card is $30 on newegg ($13-25 at mc), no need for a 7750. my cost argument is very much justified (and valid) as i have successfully pointed out that fx does not have any means to display the cpu performance results. even better with core i5 3570k, we just end up paying more money for less/similar performance with fx, and more just to see the performance (before benching even starts) results, lol.
only way for fx to even match core i5/i7 is with discreet gfx (compare that with the microcenter prices ). since fx doesn't have any means for displaying results, even core i7 is instantly better when you compare strictly cpu vs cpu (which is what you were doing). i had to 'cheat' and added a way for fx to display it's bench results, 'cuz that's the only way fx will even think of coming close to matching a core i7 3770k.
8350rocks :
The architecture diagrams have been out since January of this year. The 30% figure is quoted against piledriver not bulldozer.
where does it say that the 30% perf/watt improvement is against piledriver. i'd like to see that.
8350rocks :
Does intel quote haswell as an improvement % of sandy bridge or ivy bridge? No one compares their improvement to architecture that is 2 generations ago...only the current generation. Kaveri is coming with Steamroller cores as well...it has been announced by AMD that it will likely be the first steamroller product out, with FX series desktop CPUs on the heels of it in Q1 2014.
why is haswell even relevant here? we're comparing fx with core i5//i7. intel (amd too) often sinks to new lows when comparing performances. they claimed 200%+ improvement with hd4600 (haswell gt2) which turned out to be against hd2000 (or was it 2500, i don't care anymore ). amd does the same thing as well (bulldozer beats core i7 980x). it's called benchmarketing, intel, amd, nvidia all do this.
almost all of us here knew of kaveri having sr cores for a long time, but amd themselves semi-confirmed it and then went silent. after that there was a strong rumor of sr (or was it kaveri) being cancelled after not passing internal evaluation to which amd only vaguely responded.
8350rocks :
Google Global Foundries 20nm 3D TSV...just let me know what happens.
i googled it. right from glofo's page:
At its Fab 8 campus in Saratoga County, N.Y., the company has demonstrated its first functional 20nm silicon wafers with integrated Through-Silicon Vias (TSVs). Manufactured using GLOBALFOUNDRIES’ leading-edge 20nm-LPM process technology, the TSV capabilities will allow customers to stack multiple chips on top of each other, providing another avenue for delivering the demanding performance, power, and bandwidth requirements of today’s electronic devices.
now, my limited knowledge says that LPM means low power mobility, not high performance (which is called hp or hpp afaik). are you saying that amd will make excavator on low power mobile node? the exc opterons too?
8350rocks :
I am not talking poorly about AMD, I am being brutally honest about strengths and weaknesses, though it seems the intel guys don't like to talk about the weakness of the product they prefer too much...sore spot maybe?
well, your honestly revealed a lot of gaps in your own claims. that's brutally true.
....i dunno, ask intel guys.
Losing performance or barely gaining i think i added like 30 benchmarks last year and it turned out to be 8-12% faster on average compared to a 1100T while being clocked 9% more and having a turbo that actually worked.
I think people will be let down and surprised with steamroller i hope it turns out, i want one.
intel has complied, albeit in their own way. they provide a switch according to court order. it's up to developers to use the switch or leave it as is. this comes down to amd having strong relationship with isvs. this has been discussed to death before.
what the heck is an outlet pc and why does it look like a hardware shop with an online outlet? why does web of trust give it lower credibility score than newegg? doesn't look better than newegg. anyway, in terms of price, fx8350 and core i7 aren't even in the same class. if you're gonna find some store that sells cheap cpus, why not go all the way to microcenter? fx8350 goes even cheaper - $180. core i5 3570k goes for $190 and core i7 3770k goes for $230.
PCpartpicker.com recommends them as a source for purchase along with TigerDirect, newegg, MicroCenter and Superbiiz to name a few
after all that bragging about fx8350's 'advantages' you resort to this excuse. you were comparing cpu performance only, remember? actually a lot of people (if not majority of users) use only igpu, especially in office number crunchers.
what's the point of running benches if you can't see them? that's where fx falls flat on it's face. you don't need a $100 discreet gfx card to see how cpu benches turned out, just enough to see the results, so even a rubbish igpu will do just fine. it's still huge drawback for fx.
Ok, by your own admission fx8350 + $40 graphics card costs same as i5-3570k and the graphics on the $40 GPU are still better...besides...if you want to enter that debate we can talk about the A10-5800k which is a far superior solution for that same issue, and it costs $120. Now you save $100 and get a better product.
the cheapest pcie card is $30 on newegg ($13-25 at mc), no need for a 7750. my cost argument is very much justified (and valid) as i have successfully pointed out that fx does not have any means to display the cpu performance results. even better with core i5 3570k, we just end up paying more money for less/similar performance with fx, and more just to see the performance (before benching even starts) results, lol.
only way for fx to even match core i5/i7 is with discreet gfx (compare that with the microcenter prices ). since fx doesn't have any means for displaying results, even core i7 is instantly better when you compare strictly cpu vs cpu (which is what you were doing). i had to 'cheat' and added a way for fx to display it's bench results, 'cuz that's the only way fx will even think of coming close to matching a core i7 3770k.
