Prelude to a Review-
The AMD 780G chipset got us excited about integrated graphics platforms again after its release last March. You can imagine our surprise when AMD contacted us in April asking what we would like to see in the next IG chipset scheduled for release this year. Of course, we obliged AMD with our wish list that included everything from 8-channel LPCM audio over HDMI to HD 3650 or higher-level performance.
We also requested a new Southbridge with improved RAID performance along with RAID 5 capability. More importantly, we wanted a chipset that could run true CrossFire and bridge the gap between the budget IGP and enthusiast level markets. In other words, we wanted a chipset that could serve the multimedia and small form factor audience in a uATX form factor or provide top-flight performance and features for the enthusiast in an ATX form factor. You know, something like the NVIDIA 750a SLI product or Intel’s P45 only with an IG unit.
AMD listened intently and replied they had something that might just fit our requirements. We were even more surprised to learn that it was arriving in late June under the 790GX moniker. Yes, we had to wait until early August but estimated release schedules in this industry have a tendency to be overly optimistic. For those diehard AMD fans, the delay in the release of the 790GX has been frustrating. Mainly due to the fact that rumors swirling around the internet about the performance and capabilities of the 790GX have been a bit more optimistic than the release schedule.
Unfortunately, speaking of release schedules, we think later August would have been a better target after spending the last week testing our 790GX products. In fact, we ran across so many problems that our article today is a preview of the chipset capabilities. We will follow-up quickly (Editor- no more food or Guitar Hero until this is finished) with a full review of products from Gigabyte, ASUS, Biostar, and Foxconn.
The majority of our problems center on BIOS tuning and driver related maladies. After speaking extensively with the motherboard suppliers, we are certain the BIOS releases that arrived late last night or those coming today will address problems ranging from NB multipliers/HT Ref Clock change requests not accepted via BIOS or AOD to 8GB compatibility issues along with other minor performance hindrances like memory SPD settings not being read correctly when overclocking. PCI peripheral support with a couple of network and audio cards is also giving us trouble. Of course, BIOS tuning can take you only so far and the requirement for solid drivers is necessary.
The 8.521.1 driver set, aka Catalyst 8.8 beta, has significant performance optimizations for the 790GX plus full support for the new C1E power savings mode, PowerPlay, and deep sleep instructions for the SidePort memory, umm Performance cache. As is the case with beta drivers there are liable to be various features that might not work correctly. One important feature that failed to work properly for us was CrossFire operation with our HD 4850 or HD 4870 cards.
Other problems ranged from proper C1E implementations and S1/S3 resume issues to HDMI repeater/screen resolution setups with commercial BD playback software. AMD informed us late today that we should roll back to the 8.7 drivers for testing all items but C1E. Of course, this meant graphics, power management, and performance testing on our test platforms just got tossed out the window. It also meant a reduction in IG performance around 3%~5% and some quirky results with C1E and Cool-n-Quiet enabled.
On a side note, we still do not have the latest version of AOD working correctly with any of our 790GX and 9950BE combinations after a stellar appearance on the 790FX board we utilized in our SB750 preview. Actually, these problems are typical during the launch of a product. It just seemed that in our case the perfect storm brewed as it was nearly impossible to close out each benchmark session without running into a problem. We sailed through discreet graphic card testing with the beta drivers but were stymied with the inability to run CrossFire although Hybrid CrossFire worked fine.
Our power draw tests revealed three different sets of numbers, not an explainable difference due to a board’s components, but a 30W difference at idle with the same components and BIOS settings. RAID 5 testing resulted in several different sets of IOMeter results between the boards that we are still investigating. Problems even carried over to HDMI output through our receivers although it appears rolling back to the 8.7 drivers today cured those issues.
In our estimation, the BIOS and drivers needed some additional brewing time before the product release. While it may seem we are picking on AMD, this occurs with NVIDIA and Intel also. In fact, we could devote an entire page to our early experiences with G45. However, all this said, we did find the motherboards to be extremely stable in the normal course of testing with major applications that typical users will utilize. In addition, performance from the integrated graphics unit is simply superb considering AMD’s competition. We did not discover any show stopping problems that would prevent us from purchasing the product at this time. Just beware that a BIOS spin and updated driver release will be required to get the most out of the board’s additional features.
So let’s take a look at the chipset specifications of the 790GX chipset.
Facebook
Twitter
RSS
39 Comments
View All Comments
mpjesse - Friday, August 22, 2008 - link
Did the writer get sick? Did he DIE? 2+ weeks to benchmark an integrated chipset? Practically the entire galaxy has already reviewed this chipset. I'm starting to get tired of both the physical speed (or lack thereof) of this website and the quickness (again, lack thereof) in which crap is published.-Fed Up
bravomail - Wednesday, August 20, 2008 - link
Here is the article with the pictures (in russian unfortunately)http://www.riddik.net/publ/1-1-1-25">http://www.riddik.net/publ/1-1-1-25
The guy ripped apart AMD BE CPU only to find out some bubbled thermopaste between chip and attached lid.
