Ivybridge should match LLano in graphics

ydnas7

Member
Jun 13, 2010
160
0
0
http://www.xbitlabs.com/news/video/...ics_Performance_than_Core_i_Sandy_Bridge.html

this is comparing a low freq / cut down Sandybridge 6EU with LLano
boost the Intel IGP to 2600k specs and LLano is perhaps 50% faster than SB
but IB is coming 6 months after LLano, it has 20% increase due to process, just add an additional 4 EU (from 12 to 16 - just a wild guess) would make it equivalent to LLano for graphics. Add any more EU and it is beyond LLano.
 

podspi

Golden Member
Jan 11, 2011
1,982
102
106
Actually, from that one benchmark it looks like Llano is closer to 90% faster than HD 3000.

But yes, if Intel wanted to it could double the EU's and be at about LLano's performance level. Or, they could push the clockspeeds up. Or both.

Though we should probably wait for some non-synthetic benchmarks.
 

Idontcare

Elite Member
Oct 10, 1999
21,110
59
91
Yep, and the game of one-upmanship in the on-die GPU can go on and on, AMD could release a Llano SKU with more SP's, Intel can up the EU's, etc.
 

Arkadrel

Diamond Member
Oct 19, 2010
3,681
2
0
How does this:

AMD Expects Fusion "Llano" to Offer Three Times Higher Graphics Performance than Core i "Sandy Bridge".
turn into you makeing a title:

Ivybridge should match LLano in graphics
I dont get it.... There was NOTHING, about Ivybridge in the artical.


Title of thread, is very mis-leading.
And no Ivybridge IGP should not match Llano... it ll be much slower, the end.
 
Last edited:

Abwx

Lifer
Apr 2, 2011
11,543
4,327
136
AMD says three times faster than SB GFX wise...
That makes 200% faster...
IB claimed 20/30% better GFX parfs than SB
seems a little short to even match a 160 SPs
low end Llano..

Or is it some spinning....?...
 

podspi

Golden Member
Jan 11, 2011
1,982
102
106
~ Radeon 5570 is about twice (+100%) as fast as the HD3000 or more (in benchmarks).
To match the Llano, the Ivy bridge would need to have twice as many or more EUs.


I don't know if Intel would do this (they still don't seem to be taking on board graphics as seriously as AMD quite yet) but they definitely COULD do this. HD3000 is only something like ~ 110 million transistors. It wouldn't kill them to double that @ 22nm.
 

Vette73

Lifer
Jul 5, 2000
21,503
8
0
I don't know if Intel would do this (they still don't seem to be taking on board graphics as seriously as AMD quite yet) but they definitely COULD do this. HD3000 is only something like ~ 110 million transistors. It wouldn't kill them to double that @ 22nm.


Yea but only the K chips right now have the 3000, all the other SB have 2000. So very gew, if any, are even using 3000 on the desktop.

The laptop Llano I think will have even more shaders than the desktop, 480 vs 400.
 

Abwx

Lifer
Apr 2, 2011
11,543
4,327
136
Yea but only the K chips right now have the 3000, all the other SB have 2000. So very gew, if any, are even using 3000 on the desktop.

The laptop Llano I think will have even more shaders than the desktop, 480 vs 400.

Looks like 400sp top DT and 320/240 max for laptops..
 

Vette73

Lifer
Jul 5, 2000
21,503
8
0
That s quite a lot....
Laptop graphics trouncing the desktop ones ??..
That s a first...


It still would not touch desktop/sep parts as it still shares bandwidth with the CPU with DDR3.

I am guessing that is the highest laptop part with most in the number range you gave.
 

ydnas7

Member
Jun 13, 2010
160
0
0
I dont get it.... There was NOTHING, about Ivybridge in the artical...
And no Ivybridge IGP should not match Llano... it ll be much slower, the end.

The article was about a neutered SB, but look at a 4 core SB die and it seems obvious that there is suitable space for another 4 eu without changing die size (the 4 eu being left of to maintain schedule/minimise risk). there are also rumors that IB CPU is 20% faster than SB. so although the article comparison was made against a 6 EU 1100mhz part (i5-2300) but as LLano will be introduced about 6months after SB and 6 months before IB, it could very well be competing against a 16EU (12+4) 1600Mhz (1350Mhz * 1.2) IGP in IB.

Off course Intel could surprise us with a 12 EU part or a 24 EU part, but my Wild Ass Guess is that it will be 16 EU, and that it will match LLano

nb
16EU x 1600Mhz is about 4 times more throughput than 6EU x 1100Mhz
 

Edrick

Golden Member
Feb 18, 2010
1,939
230
106
It is getting to the point where Llano and IB graphics will be good enough for anyone who only needs the power of an IGP. These people are generally not gamers or CAD/Video engineers. No matter how good IGPs get, AMD and Nvidia will always have better options available.
 