Look @ wccftech's review of steamroller architecture, they quote AMD's press release directly.
why is haswell even relevant here? we're comparing fx with core i5//i7. intel (amd too) often sinks to new lows when comparing performances. they claimed 200%+ improvement with hd4600 (haswell gt2) which turned out to be against hd2000 (or was it 2500, i don't care anymore ). amd does the same thing as well (bulldozer beats core i7 980x). it's called benchmarketing, intel, amd, nvidia all do this.
almost all of us here knew of kaveri having sr cores for a long time, but amd themselves semi-confirmed it and then went silent. after that there was a strong rumor of sr (or was it kaveri) being cancelled after not passing internal evaluation to which amd only vaguely responded.
Steamroller was confirmed as being out Q4 2013 2 weeks ago.
i googled it. right from glofo's page:
At its Fab 8 campus in Saratoga County, N.Y., the company has demonstrated its first functional 20nm silicon wafers with integrated Through-Silicon Vias (TSVs). Manufactured using GLOBALFOUNDRIES’ leading-edge 20nm-LPM process technology, the TSV capabilities will allow customers to stack multiple chips on top of each other, providing another avenue for delivering the demanding performance, power, and bandwidth requirements of today’s electronic devices.
now, my limited knowledge says that LPM means low power mobility, not high performance (which is called hp or hpp afaik). are you saying that amd will make excavator on low power mobile node? the exc opterons too?
And it was Kaveri that was rumored to be canceled. But I don't think that was true. They may have thought about it, but the numbers are there to change the APU game.
The question is how long of a lead will AMD have in getting these Jaguars on the market before the 22nm Atoms come out. As Intel ramps Broadwell on 14nm in Q4, the 22nm capacity will open up for Atoms.
it was a fix, in accordance with the lawsuit's verdict. amd, for some reason didn't push further. 'meh' is what amd decided to live with.
8350rocks :
PCpartpicker.com recommends them as a source for purchase along with TigerDirect, newegg, MicroCenter and Superbiiz to name a few
Ok, by your own admission fx8350 + $40 graphics card costs same as i5-3570k and the graphics on the $40 GPU are still better...besides...if you want to enter that debate we can talk about the A10-5800k which is a far superior solution for that same issue, and it costs $120. Now you save $100 and get a better product.
are you're seriously trying to segue to gpu performance and apus? lawl! we are comparing cpu (fx8350 vs core i5 3570k/i73770k) performance, not gpu performance. here, the igpu or any gpu is just a display output to show the results, nothing else. if you're gonna bring in a10-5800k, a core i5 can easily outperform it in terms of cpu performance let alone an i7. apus are irrelevant to current discussion (just keep in mind that even an i5 can outperform any apu in cpu perf).
8350rocks :
Ok, then $180 + $30 != $300...90% performance for 60-70% of the cost?
assuming your math is right, yes. but the sheer need for 'cheat' (need of a display output via discreet gfx) is a glaring drawback for fx.
but... wait, your math is wrong. you didn't compare microcenter's fx ($180) price to mc's core i5 ($190) or i7 price ($230) (i just rechecked mc prices). you're being so unfair. hahaha
seems that even when you go the cheapest, fx+ dgfx combo($180+$12to$25) just loses against core i7 for too small difference in price, and instantly loses against core i5 3570k.
your attempt is amusing. wrong, but amusing nonetheless.
8350rocks :
Look @ wccftech's review of steamroller architecture, they quote AMD's press release directly.
oh no. even amd fanboys dislike wccdefghnocredtech. again, i'd like to see i.e. some kind of credible article or official press release. also check the date, if it's before or after the nearly credible rumor of kaveri/sr failing internal evaluation.
8350rocks :
Steamroller was confirmed as being out Q4 2013 2 weeks ago.
What? steamroller is coming out in q4 2013. confirmed 2 weeks ago, no less. is there any official confirmation from amd? i can't believe i missed something so big when i've been closely following steamroller/kaveri related info for months. even if it's credible, q4 can easily be december and then quietly slip to 2014. historically, amd has launched their cpus(fx) in october-november timeline. and, they have officially stated that piledriver(vishera) will remain flagship (am3+) throughout 2013. so there is a big contradiction here.
8350rocks :
That's just what's being release first...read more...
read more where? i searched through the glofo site, no mention of 3d or tsv for high performance nodes. heck, i found nothing on 20nm high performance node. only confirmation is on 28nm hpp which will manufacture kaveri apus and possibly steamroller cpus.
someone help me out here, what am i missing? most of the new stuff from 20nm to 14nm is mostly about mobility - low power, ulp, and arm socs.
8350rocks :
No holes man...only truth
'truth'? you tried to divert to igpu performance comparison(fx8350 doesn't even have one ) and then went on to unfairly skew price comparisons. :lol:
intel has complied, albeit in their own way. they provide a switch according to court order. it's up to developers to use the switch or leave it as is. this comes down to amd having strong relationship with isvs. this has been discussed to death before.
the problem is the way intel implemented the switch. If used to specify AVX for the maximum speed code, it will NOT RUN on any cpu that doesn't have AVX because you specified it not to write any lesser code. Who in any form of business will do that? End users, sure, businesses who want sales won't.
it was a fix, in accordance with the lawsuit's verdict. amd, for some reason didn't push further. 'meh' is what amd decided to live with.
It was part of the 1.25B. This was also a hush fund where AMD wasn't allowed to complain further. Complaints now have to come from public domain, and who has the money to fight Intel?
Until some future event allows AMD to open another case against Intel's practices, they can't bring up the past. That doesm't mean the public should ignore the fact that IT DID HAPPEN, and is still afflicted today.