Use Google translate to read this story.
computerfarmer - Tuesday, August 19, 2008 - link
It is now the 19th of August, perhaps the review is coming soon?Beta BIOS was on the 13th of August.
Waiting
Waiting
Waiting...................
OCedHrt - Thursday, August 14, 2008 - link
With all this advancement in IGP, why does Hybrid Crossfire only work with low end cards? I would love to be able to use it with a 4850 or 4870 where the IGP switches completely over to the discrete as needed.MikeODanyurs - Sunday, August 17, 2008 - link
The new DFI 790GX card states it has Hybrid CrossFire that will work with HD 3850 and I believe will even work with the IGP with 2 cards.someguy11 - Wednesday, August 13, 2008 - link
"unless AMD can implement something akin to HybridPower from NVIDIA, which allows the discrete card to power down and switch to the IG unit at idle for less demanding tasks like Office Applications or Bejeweled. Otherwise, the IG unit and all of its potential benefits are wasted with a discrete card setup"Does anyone know if the implementation of something like HybridPower from AMD on the current day 790GX boards is possible?
In other words, if I buy a 790GX will a power saving feature where the discrete card can be powered down be simply a BIOS flash or will new boards have to be made (assuming AMD develops something along this route)?
I ask b/c this "power down" feature really interests me and if this can be implemented via a BIOS upgrade, then I am more apt to get a 790GX today rather than a 790FX board who knows when. I also like the idea of having a board with onboard IG so you can play the graphics card price wars when you want to.
Thanks for the help!
ZootyGray - Tuesday, August 12, 2008 - link
There are lots of unbiased websites offering useful reviews. I am sick of waiting for your uncompleted works and biased results.Your review of 4870x2 is the end of the line - that is the worst trash I have seen.
Why would anyone want to wait for you to trash more AMD hardware.
Save your energy for yourself. I do not need your self-importance.
Maybe when you can followup on last May's 780G review, as promised, I might be interested - until then - I apologize for thinking you were some kinda good review place. Yer out. Bias is not quality. It's abuse. Not your victim anymore.
computerfarmer - Saturday, August 9, 2008 - link
On page 2 it is noted as saying the new 790GX graphic is set(default) at 700mhz compared to the 780G at 500mhz. The manual for the Gigabyte GA-MA790GP-DS4H (rev. 1.0) page 42 has the default set at 650mhz. This leads me to believe that side by site tests from different manufacturers should show differences based on default settings. Also SidePort memory ratings need some attention. If SidePort is DDR3 at 1333mhz and system memory is at 800/1066mhz then how do they function together at different speeds? Or is the SidePort memory speed based on system memory up to 1333mhz?Thank you Anandtech for such an informative article.
maree - Friday, August 8, 2008 - link
Quoting from the article"For the multimedia user, ... The SB750 does offer ACC and along with it the opportunity to run lower voltages ..."
Does it mean motherboards running on this chipset can take a phenom 9550/9850BE an turn off 2 cores then expect the power performance of amd 4850e?
ZootyGray - Thursday, August 7, 2008 - link
I really don't want to go dig up exact quotes from previous reviews."The Three Amigos" review revealed "pop goes the mosfet" issues with products produced by various mobo manufacturers. I really liked that review - BUT - a followup was indicated as coming - and it never appeared.
This review ends in a similar manner.
And the Foxconn review seemed to really sidetrack and resulted in 3 articles; and for my little brain, I found it difficult to follow the coherence of the whole thing.
Now we have a whole new chipset and a bunch of mobos you say you are benching soon. Ok, so that makes sense - assuming this will actually happen soon. No problem there.
BUT - there's this really interesting comparison to 780G which you are presenting. I wonder what happened to the mosfet issue that you so beautifully revealed. I wonder - Is it in play here as well? I DOUBT that! This is a performance board - right?
BUT - are you trying to lead some people to buy the original 780G boards regardless of resolution (if any) of the "pop goes the mosfet" issues. And asus has produced new mobos that clain 125watt handling power - ie no "pop"???
I think all this uncertainty might be dangerous for some people with great expectations.
I think some unfinished business should be clarified.
I think some comment on 'mosfet' should be included in these upcoming benchies.
I think this might be misleading a lot people - and your unfinished work is a little underhanded slight on AMD products. I REALLY HOPE you clear this mess up; since it was your baby to start with - and that was good. And that caused me to respect Anandtech.
Please don't leave me just hanging on and waiting - I doubt I am the only one. I would prefer completion rather than assuming this is another antiAMD site, and have to go elsewhere. It's your credibility, for me, at least, at this point.
Golf taught me that follow through is a big part of the golf swing. I know you are busy. Some loose ends can bite you. How close IS this to the 780G boards anyway? Has the "pop" been fixed?
I hear Vanilla Fudge "Keep Me Hanging On" playing in the background - wow, it has been a while since I heard that.
Thank you.