Intel Core 2 Quad Q9550S: A New 65W Quad-Core
by Anand Lal Shimpi on January 27, 2009 8:00 PM EST- Posted in
- CPUs
x264 HD Video Encoding Performance
Graysky's x264 HD test uses the publicly available x264 codec (open source alternative to H.264) to encode a 4Mbps 720p MPEG-2 source. The focus here is on quality rather than speed, thus the benchmark uses a 2-pass encode and reports the average frame rate in each pass.
I measured power and performance in the second pass of the benchmark since that’s where the more CPU intensive work gets done.
First, we look at performance:
The Q9550S takes the cake with the lowest average power during the x264 encode, even slightly lower than the Q9400.
Peak power is also lowest on the Q9550S, note that it draws 11W less than the Core i7-920. But the thing to keep in mind is that, once more, the i7-920 is about 40% faster than the Q9550S.
Let’s look at the total energy consumed by the system during the benchmark:
Once again, the two Core i7 platforms offer better energy efficiency than the new Q9550S. In fact, the Q9550S offers about the same energy efficiency as the rest of the Core 2 Quad lineup and AMD’s new Phenom II X4 940. If you want energy efficiency, you actually want a Core i7.
Facebook
Twitter
RSS
62 Comments
View All Comments
strikeback03 - Wednesday, January 28, 2009 - link
Far and away the most cost efficient thing for those like you who only care about games is to stick with your dual core, followed by getting a faster dual-core or an SSD. Check the performance numbers in the Phenom II launch article, as most of the games are not using the quad-cores, very few of them look good in added performance for the money.WillR - Wednesday, January 28, 2009 - link
What it really boils down to is "which socket do you already have?". And Intel knows this. Think about it, they've been beating AMD pretty much since the C2D's came out so most people adopted that platform and already own Socket T/775 boards with C2D chips. Now that AMD has released a competing 45nm quad core, Intel has had to lower their prices to attract purchases of customers they already had. The decision for many people (including yourself) is do you spend $280 on a new Q9550 or $195 for a new P2 920 and another $100-150 on a new motherboard that will make it work? Clearly the almost $300 CPU is the cheaper option. And I'd bet most will go for the Q8200 or the Q9400. "Most" being the average consumer that buys it and gets someone else to install it for them. Intel would be silly not to get another $85, or even the $35 for the Q9400, out of customers that are upgrading from Core2Duo's. IMO, it's worth it just to avoid the hassle of changing 2 pieces of hardware at 1 time. That's a major headache if one of the parts is DOA.The only place Intel can lose business (in reference to quad cores) to AMD right now is people buying Phenom 9600s for $110 that want a quad core "just because", to people that already have an AM2 platform, AMD fanbois, and people that have not bothered to upgrade their 2Ghz P4 yet. And those last aren't going to go with AMD because they think AMD parts are cheap for a reason. There are many people that just won't buy from tech companies like AMD because they consider them "second rate" businesses with low quality products, even though they've never owned anything they make.
plonk420 - Tuesday, January 27, 2009 - link
what build of x264 was this?i'm assuming this build was downloaded via MeGUI and its updater...
Jedi2155 - Tuesday, January 27, 2009 - link
Have we really become that? I didn't think there ever wood be high volume enthusiasts.hansmuff - Tuesday, January 27, 2009 - link
I was hoping to get some information about how the chip overclocks and if there are significant differences between it and the non-S cores in terms of overclocking.Anything the author can add?
B3an - Tuesday, January 27, 2009 - link
Exactly, thats what nearly all of us care about. Such an OBVIOUS thing to have in the article.Anand Lal Shimpi - Tuesday, January 27, 2009 - link
The Q9550S didn't overclock any better than our other Q9550 that we used in the overclocking section in the Phenom II review.-A
Giant Panda - Tuesday, January 27, 2009 - link
You people really need to read before you post. At the bottom of page one the author states and I quote "...and in case you’re wondering, no, they don’t overclock any better. Our Q9550S couldn’t get any further than the Q9550 we used in our Phenom II review." If you aren't going to even bother reading the article why do you bother to post and ask questions that were answered in the article you clearly didn't even read?Ryun - Tuesday, January 27, 2009 - link
In the Photoshop tests I'm assuming you calculated joules by multiplying the time it took to complete the test by the average system wattage drawn from the wall. If that is the case the Phenom II 940 joules should be closer to about 3800 joules (24.2sec * 157watts) and not the 4700 joules you have listed.Please correct me if I am mistaken.
Anand Lal Shimpi - Tuesday, January 27, 2009 - link
I actually took the system power every second during the test and summed that. The numbers are close, but not identical.-A