Here's a few quotes that were appearing before my post, on Page 51,
griptwister said:
Anyways, I'm curios to see how a 5Ghz chip compares to a 4 Ghz chip when people say they don't notice a performance improvement past 4.5Ghz on the 8350 chip. Also, how will this chip compete against Intel? Especially at that price point. I just don't see this chip beating a hexicore i7, even at 5 ghz. Unless they somehow changed the singlethread performance...
and ever since you have been trying to defend your 50% on average claim, even changing it from SB to all Intel cpus, trying to maintian the 50% lead.
all back-pedaling ... and a sudden "AAC is my favorite" defensive measure. I have never insulted you, just trying to offer advice that AAC != average performance.
I repeat again, all this is just my fancy guess work, and for all you know I could be very wrong.
First of all, noob cool down. I am not planning to put you down in this forum in anyway, and that is not my intention. Let's have a discussion, not an argument.
Don't pretend to be naive, and try to change the topic. The argument was with respect to single threaded IPG ratios from the very start of your discussion with me.
It was people like you who just read 50% and then went crazy!!
50% to 23% against SB is a huge margin of error, one you seem to continue to defend with changing the initial data.
Another funny thing is the choice in how the wording that is used. Intel being 51% faster is also the same as AMD only being 33% slower, Same as intel being 23% faster is only amd being 19% slower. Notice how AMD only needed 14% increase to gain 28% towards Intel? What happens IF Steamroller is actually 15-20% over pd?
And it was Kaveri that was rumored to be canceled. But I don't think that was true. They may have thought about it, but the numbers are there to change the APU game.
May have been thinking of Krishna/Wichita which were 28nm follow ups to Brazos that were scrapped in favor of Jaguar.
Which again breaks down to efficiency. You're comparing a refined architecture that's been improved many times, to 2nd gen architecture. The efficiency is going to be drastically better for intel. That's what it is...fewer miscalculations through the front end of the architecture allow intel to run more efficiently at the CPU level. Though I still do not accept your argument entirely on the grounds that systems were not optimized for the individual architectures.
I never said that; I said specifically, "assuming" the code paths are more or less the same. Only way to know for sure would be to decompile the program and go looking for processor macros. Its entirely possible the app is using an Intel codepath that is significantly more efficient, thus giving it better numbers. Likewise, I also pointed out (numerous times) that if you don't get 100% core scaling in multithreaded benchmarks, the numbers get skewed (though you can at least correct by using Task Manger in this case).
If Intel was 51% better than AMD...then how on earth does the FX8350 beat Intel's i5-3570k and i7-3770k at so many things? Is it just 175% better at certain things? How do you close the loop for your logic?
Clockspeed. IPC calculations remove clockspeed from consideration, but that extra 600+MHz per core? Yeah, that makes up for a LOT in terms of performance.
Ok, let's compare a wide range of benchmarks, shall we:
Microsoft Excel 2007 SP1 Monte Carlo:
FX8350: 12.6
i7-3770k: 10.0 (+26%)
7-zip:
FX8350: 23407 (+2.6%)
i7-3770k: 22810
Doesn't look so drastically offset anymore does it? Hmm...that's interesting...so the FX8350 keeps within 10-20% of the i7-3770k in nearly everything but extremely singlethreaded applications with very specific uses? It also destroys the i5-3570k at nearly everything...how odd...but I thought...the i5-3570k was supposed to be the second coming or something...funny, huh?
Trying to figure out your conclusion here. I see one significant (>10%) win for FX (TrueCrypt 7.1a) and, even throwing out the signlethreaded benchmarks, 5 >10% wins for Intel (WinRAR 4.2, iTunes, Adobe Lightroom 4.2, x264 encoding (1st pass), 3ds max 2011(CPU), POV_RAY 3.7RC6 Multithreaded). Throw in the single threaded benchmarks, and you end up with a rout.
And that's the problem, the same exact one I pointed out back when BD was in its early design stages: The majority of work is going to be done on a limited number of threads, so IPC + Clockspeed is a greater performance factor then number of cores. Yes, FX "hangs around" due to a clock speed advantage, but how long is that going to last do you think? What happens when Intel starts releasing chips at 3.8GHz stock and throws a +10% IPC gain? Woops, Intel takes a giant performance lead again, and AMD needs to re-design their arch to be more IPC friendly. FX is basically banking on the fact Intel won't be able to close in clockspeed, and given Intels inherent process edge, I really doubt that will be the case.
Simple test: Clock an i5 at 3.8GHz and retest. FX suddenly won't look nearly as attractive. Thats the danger AMD is walking into: If Intel closes in clockspeed, AMD is done.
(Also, does anyone else REALLY hate the descending quotes in the new forums? Can we at least get an option to disable those when quoting someone?)
i (ab)use the spoiler tag to hide walls of text. it still doesn't make replying easier though, as your reply has noob's id but you're clearly replying to someone else. new quoting system has higher chance of mis-edits, lol.
The new forum is horrid. I can't even log in with my phone now, and the edit area doesn't "submit", just sits there, button is non-functional. I have to wite it all out, preview, then copy/paste it back on the first page where I can use the "submit answer"
Another funny thing is the choice in how the wording that is used. Intel being 51% faster is also the same as AMD only being 33% slower, Same as intel being 23% faster is only amd being 19% slower. Notice how AMD only needed 14% increase to gain 28% towards Intel? What happens IF Steamroller is actually 15-20% over pd?