Arkadrel

Diamond Member
Oct 19, 2010
3,681
2
0
Intel Core i5-2300: P1007
AMD A8-3550 APU: P3335

From the Xbitlabs artical.... Im assumeing this is the same TPD and Pricerange, so thats why their compaired to one another.

The Llano comes out scoreing 330%+ more than the i5-2300, in 3D mark Vantage.

That is what the artical is about, that said, if intel wanted to, Im sure they could make a Ivy Bridge in the same TPD/Price range, that gave sameish IGP performance.

It is getting to the point where Llano and IB graphics will be good enough for anyone who only needs the power of an IGP. These people are generally not gamers or CAD/Video engineers. No matter how good IGPs get, AMD and Nvidia will always have better options available.

IGP wont stop growing with APUs of the future,.. mainly because of GPGPU computeing (theres no loss in continued GPU growth). That said Im sure there will always be better "pure" GPU products avalible from Nvidia and AMD.
 
Last edited:

Vette73

Lifer
Jul 5, 2000
21,503
8
0
I 'heard' they were shipping to OEMs. Are they available in the market yet?


Just to OEMs as far as I know.

AMD wants OEMs to get them and have systems fully running and ready to go in mass before the back to school period when sales jump.
 

Tuna-Fish

Golden Member
Mar 4, 2011
1,475
1,978
136
Add any more EU and it is beyond LLano.

Yep, and the game of one-upmanship in the on-die GPU can go on and on, AMD could release a Llano SKU with more SP's, Intel can up the EU's, etc.

No. Looking at the specs, Llano will be very heavily memory-limited. It will be simply impossible to improve the graphics beyond Llano by just adding execution units -- you will either need more memory channels (unlikely for low-end parts), or some sort of local framebuffer.
 

Riek

Senior member
Dec 16, 2008
409
14
76
The article was about a neutered SB, but look at a 4 core SB die and it seems obvious that there is suitable space for another 4 eu without changing die size (the 4 eu being left of to maintain schedule/minimise risk). there are also rumors that IB CPU is 20% faster than SB. so although the article comparison was made against a 6 EU 1100mhz part (i5-2300) but as LLano will be introduced about 6months after SB and 6 months before IB, it could very well be competing against a 16EU (12+4) 1600Mhz (1350Mhz * 1.2) IGP in IB.

Off course Intel could surprise us with a 12 EU part or a 24 EU part, but my Wild Ass Guess is that it will be 16 EU, and that it will match LLano

nb
16EU x 1600Mhz is about 4 times more throughput than 6EU x 1100Mhz

considering the 12EU with a higher frequency is not at all doubling the performance of the 6EU... and rumours state 30% improvement with IB it won't get clsoe to the supposably scores of llano.
 

Idontcare

Elite Member
Oct 10, 1999
21,110
59
91
No. Looking at the specs, Llano will be very heavily memory-limited. It will be simply impossible to improve the graphics beyond Llano by just adding execution units -- you will either need more memory channels (unlikely for low-end parts), or some sort of local framebuffer.

This is SWAG (stuff we all get), right?

If I had any idea I needed to include a bevy of obvious stuff that needs to be incorporated to go along with an increase in SP's and EU's (higher bandwidth DDR, more local cache, yaddi yadda) then I would have definitely increased the word-count on my posts.

If Llano is already "very heavily memory-limited" then I would question why they pursued increasing the SP's to the point they did on an intentionally lower-cost product.

"No" improvement, your words not mine, beyond the existing SP count would imply they fully saturated the diminishing returns curve...for a lower-cost product surely they could cut the SP's by a healthy 25% or more, have a product that costs all the less, and not lose but a few percentage points of performance (if even that much, diminishing return curves have pretty long tails, and you claim they are all the way out at the end of it already).
 

Arkadrel

Diamond Member
Oct 19, 2010
3,681
2
0
eDram ^-^

Xbox360 has like 10mb of it? thats all the memory bandwidth it needs.

I dont think memory bandwidth is a issue, technically it can be worked around in many ways (in future APUs). Heat and Power... are probably "more" of a issue, on the scale of what is viable for APUs.

Big CPUs already reach 200watts use... and need a decent cooler to keep temps down.
Throw in a high performance GPU... and yeah you see where this is going.
Heat will be a big issue with these things in the future.


Xbox360:

The 10MB of EDRAM is actually on a separate die, at least initially. As future process technologies become available, it is possible that it could be on the same piece of silicon as the GPU. Still, the EDRAM resides on the same package,and has a wide bus running at 2GHz to deliver 256GB/sec of bandwidth. That's a true 256GB/sec, not one of those fuzzy counting methods where the 256GB is "effective" bandwidth that accounts for all kinds of compression.

10mb eDram on chip, giveing 256 GB/s memory bandwidth for the GPU (on the Xbox360).


AMD gets a little help from IBM, puts 6mb or so eDram on chip, with a wide bus running at 2ghz or so.... no more memory bandwidth issues.
 
Last edited:
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |