• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

AMD Carrizo Pre-release thread

M

monstercameron

Diamond Member
OEFXfBC.jpg

source: http://www.chw.net/2014/10/primeros-benchmarks-de-los-futuros-soc-amd-a-8000-series-carrizo-l/

Not much info yet but so far it seems as if they are sticking to the current configuration, 2 modules and 8 CUs.
 
Last edited:
Which Intel CPU is this Carrizo positioned against? Core i3 Haswell? What is the TDP and why is it clocked at only 2.6 GHz? Will there be notebook variants of Carrizo?
 
meloz said:
Which Intel CPU is this Carrizo positioned against? Core i3 Haswell? What is the TDP and why is it clocked at only 2.6 GHz? Will there be notebook variants of Carrizo?
Click to expand...

Given that this is an ES, clock speeds are probably not final. Same deal as with the 2.3GHz Skylake ES there have been screenshots of.

Kind of curious how this will do- smaller L2 should have brought the CPU cache latency down to something a little less horrific, and the improved compression technology we saw in Tonga should be a massive help in the bandwidth constrained GPU. If they get the price right, it could be a decent choice for low end gaming rigs/laptops.

Of course if they price it like Kaveri, it's probably dead on arrival.
 
meloz said:
Which Intel CPU is this Carrizo positioned against? Core i3 Haswell? What is the TDP and why is it clocked at only 2.6 GHz? Will there be notebook variants of Carrizo?
Click to expand...

good questions. This is an engineering sample which tend to be clocked lower. It could also be the that these results are for carrizo-l the mobile variant.
 
meloz said:
Which Intel CPU is this Carrizo positioned against? Core i3 Haswell? What is the TDP and why is it clocked at only 2.6 GHz? Will there be notebook variants of Carrizo?
Click to expand...
It's an engineering sample, which may relate to the clockspeed. Or it could be TDP related. Carrizo may be notebook-only.


edit: hotel internet seems to have gotten me third place...
 
Last edited:
The performance is lower than the A10-4600M.

The TDP is 15 watts for AMD Eng Sample: 2M1801C1Y4381_26/18/08/04_9874

100x26 Boost
100x18 Base
100x08 Idle
100x04 GPU Base
PCI_ID Device: 9874

The GPU benchmark says the nominal is 626MHz. This is 60 less MHz than the 686 MHz in the iGPU of FX-7600P.
 
Last edited:
Looks like they are releasing it first for mobile?? That seems the way to go. An APU has much more appeal to me in a notebook than a desktop, but Kaveri came out first for desktop and never had much availability in notebooks. Lets see if they get it out on time and get some design wins for attractive products.
 
Not sure if this is true. I just did a search via google.
http://hardware.forumsee.com/a/m/s/...-christmas-full-carrizo-for-the-new-year.html

Kaveri, Beema and Mullins are on their way out to be replaced by the Excavator based Carrizo family towards the end of the year. We can hope they will appear in products in time for Christmas as the low power Carrizo-L, rumoured to be around 12-35W TDP, will arrive. In the new year the more powerful Carrizo, speculated at 45-65W TDP, will be available. It is unclear how long the delay will be between availability to system builders and the products appearing on the market. The chips will support DDR3, contain a GPU based on GCN 3.0 and stacked on-package memory which will be accessible by Through Silicon Via to act as a sort of L3 cache for HSA applications. DigiTimes also mentions it will run Win8 and Win10 as well as SLED.

AMD's mobile APU update, Carrizo-L for Christmas, full Carrizo for the new year
 
Huh. If the top-end Carrizo in March with be a 65W part, will it be able to outperform Kaveri at all? Increased density doesn't say much in favor of higher clockspeeds.

Also, where is the rumored GF28A?
 
DrMrLordX said:
Huh. If the top-end Carrizo in March with be a 65W part, will it be able to outperform Kaveri at all?
Click to expand...

Yes because the 95W Kaveris are actualy 67W TDP, this is the reason there s not much difference with the 65W parts.

About this i did find it funny that the first reflex of some people was to assume that the 65W parts were of a higher TDP without even thinking that it could be the higher power part that had its official TDP greatly exagerated.
 
Last edited:
I guess it also depends on whether Carrizo will be 20 or 28 nm? I've heard both. If the former, then 65 W TDP could give more headroom compared to 65 W TDP for 28 nm on Kaveri.
 
Excavator in 2011-2012 @ Sunnyvale teams put it on 20-nm LPM.
Excavator in 2012-2013 @ Boston teams put it on 28-nm SLP. (LP node shared with Samsung; SLP = LPP or ET-SOI = FD-SOI)((It is required to be shared with Samsung for AMD to use it))

~2012 -> Steamroller and Excavator was moved from Sunnyvale teams to Boston teams. So, Sunnyvale could design from scratch a new high performance x86 core. Like, they did in 2005/2006 to 2010 called Bulldozer.

Steamroller was unfixable as it was largely complete when Boston got it. While, Excavator is a complete mystery. As it was at an incomplete state on 20-nm LPM.

The majority of the Boston team are part of the FD-SOI community as well.
 
Last edited:
Abwx said:
Yes because the 95W Kaveris are actualy 67W TDP, this is the reason there s not much difference with the 65W parts.

About this i did find it funny that the first reflex of some people was to assume that the 65W parts were of a higher TDP without even thinking that it could be the higher power part that had its official TDP greatly exagerated.
Click to expand...

Who's to say that they aren't exaggerating the TDP of the top-end Carrizo CPU as well? I guess more will be revealed closer to launch, but for now, it seems kind of weird.
 
Carrizo will not benefit from a node shrink, i guess that IPC will somewhat increase by a still unknown quantity while there can be some gatings and cache managements that should reduce the power usage.

On the IPC front they will likely gain what they project with Excavator plus a bonus that should had been available with Kaveri but was left untapped, i mean the latency wich increased notably and wich deprived Kaveri of as much as 15-20% perfs in some softs like 7zip, winrar and also in latency sensitive games.
 
Abwx said:
Yes because the 95W Kaveris are actualy 67W TDP, this is the reason there s not much difference with the 65W parts.

About this i did find it funny that the first reflex of some people was to assume that the 65W parts were of a higher TDP without even thinking that it could be the higher power part that had its official TDP greatly exagerated.
Click to expand...

Kaveri uses much less power than Trinity/Richland. However, it does appear to need more than 67W to keep full turbo. Carrizo should easily be able to keep pace with a similar clockspeed and lower tdp.

However, Kaveri still does use more power than eqivalently rated intel CPUs. Intel is generally even farther away from tdp (except on mobile where intel pushes the tdp envelope to the max).
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top