Noob222 clearly addressed this...it was part of the settlement money Intel had to pay.
are you're seriously trying to segue to gpu performance and apus? lawl! we are comparing cpu (fx8350 vs core i5 3570k/i73770k) performance, not gpu performance. here, the igpu or any gpu is just a display output to show the results, nothing else. if you're gonna bring in a10-5800k, a core i5 can easily outperform it in terms of cpu performance let alone an i7. apus are irrelevant to current discussion (just keep in mind that even an i5 can outperform any apu in cpu perf).
The i5-3570k might win a raw CPU comparison...but run a game with it on intel's iGPU and see who has framerates worth playing. Do not forget, it is your angle about the iGPU...I told you it was rubbish to begin with. So don't insinuate I am the one changing gears...you are. The iGPU is garbage, plain and simple. Even people who buy the CPU just for running monte carlo sims or whatever would spend money on a better GPU...it's that necessary Especially high end rendering machines for companies that would even bother to spend more than the FX8350, and they would only do so because they needed the extra performance. So, if they were going to go that far, you don't think they would put at least a workstation card in it? Much less the possibility of 2-4 in the same machine to quickly perform a full scale 3d model render? Your argument holds as much water as a minnow seine.
assuming your math is right, yes. but the sheer need for 'cheat' (need of a display output via discreet gfx) is a glaring drawback for fx.
but... wait, your math is wrong. you didn't compare microcenter's fx ($180) price to mc's core i5 ($190) or i7 price ($230) (i just rechecked mc prices). you're being so unfair. hahaha
seems that even when you go the cheapest, fx+ dgfx combo($180+$12to$25) just loses against core i7 for too small difference in price, and instantly loses against core i5 3570k.
your attempt is amusing. wrong, but amusing nonetheless.
It's on special at MicroCenter...so what...right now for 1 more week you can buy it for that...then it's back up to $289-$299 where it was before. Additionally...you seem to forget that the FX8350 beats the i7-3770k in many categories...so...it's not a "drastically" superior chip...at all. For the same cost CPU vs CPU FX8350 > i5-3570k. You cannot prove otherwise...there are 2 benchmarks where the i5 actually wins, the rest it loses or the results are within margin of error...those are AAC encoding (itunes, etc.) and skyrim. Your basing your claims on false info. The benchmarks posted earlier disprove your argument for i5-3570k value, and the only reason the argument about the i7-3770k is even remotely feasible is because you have 7 more days of price savings...otherwise the value is less than the cost on the i7.
oh no. even amd fanboys dislike wccdefghnocredtech. again, i'd like to see i.e. some kind of credible article or official press release. also check the date, if it's before or after the nearly credible rumor of kaveri/sr failing internal evaluation.
Actually, it was a quote directly from the AMD press release...pretty hard to fudge that...it was also well after the Kaveri rumor. AMD's quarterly investor presentation at the end of march is what showed Steamroller was still on track...google it. Do some research...maybe you'll stop posting rubbish without facts after you actually read some of this stuff.
What? steamroller is coming out in q4 2013. confirmed 2 weeks ago, no less. is there any official confirmation from amd? i can't believe i missed something so big when i've been closely following steamroller/kaveri related info for months. even if it's credible, q4 can easily be december and then quietly slip to 2014. historically, amd has launched their cpus(fx) in october-november timeline. and, they have officially stated that piledriver(vishera) will remain flagship (am3+) throughout 2013. so there is a big contradiction here.
Historically releasing something at X time means nothing.
Look here and see...you must have missed it, since everyone from the no names to the big names covered it.
read more where? i searched through the glofo site, no mention of 3d or tsv for high performance nodes. heck, i found nothing on 20nm high performance node. only confirmation is on 28nm hpp which will manufacture kaveri apus and possibly steamroller cpus.
someone help me out here, what am i missing? most of the new stuff from 20nm to 14nm is mostly about mobility - low power, ulp, and arm socs.
If you read here:
http://thefoundryfiles.com/category/technology/
They state that it is only the first step into the 20nm node. They will develop applications on the 20nm and 14nm-XM processes further. The difference is, because of customer demand, the LPM wafers were the first thing they have perfected with the 3D TSV process of creating the silicon. 20nm silicon is already shipping in early stages to developers for them to start to design their processes around. Production on 20nm TSV is ramping up toward the end of this year for LPM, and will begin for other products based on that architecture after that.
'truth'? you tried to divert to igpu performance comparison(fx8350 doesn't even have one ) and then went on to unfairly skew price comparisons. :lol:
I no more skewed price comparisons using an average cost, then you did by trying to insinuate there was any advantage to intel having on board graphics...that's like trying to sell "magic beans" to a farmer looking for cattle feed. It's a simple fact that many people out there care nothing for intel's onboard graphics. If you wanted to try to argue that with an i3 for a HTPC...you might have an argument. But the i5-3570k with onboard graphics is a flatout inside joke for intel. On the i7-3770k it's ridiculous.
as for early dev, LPM and clock cycles are intended to be low, much more easier done, by both the foundry and its partners, just see 7970 which isnt LPM by the way
signal strength i much lower as well of course
Caz their also doing changes to the cache mechanism. Right now it use's a very weird way of accessing cache that results in very inefficient reads and writes unless the machine code is done a certain way. Agner bumped into that, its one of the reasons the BD/PD CPUs get such poor L2 cache performance. AMD is supposed to be fixing that and increasing the read / write buffer and reducing the latency to commit writes. ~If~ their successful then it will be a very big performance fix for them.
