Trinity vs Ivy Bridge

[jimbo75]

Well that was just the 1.7 GHz chip and there will be a 2GHz one so it will rise by a little more. I think what is going on is intel has benched IVB vs older chips in order to get the 60% figure that was talked about. It'll be closer to 50% best case, and generally 30%-40% faster in my opinion.

Even if this 17W Ivy Bridge hits 13 fps, Trinity @17W will be a good 50% faster at ~20 fps. Again I believe this is also as good as it will get in a comparison and Trinity will be further ahead in actual gaming.

 

[Paran]

I meant GPU clocks. And again, OpenGL benchmarks could differ to d3d Benchmarks. Intel is weak in OpenGL. AMD supports OpenGL 4.2 whereas Intel just 3.1.

 

[Deleted member 13524]

Well that was just the 1.7 GHz chip and there will be a 2GHz one so it will rise by a little more. I think what is going on is intel has benched IVB vs older chips in order to get the 60% figure that was talked about. It'll be closer to 50% best case, and generally 30%-40% faster in my opinion.

Even if this 17W Ivy Bridge hits 13 fps, Trinity @17W will be a good 50% faster at ~20 fps. Again I believe this is also as good as it will get in a comparison and Trinity will be further ahead in actual gaming.

Not to mention the fact that the top-performer 17W Trinity will probably cost like 1/3rd of the top-performer 18W Ivy Bridge.

 

[Paran]

17W Ivy Bridge.

 

[CarstenS]

Intel actually promises an almost 3x increase for "Vantage Performance" performance compared to a somehow strange Ci7 2600k with HD2000 graphics - at least for desktops:
http://www.xbitlabs.com/news/cpu/di...y_Bridge_Performance_Numbers_to_Partners.html

TBH, I don't know how much the clock targets for IVB-graphics differ from desktop to mobile to ULV, but this might give a notion for the gains we can expect from an architectural overhaul.

 

[Paran]

TBH, I don't know how much the clock targets for IVB-graphics differ from desktop to mobile to ULV, but this might give a notion for the gains we can expect from an architectural overhaul.

Up to 1300 Mhz for mobile Quadcore, 1150 Mhz for ULV mobile.

http://chinese.vr-zone.com/5796/intel-ivybridge-mobile-12022011/

 

[Deleted member 13524]

http://vr-zone.com/articles/amd-adds-a-third-foundry-for-its-fusion-apus-hello-ibm/14759.html

It seems Trinity will be made in both GF and IBM East Fishkill.

I wonder if there'll be any substantial heat/power performance difference between chips made in different factories.

 

[DarthShader]

Wait, what is that claim based on, what is the source? That single slide pictured??

 

[AlphaWolf]

Wait, what is that claim based on, what is the source? That single slide pictured??

No, the source is Rory Read (CEO of AMD).

 

[I.S.T.]

http://vr-zone.com/articles/amd-adds-a-third-foundry-for-its-fusion-apus-hello-ibm/14759.html

It seems Trinity will be made in both GF and IBM East Fishkill.

I wonder if there'll be any substantial heat/power performance difference between chips made in different factories.

Isn't IBM's process not that different from GF's?

 

[entity279]

Actually, last year IBM, GF & Samsung officialised an alliance which boasted near-zero effort to transition a design from one foundry to another.


LE: Hardware.fr guesses the same thing: http://www.hardware.fr/news/12126/ibm-amd.html

 

[Deleted member 13524]

IIRC, back in the Athlon XP/64 days there were sometimes large differences in overclockability between CPUs from different fabs, even if they had the same name.

 

[mboeller]

From the 3DCenter.de Forum:

http://wcc.on24.com/event/40/32/51/rt/1/documents/player_docanchr_1/part4.pdf

=> page 14 is rather interesting

it seems that the 17W Trinity will only have one module, otherwise the rather pathetic productivity-performance of the 17W Trinity APU would be a disaster.

=> Therefore only the 25W Trinity should have 4 cores.

=> it seems AMD used a 2-core Llano A4 with 35W for the perf./w comparison and not a 4-core A8.

 

[jimbo75]

From the 3DCenter.de Forum:

http://wcc.on24.com/event/40/32/51/rt/1/documents/player_docanchr_1/part4.pdf

=> page 14 is rather interesting

it seems that the 17W Trinity will only have one module, otherwise the rather pathetic productivity-performance of the 17W Trinity APU would be a disaster.

=> Therefore only the 25W Trinity should have 4 cores.

=> it seems AMD used a 2-core Llano A4 with 35W for the perf./w comparison and not a 4-core A8.

http://hothardware.com/Reviews/AMD-Fusion-A83500M-ASeries-Llano-APU-Review/?page=5

Having thought about it some more you may well be right. I don't see how a quad can score 3500 in this while having almost double perf/watt.

The plot thickens though - what's going on here?

That's overall score, however it's still pretty bizarre. Based on that it could be a relatively fast dual core or relatively slow quad and score about the same.

Note also there are a lot of disk related benchmarks in the productivity score which might help explain why Brazos isn't so far behind.

 

[Deleted member 13524]

From the 3DCenter.de Forum:

http://wcc.on24.com/event/40/32/51/rt/1/documents/player_docanchr_1/part4.pdf

=> page 14 is rather interesting

it seems that the 17W Trinity will only have one module, otherwise the rather pathetic productivity-performance of the 17W Trinity APU would be a disaster.

=> Therefore only the 25W Trinity should have 4 cores.

=> it seems AMD used a 2-core Llano A4 with 35W for the perf./w comparison and not a 4-core A8.

And you assumed all that from..?
Slide 14 is measuring what results, exactly? You're assuming it's PCMark Vantage?

And even if that's PCMarg Vantage:
The 17W Trinity is probably clocked @ ~1.2GHz. Why wouldn't it be a 2-module/4-core chip, given it has ~26% less "productivity score" as an A8-3500M 4-core Llano @ 1.5GHz (which turboes up to 2.4GHz)?

Seems more like just another confirmation that it's a 2-module, if you look at the numbers.


But the GPU seems to be seriously cut-down, though

 

[Deleted member 13524]

It seems the 25W Trinity is a "monster" in GPU performance, though.

 

[Alexko]

And it's got to be cheaper than an ivory bridge.

 

[Paran]

It seems the 25W Trinity is a "monster" in GPU performance, though.

Fast enough for Ivy Bridge do you think?

 

[Deleted member 13524]

Fast enough for Ivy Bridge do you think?

www.pcstats.com/articleview.cfm?articleid=2601&page=17

With a score of 3600 in Vantage, I believe the 25W Trinity will be probably faster than any Ivy Bridge iteration, mobile or desktop.

 

[Paran]

www.pcstats.com/articleview.cfm?articleid=2601&page=17

With a score of 3600 in Vantage, I believe the 25W Trinity will be probably faster than any Ivy Bridge iteration, mobile or desktop.

3770 Slide: http://www.xbitlabs.com/news/cpu/di...y_Bridge_Performance_Numbers_to_Partners.html

No exact numbers though.