when you go from one ISA to another you need to recompile, you might need to do work to make it recompile to another ISA but it still is a recompile. On the intel helped apple move i can't find anything in search of this forum or on the inet.
you should become a comedian, i will let other people make up there own minds but to me all you have done is wildly made accusations, been completely dismissive without being able to logically say why, never actual address any counter points to your wild rants.
Given that the 18watt apu can match a mobile SB in GPU performance what do you think a 60watt APU is gonna do, then your dismissive when it does.
basically i know im being trolled.........yay :thumbsup:
Really what game was that? I bet intel driver team was all over that game to get it running descent on its IGP . So AMD could do a comparsion with it . Actually I am surprized it even ran on HD graphics its such a popular game.
. . ..
Bring me back to my previous point. Intel's drivers suck just as bad as their IGP's. That is another reason why AMD could have an advantage with Llano.
Damn son, my eyes are bleeding from all the grammatical, punctual and logical gaps you're puking up on this thread!
I'm not familiar with CPUs and their performance, but even so I can tell AMD has a good thing going - and there's no hints of rigging in the video!
Now I'm going to read something that actually has some semblance of punctuation and spelling. Gah.
More importantly, was it having fun consistently pausing for a second or more at a time like in the demonstration? There's no question that Sandybridge is slower, but the stuttering in that video was very... odd and uncharacteristic of simple low frame rate.
Sadly, having a P67 based board means that I can't play with it myself =(
Given that the 18watt apu can match a mobile SB in GPU performance what do you think a 60watt APU is gonna do, then your dismissive when it does.
yes your correct, i was getting annandale GPU mixed up with HD3000, that saidI just had a lok at ATs mobil tables and the 2820QM is more than 100% faster than e 350
Now your being reasonable . good . Look you just said what I been saying . You said thisyes your correct, i was getting annandale GPU mixed up with HD3000, that said
http://www.anandtech.com/show/4134/the-brazos-review-amds-e350-supplants-ion-for-miniitx/5
vs
http://www.anandtech.com/show/4083/...core-i7-2600k-i5-2500k-core-i3-2100-tested/11
isn't very flatering for HD3000. E-350's GPU is running at 500MHZ and its an 80 shader/8mtu/4rop part. you think HD3000 is gonna keep up with Llano? which is going to be something like 480:24:8 and likely around the 700mhz mark, have well over twice the memory bandwidth of 6310 as well (single channel 1333 vs dual channel 1866)
edit: alsoif you look at the 5570 performace between the two reviews you can see that bobcat is also a limiting factor, if the 6310 was on a quad core it would be getting higher frames as well ( how much is a complete unknown)
To Nemesis: Now you are just pushing it. Can't you post once without doing that?
Yes it did. It's improving quickly every generation, but Intel still needs closer relationship with the developers. I also ran it to that same point with default settings(3.4GHz CPU with Turbo Mode, and 1350MHz Turbo GPU), and I got 56-57, which is basically no different. If something hard bottlenecks the graphics, what happens is you get no scaling, and I believe that could be the lack of developer work.
Now your being reasonable . good . Look you just said what I been saying . You said this
isn't very flatering for HD3000. E-350's GPU is running at 500MHZ and its an 80 shader/8mtu/4rop part.
Intels Igp is 12 shaders Hd 3000 you said bobcat was a limiting factor . Thats the point AMD said SB was running at 2 ghz. Now look again at the mobil results on zacatas and the intel mobil 2820 and note power usage. SB is dam close to zacata in power usage. Thats what I was getting at . Whats known already in real reviews does't line up with what this video is saying at all.
Look be smart here If amd makes llano that good it cuts off its own arm . good enough for all most all people other than a small percentage less than 1% will kill highend discrete as goodenough becomes great when its free.
at low power draw PSU's are less efficent unless designed for low power draw. also note how E-350 beats atom in power across all tests.don’t have any pico PSUs or anything super efficient readily available so don’t expect any of the numbers to be particularly impressive but what they are is comparable to one another.
Yes it did. It's improving quickly every generation, but Intel still needs closer relationship with the developers. I also ran it to that same point with default settings(3.4GHz CPU with Turbo Mode, and 1350MHz Turbo GPU), and I got 56-57, which is basically no different. If something hard bottlenecks the graphics, what happens is you get no scaling, and I believe that could be the lack of developer work.
sigh, first off i cant actually understand what you are saying.
your attempt to some how link TDP makes no sense, the Q2820 is shown constantly to exceed its TDP of 45watts in the AMD demo and Llano is generally 5-10 watts below while providing much better graphic performace.
also shader count outside of comparable architexture is useless, i could also call the E-350 6310 part a 16 shader part. trying to make it seem like intel is doing so much with so much less isn't accurate.
SB is no where near zactate power usage, if your looking at the anand E-350 review note this part
at low power draw PSU's are less efficent unless designed for low power draw. also note how E-350 beats atom in power across all tests.
But look at the compare real world AT did with the 2820 Vs the e 350 . Power usage included. the 2820 is very close to the e 350 . It right there in Ats reviews on mobiles, Its very very close . Use ats tables its good info . So now its the PSU that caused all tis . doesn't all need PSU. The only place were there was a big differance was idle time . Buy the way I was unaware that mobils had PSU. I thought it was batteries only . The battery in the e 350 is much much smaller thats a fact.