On a slightly different tangent, I've been looking to rebuild my home server system and stumbled across some very interesting parts. Previously I was using a VE-900, which works amazing btw, though it's PCI slot absolutely hates my Sil3124 card which I need to plug my external eSATA array into. So I went looking for a replacement and found this gem.
I can just plug in a 2.5 inch HDD and my array into the back eSATA port. *Poof* home network server.
Wonder how the next round of incredibly small / low power Mini-ITX boards will look like. Via has the market cornered on anything requiring tons of COM ports and GPIO and it's looking like AMD is cornering the HTPC and home server segments.
I do hope AMD Pull a rabbit out of there hat with this revision of the architectural silicone,
It will be interesting, Its always good to have competition in any sort of market.I do hope AMD Pull a rabbit out of there hat with this revision of the architectural silicone,
It will be interesting, Its always good to have competition in any sort of market.
Wonder how the next round of incredibly small / low power Mini-ITX boards will look like. Via has the market cornered on anything requiring tons of COM ports and GPIO and it's looking like AMD is cornering the HTPC and home server segments.
With Kabini/Temash they'll get even smaller. The chipset is integrated.
Saw these today. Gigabyte getting into the NUC space too.
the problem is the way intel implemented the switch. If used to specify AVX for the maximum speed code, it will NOT RUN on any cpu that doesn't have AVX because you specified it not to write any lesser code.
Do you have any idea what are you talking about ?
Learn the difference between 'march' and 'mtune' .
Learn the difference between /Qx, /Qax , /arch:target,
Learn what is meant by code dispatcher. Learn what is meant by run time codepath selection.
Till you learn, stop talking out of your ass. You dont know the first thing about what you are so confidently blathering about.
the problem is the way intel implemented the switch. If used to specify AVX for the maximum speed code, it will NOT RUN on any cpu that doesn't have AVX because you specified it not to write any lesser code. Who in any form of business will do that? End users, sure, businesses who want sales won't.
It was part of the 1.25B. This was also a hush fund where AMD wasn't allowed to complain further. Complaints now have to come from public domain, and who has the money to fight Intel?
Until some future event allows AMD to open another case against Intel's practices, they can't bring up the past. That doesm't mean the public should ignore the fact that IT DID HAPPEN, and is still afflicted today.
yeah, that's how intel did it. it's the sad state of corporate ethics (or lack of it). no one is ignoring that it happened. from outside, it looks like amd decided to put up and shut up. only some people(not amd) cry about it from time to time. still, amd has to do something about their own compiler since intel's isn't helping at all.
8350rocks :
The i5-3570k might win a raw CPU comparison...but run a game with it on intel's iGPU and see who has framerates worth playing. Do not forget, it is your angle about the iGPU...I told you it was rubbish to begin with. So don't insinuate I am the one changing gears...you are.
where did gaming on intel's igpu (vs the apus) come from? now i know you're really trying to divert away from core i5 3570k/core i7 3770k vs fx8350's cpu comparison. my stance about the igpu is that it's there for displaying bench results, nothing else. it hasn't changed ever since i pointed it out. does fx8350's igpu display anything or play games? oh wait...
8350rocks :
The iGPU is garbage, plain and simple. Even people who buy the CPU just for running monte carlo sims or whatever would spend money on a better GPU...it's that necessary Especially high end rendering machines for companies that would even bother to spend more than the FX8350, and they would only do so because they needed the extra performance. So, if they were going to go that far, you don't think they would put at least a workstation card in it? Much less the possibility of 2-4 in the same machine to quickly perform a full scale 3d model render? Your argument holds as much water as a minnow seine.
now you're just assuming things (that "if people buy this, they can also buy that" - totally irrelevant to the cpu performance comparison) instead of sticking to the point: in a cpu vs cpu comparison, fx8350 loses simply due to lack of a display output against core i5 3570k/i7 3770k. you can run povray et al on fx all day, unless you can see the benches, it's worthless. i said this earlier, and say this again - the igpu inside core i5/i7 is just there for display output. it does not contribute to (cpu vs cpu) performance. that's why i mercifully awarded the fx a discreet gfx, just so it could show it's benches and results. but doing that adversely affected fx's value. simple. trying to change the topic isn't helping your 'cause' at all. :lol:
as for 'high end rendering machines' - those use gpu acceleration, mostly nvidia and amd's workstation cards with either xeons or opteron pcs (not fx). actually, lga2011 core i7 (even some of those use low end gfx cards only for display and minor gpu accelerated tasks) are much more common in those machines than fx, but that's a whole different discussion (we're comparing fx with core i5 3570k and 3770k cpu performance). even one was to build a low end number cruncher, the cpu will still need a rudimentary display - that's where fx falls down.
8350rocks :
It's on special at MicroCenter...so what...right now for 1 more week you can buy it for that...then it's back up to $289-$299 where it was before.
where does it say that core i7's price on microcenter is a special offer? why shouldn't people take advantage of the offer if it is really one? after checking the 'hot ad deals' page's processors section, i noticed that fx8350, core i5 3570k and core i7 3770k all are on that list, not just core i7. that's why i said not to throw around prices, they change on a daily basis. i simply posted the prices at the time of discussion.
8350rocks :
Additionally...you seem to forget that the FX8350 beats the i7-3770k in many categories...so...it's not a "drastically" superior chip...at all.
like what, the ability to display such 'winnings'? :lol: that alone give core i7 a 'drastic superiority' (your own words, i never said core i7 is much, much better than fx in cpu performance ). if you're gonna claim 'many categories' - most of those are multithreaded synthetic benches like povray or the ones that use amd's specific instruction sets. the only real world benches where fx competes well against core i7 is in some video editing suits and 7zip. unless the software uses all 8 integer clusters, fx cannot even get close to a core i7 let alone beat it.
8350rocks :
For the same cost CPU vs CPU FX8350 > i5-3570k. You cannot prove otherwise...there are 2 benchmarks where the i5 actually wins,
here's your mistake: it's not for the same cost. it's the same price without the discreet gfx that the fx badly needs to show it's 'wins'. that's long before benchmarking even starts (fx d.o.a., or defeated at starting point). how're you gonna see those 'wins' without display, huh? you were comparing strictly cpu vs cpu, guess what, the core i5/7 come with display output built in, fx doesn't - instant loss for fx in that kind of comparison.
8350rocks :
the rest it loses or the results are within margin of error...those are AAC encoding (itunes, etc.) and skyrim. Your basing your claims on false info. The benchmarks posted earlier disprove your argument for i5-3570k value, and the only reason the argument about the i7-3770k is even remotely feasible is because you have 7 more days of price savings...otherwise the value is less than the cost on the i7.
i am basing my claims on facts and benches from credible sources like toms. the core i5 only loses where the software uses all 8 of fx's integer clusters - real world examples would be 2-pass x264 encoding, truecrypt and 7zip. every other time it either handily beats fx (even in multithreaded applications that scale up to 4-5 cores only) or comfortably keeps up with it, within very acceptable margins. majority of current mainstream multi-core-friendly softwares don't scale beyond 4 cores. that's unfortunate, but true. by the time majority softwares use 6 cores, both amd and intel will have new solutions (sorta like what happened with thuban cpus).
you bring up a good point, actually. in games, i5/i7s maintain a significant advantage over fx. not just in skyrim or starcraft. in far cry, guild wars, multiplayer games, dirt 3, showdown, f1 games, crysis 3 (despite it being mostly gpu bound) and so on. toms' own tests show that clearly. and the amount of cooling and power needed to oc the fx just to beat i5/i7's stock perf makes fx's value degrade further. since you were comparing cpu vs cpu, cpu bound games (unlike gpu bound ones) somewhat fit into the discussion (provided both intel and amd rig has a gaming card like 7950/7870xt/7970/gtx670/680 and such assuming your 'if people can buy this, that can buy that'.) where i5 and i7 deliver noticeably higher performance even at stock. but here we're not really comparing strictly cpu performance, are we? we're comparing cpu+ discreet gaming card combos. even in strictly cpu vs cpu comparo - i5 and i7 instantly beat fx because intel's can play at least some games (only for academic benching purposes, lol) because of the built in igpu - then we slip into igpu performance, not cpu.
your argument about fx is much less feasible than mine about core i7. no display, no worth - remember?
8350rocks :
Actually, it was a quote directly from the AMD press release...pretty hard to fudge that...it was also well after the Kaveri rumor. AMD's quarterly investor presentation at the end of march is what showed Steamroller was still on track...google it. Do some research...maybe you'll stop posting rubbish without facts after you actually read some of this stuff.
i do my research just fine, that's why i asked you to post links because of your claim. your lack of posting anything credible after multiple requests shows your own failure.
8350rocks :
Historically releasing something at X time means nothing. Look here and see...you must have missed it, since everyone from the no names to the big names covered it.
no. i didn't miss amd's declaration to release steamroller opterons or kaveri apus. where are links for the mainstream desktop steamroller(fx)?
8350rocks :
If you read here:
http://thefoundryfiles.com/category/technology/
They state that it is only the first step into the 20nm node. They will develop applications on the 20nm and 14nm-XM processes further. The difference is, because of customer demand, the LPM wafers were the first thing they have perfected with the 3D TSV process of creating the silicon. 20nm silicon is already shipping in early stages to developers for them to start to design their processes around. Production on 20nm TSV is ramping up toward the end of this year for LPM, and will begin for other products based on that architecture after that.
but, how long after the lpm ramp up do the high performance nodes get that capability? is it before or after intel releases 14nm broadwell/skylake cpus? 'cusz intel will launch 14nm broadwell in 2014 when 28nm (possibly) steamroller cpus come out. tbh, that's so far in the future, i don't know for sure what will happen. we get there when we get there.
that article is all about why 14nm-xm is not a misnomer, nothing on 20nm hp node.