The e 350 isn't even in the ballgame if tablets are the big deal this year . Zacata at 8 watts isn't going into a tablet that will be meaningfull . Oaktrails is up against NV and Arm here and imagination tech . Oaktrail at 3 watts is still a little power hungry. Until intel gets atom to 32nm rather than the present 45nm its a tuff road for intel . But the very lowend notebooks for zacata means little to intel . llano selling in a notebook if its IGP is all that if sold at the 400 500 dollar range would be stupid of AMD . They need to market to gamers with this platform . and the tablets will cut deep into the zacata market. Like I said if AMD llano is that good on graphics AMD needs to price it accordingly or lose out on margines
Yes. They are doing better lately, too. But they love doing things in a way that serves their design and manufacturing needs more than serving their users. In the graphics area, they should work on making them more compatible--there should be code to make popular games perform well, but any of them should work. Also, more work on making the drivers perform to meet deadlines, rather than just get some throughput, so that when they aren't quite capable of the workload, they gracefully slow down, instead of rush and stutter.Doyou really think intel needs to pay attention to developers.
AMD has been talking it up for longer than Intel has. Intel has the R&D resources to use to make it happen quicker, but AMD is far from looking at it in hindsight.With the advent of soc don't you think game developers should work more with the market leader . Its clear in 4 years God willing that Soc will be the final solution. Even NV sees this . well ahead of AMds hindsight.
Er, what? The Xbox360 was never to be DX10-capable, AFAIK. Just like the original Xbox, it was meant to be an in-between, slightly different from any PC GPU feature set.Had a certain group of people not put it all over the net about what was going on between MS and ATI on the360 MS would have changed the orginal DX10 spec . Not a chance that would have happened.
LOL. Intel's own x86 CPUs were beating the crap out of Itanium, at 1/10th the cost per machine, except in a few cherry-picked scenarios that almost no one cares about (sorry to those of who you used them well ). Intel had experience with making CPUs that could show x86 a thing or two, as well, so it's not even that x86 really has any magic to it (i960, anybody?). The Itanium was never going to replace IA32, and should have been left as a research experiment. It was not some Microsoft and AMD collusion that killed wide adoption of IA64 CPUs. It was Intel's IA64 products performing poorly, being too hot, being too late, and then being too expensive, all for a little hardware RAS. Much like Netburst, it was Intel's hubris that was the problem, thinking they could turn an ideal into a reality. The market was begging for someone like AMD to come out with something they actually wanted to buy, and AMD managed to do it.But ATI and MS conspired just like AMD and MS conspired on 64 bit x86. So many here blame intel for X86 being around still. That was AMds doings. Intel was trying to leave the market with itanic but got hammered.
your making no sense anywhere in this post ( thats normal)
are you comparing zactate or llano to the 2820, one is 40nm bulk the other is 32 nm SOI HKMG.
second there are ITX/min ATX e-350's anands review is using one of these, and as anand said himself he did not use a great low power power supply at that.
even with the power supply in mind the E-350 is still 3.5-6 times lower idle then a 2600k and 4 times underload according to http://www.anandtech.com/bench/CPU/52
the 2820 isn't in that list.
and i cant find any 2820 laptops to compare in http://www.anandtech.com/bench/Product/335?vs=332
simply fact is Llano will have 4-6 times the GPU resources a high clock and more then 2 times the bandwidth of a 6310. given that the 5570 wipes the floor with SB HD3000 graphics and llano will have comparable resources but less bandwidth ( but the advantage of much more direct CPU access) i really dont quite understand what your actual point is.
Really what game was that? I bet intel driver team was all over that game to get it running descent on its IGP . So AMD could do a comparsion with it . Actually I am surprized it even ran on HD graphics its such a popular game.
Yes. They are doing better lately, too. But they love doing things in a way that serves their design and manufacturing needs more than serving their users. In the graphics area, they should work on making them more compatible--there should be code to make popular games perform well, but any of them should work. Also, more work on making the drivers perform to meet deadlines, rather than just get some throughput, so that when they aren't quite capable of the workload, they gracefully slow down, instead of rush and stutter.
AMD has been talking it up for longer than Intel has. Intel has the R&D resources to use to make it happen quicker, but AMD is far from looking at it in hindsight.
Er, what? The Xbox360 was never to be DX10-capable, AFAIK. Just like the original Xbox, it was meant to be an in-between, slightly different from any PC GPU feature set.
LOL. Intel's own x86 CPUs were beating the crap out of Itanium, at 1/10th the cost per machine, except in a few cherry-picked scenarios that almost no one cares about (sorry to those of who you used them well ). Intel had experience with making CPUs that could show x86 a thing or two, as well, so it's not even that x86 really has any magic to it (i960, anybody?). The Itanium was never going to replace IA32, and should have been left as a research experiment. It was not some Microsoft and AMD collusion that killed wide adoption of IA64 CPUs. It was Intel's IA64 products performing poorly, being too hot, being too late, and then being too expensive, all for a little hardware RAS. Much like Netburst, it was Intel's hubris that was the problem, thinking they could turn an ideal into a reality. The market was begging for someone like AMD to come out with something they actually wanted to buy, and AMD managed to do it.
This is a total non-sensical argument compared to the previous posts...
- You directly said SB should be compared with Zacate
- I made the post this quote is responding to, saying they shouldn't be compared because they won't compete at the same price point
- You make this post rambling on about tablets? 32nm and 45nm? What is that garbage?
What you wrote here is totally out of left field. It doesn't even make any sense in the context of your own previous statements.
The fact that you would use non-sequitors suggests you are in fact just trolling here. You're obviously capable of thinking rationally, why are you purposefully crapping all over the Llano and Zacate threads? More importantly, why do the mods allow this garbage? This guy has been derailing these threads for months. Soon I'll stop coming to this forum like I've already stopped going to the video forum.