8350rocks :
I no more skewed price comparisons using an average cost, then you did by trying to insinuate there was any advantage to intel having on board graphics...that's like trying to sell "magic beans" to a farmer looking for cattle feed. It's a simple fact that many people out there care nothing for intel's onboard graphics. If you wanted to try to argue that with an i3 for a HTPC...you might have an argument. But the i5-3570k with onboard graphics is a flatout inside joke for intel. On the i7-3770k it's ridiculous.
average cost? of what? you posted instantenous prices, so did i (except mine were consistent and cheaper).
prices change almost everyday. that's why you claiming core i5/i7 selling for much higher prices than fx does not hold any value. i showed that from the cheapest source (mc, in this case), prices are close enough to skip fx for core i7/i5 considering cpu performance. value gets worse for fx when you must add a discreet gfx (no matter how minor) just for display.
the 3570k/3770k does have igpu and fx does not. having a crappy one is better than having none. that single attibute gives 3570k/3770k an advantage fx8350 cannot simply beat, before benching even starts. and it's enough for fx's instant defeat.
the problem is the way intel implemented the switch. If used to specify AVX for the maximum speed code, it will NOT RUN on any cpu that doesn't have AVX because you specified it not to write any lesser code. Who in any form of business will do that? End users, sure, businesses who want sales won't.
It was part of the 1.25B. This was also a hush fund where AMD wasn't allowed to complain further. Complaints now have to come from public domain, and who has the money to fight Intel?
Until some future event allows AMD to open another case against Intel's practices, they can't bring up the past. That doesm't mean the public should ignore the fact that IT DID HAPPEN, and is still afflicted today.
yeah, that's how intel did it. it's the sad state of corporate ethics (or lack of it). no one is ignoring that it happened. from outside, it looks like amd decided to put up and shut up. only some people(not amd) cry about it from time to time. still, amd has to do something about their own compiler since intel's isn't helping at all.
8350rocks :
The i5-3570k might win a raw CPU comparison...but run a game with it on intel's iGPU and see who has framerates worth playing. Do not forget, it is your angle about the iGPU...I told you it was rubbish to begin with. So don't insinuate I am the one changing gears...you are.
where did gaming on intel's igpu (vs the apus) come from? now i know you're really trying to divert away from core i5 3570k/core i7 3770k vs fx8350's cpu comparison. my stance about the igpu is that it's there for displaying bench results, nothing else. it hasn't changed ever since i pointed it out. does fx8350's igpu display anything or play games? oh wait...
8350rocks :
The iGPU is garbage, plain and simple. Even people who buy the CPU just for running monte carlo sims or whatever would spend money on a better GPU...it's that necessary Especially high end rendering machines for companies that would even bother to spend more than the FX8350, and they would only do so because they needed the extra performance. So, if they were going to go that far, you don't think they would put at least a workstation card in it? Much less the possibility of 2-4 in the same machine to quickly perform a full scale 3d model render? Your argument holds as much water as a minnow seine.
now you're just assuming things (that "if people buy this, they can also buy that" - totally irrelevant to the cpu performance comparison) instead of sticking to the point: in a cpu vs cpu comparison, fx8350 loses simply due to lack of a display output against core i5 3570k/i7 3770k. you can run povray et al on fx all day, unless you can see the benches, it's worthless. i said this earlier, and say this again - the igpu inside core i5/i7 is just there for display output. it does not contribute to (cpu vs cpu) performance. that's why i mercifully awarded the fx a discreet gfx, just so it could show it's benches and results. but doing that adversely affected fx's value. simple. trying to change the topic isn't helping your 'cause' at all. :lol:
as for 'high end rendering machines' - those use gpu acceleration, mostly nvidia and amd's workstation cards with either xeons or opteron pcs (not fx). actually, lga2011 core i7 (even some of those use low end gfx cards only for display and minor gpu accelerated tasks) are much more common in those machines than fx, but that's a whole different discussion (we're comparing fx with core i5 3570k and 3770k cpu performance). even one was to build a low end number cruncher, the cpu will still need a rudimentary display - that's where fx falls down.
8350rocks :
It's on special at MicroCenter...so what...right now for 1 more week you can buy it for that...then it's back up to $289-$299 where it was before.
where does it say that core i7's price on microcenter is a special offer? why shouldn't people take advantage of the offer if it is really one? after checking the 'hot ad deals' page's processors section, i noticed that fx8350, core i5 3570k and core i7 3770k all are on that list, not just core i7. that's why i said not to throw around prices, they change on a daily basis. i simply posted the prices at the time of discussion.
8350rocks :
Additionally...you seem to forget that the FX8350 beats the i7-3770k in many categories...so...it's not a "drastically" superior chip...at all.
like what, the ability to display such 'winnings'? :lol: that alone give core i7 a 'drastic superiority' (your own words, i never said core i7 is much, much better than fx in cpu performance ). if you're gonna claim 'many categories' - most of those are multithreaded synthetic benches like povray or the ones that use amd's specific instruction sets. the only real world benches where fx competes well against core i7 is in some video editing suits and 7zip. unless the software uses all 8 integer clusters, fx cannot even get close to a core i7 let alone beat it.
8350rocks :
For the same cost CPU vs CPU FX8350 > i5-3570k. You cannot prove otherwise...there are 2 benchmarks where the i5 actually wins,
here's your mistake: it's not for the same cost. it's the same price without the discreet gfx that the fx badly needs to show it's 'wins'. that's long before benchmarking even starts (fx d.o.a., or defeated at starting point). how're you gonna see those 'wins' without display, huh? you were comparing strictly cpu vs cpu, guess what, the core i5/7 come with display output built in, fx doesn't - instant loss for fx in that kind of comparison.
8350rocks :
the rest it loses or the results are within margin of error...those are AAC encoding (itunes, etc.) and skyrim. Your basing your claims on false info. The benchmarks posted earlier disprove your argument for i5-3570k value, and the only reason the argument about the i7-3770k is even remotely feasible is because you have 7 more days of price savings...otherwise the value is less than the cost on the i7.
i am basing my claims on facts and benches from credible sources like toms. the core i5 only loses where the software uses all 8 of fx's integer clusters - real world examples would be 2-pass x264 encoding, truecrypt and 7zip. every other time it either handily beats fx (even in multithreaded applications that scale up to 4-5 cores only) or comfortably keeps up with it, within very acceptable margins. majority of current mainstream multi-core-friendly softwares don't scale beyond 4 cores. that's unfortunate, but true. by the time majority softwares use 6 cores, both amd and intel will have new solutions (sorta like what happened with thuban cpus).
you bring up a good point, actually. in games, i5/i7s maintain a significant advantage over fx. not just in skyrim or starcraft. in far cry, guild wars, multiplayer games, dirt 3, showdown, f1 games, crysis 3 (despite it being mostly gpu bound) and so on. toms' own tests show that clearly. and the amount of cooling and power needed to oc the fx just to beat i5/i7's stock perf makes fx's value degrade further. since you were comparing cpu vs cpu, cpu bound games (unlike gpu bound ones) somewhat fit into the discussion (provided both intel and amd rig has a gaming card like 7950/7870xt/7970/gtx670/680 and such assuming your 'if people can buy this, that can buy that'.) where i5 and i7 deliver noticeably higher performance even at stock. but here we're not really comparing strictly cpu performance, are we? we're comparing cpu+ discreet gaming card combos. even in strictly cpu vs cpu comparo - i5 and i7 instantly beat fx because intel's can play at least some games (only for academic benching purposes, lol) because of the built in igpu - then we slip into igpu performance, not cpu.
your argument about fx is much less feasible than mine about core i7. no display, no worth - remember?
8350rocks :
Actually, it was a quote directly from the AMD press release...pretty hard to fudge that...it was also well after the Kaveri rumor. AMD's quarterly investor presentation at the end of march is what showed Steamroller was still on track...google it. Do some research...maybe you'll stop posting rubbish without facts after you actually read some of this stuff.
i do my research just fine, that's why i asked you to post links because of your claim. your lack of posting anything credible after multiple requests shows your own failure.
8350rocks :
Historically releasing something at X time means nothing. Look here and see...you must have missed it, since everyone from the no names to the big names covered it.
no. i didn't miss amd's declaration to release steamroller opterons or kaveri apus. where are links for the mainstream desktop steamroller(fx)?
8350rocks :
If you read here:
http://thefoundryfiles.com/category/technology/
They state that it is only the first step into the 20nm node. They will develop applications on the 20nm and 14nm-XM processes further. The difference is, because of customer demand, the LPM wafers were the first thing they have perfected with the 3D TSV process of creating the silicon. 20nm silicon is already shipping in early stages to developers for them to start to design their processes around. Production on 20nm TSV is ramping up toward the end of this year for LPM, and will begin for other products based on that architecture after that.
but, how long after the lpm ramp up do the high performance nodes get that capability? is it before or after intel releases 14nm broadwell/skylake cpus? 'cusz intel will launch 14nm broadwell in 2014 when 28nm (possibly) steamroller cpus come out. tbh, that's so far in the future, i don't know for sure what will happen. we get there when we get there.
that article is all about why 14nm-xm is not a misnomer, nothing on 20nm hp node.
8350rocks :
I no more skewed price comparisons using an average cost, then you did by trying to insinuate there was any advantage to intel having on board graphics...that's like trying to sell "magic beans" to a farmer looking for cattle feed. It's a simple fact that many people out there care nothing for intel's onboard graphics. If you wanted to try to argue that with an i3 for a HTPC...you might have an argument. But the i5-3570k with onboard graphics is a flatout inside joke for intel. On the i7-3770k it's ridiculous.
average cost? of what? you posted instantenous prices, so did i (except mine were consistent and cheaper).
prices change almost everyday. that's why you claiming core i5/i7 selling for much higher prices than fx does not hold any value. i showed that from the cheapest source (mc, in this case), prices are close enough to skip fx for core i7/i5 considering cpu performance. value gets worse for fx when you must add a discreet gfx (no matter how minor) just for display.
the 3570k/3770k does have igpu and fx does not. having a crappy one is better than having none. that single attibute gives 3570k/3770k an advantage fx8350 cannot simply beat, before benching even starts. and it's enough for fx's instant defeat.
If you're going to base an entire supremacy argument on iGPU...then this discussion is an epic fail and you live in an alternate reality.
For benchmarks showing FX8350 with higher benches than i5-3570k please refer to my post with about 20 benchmarks a few pages back.
in a cpu vs cpu comparison, fx8350 loses simply due to lack of a display output against core i5 3570k/i7 3770k. you can run povray et al on fx all day, unless you can see the benches, it's worthless. i said this earlier, and say this again - the igpu inside core i5/i7 is just there for display output. it does not contribute to (cpu vs cpu) performance. that's why i mercifully awarded the fx a discreet gfx, just so it could show it's benches and results. but doing that adversely affected fx's value. simple. trying to change the topic isn't helping your 'cause' at all. :lol:
Except that just about every AM3+ motherboard comes with built in video, even the $45 ones. No need to throw a discrete in just to see benches.
you were comparing cpu performance only, remember? actually a lot of people (if not majority of users) use only igpu, especially in office number crunchers.
Facebook
Twitter
Instagram