Core i5 / P55 Lab Update
by Gary Key on September 11, 2009 12:00 AM EST- Posted in
- Gary's First Looks
This has been an interesting week to say the least for those of us stuck in the labs and not at AMD's DX11 GPU press briefings. Based on feedback from the Lynnfield launch article we have spent the last couple of days running additional benchmarks to address overclocking and clock for clock requests. Yes, we do listen and respond to the comments no matter how outlandish (you know who you are) some may be at times.
I will interject a personal note here, the emails/private messages that outlined a strong case for additional research and testing certainly held a lot more weight than comments like "You are on Intel's payroll...", "Worst review ever...", and the moonshot , "Illegal benchmarking methods..". First off, if we were on Intel's payroll we would not be working here (a logical conclusion, right? ;) ) As for the other comments, everyone is entitled to their opinions. We do our best to keep an open forum and let the comments fall where they may, but offering constructive criticism and facts to back up those comments is what actually causes change, not endless shock posts or attention grabbing statements. I still have hope in people abiding by the rules of Internet Etiquette, but apparently we are still a long ways off from that happening. I will step off the soap box, well, until the next article....
Just to set this up now, our overclock comparisons will be at 3.8GHz for the Core i5/i7 and Phenom II x4 965BE processors. Why 3.8GHz, well it is an easy number for all of our processors to hit on fairly low voltages with retail or mid-range air coolers. It is also an ideal clock range for the "set it and forget crowd" interested in 24/7 overclocking. Certainly we could go higher on air or water cooling and actually ran most of our Core i5/i7 numbers at 4.2GHz for the motherboard roundups. Our Phenom II x4 965BE is the hold up for higher numbers in our clock for clock comparisons.
AMD continues to have serious problems with their Phenom II processor range clocking above 3.8~4GHz on air with a 64-bit operating system. Unfortunately, there is nothing AMD can do to correct this in the current stepping, but they are actively working on improvements with each processor release. In fact, the latest Athlon II x2 processors are the first products we have that allow for 24/7 stable operation at 4GHz under Windows 7 x64. The quad cores are still lagging although our latest retail 965BE is showing promise around 3.92GHz in early testing. I state this now so it does not come as surprise later.
I will post several benchmark results later today based on our motherboard test suite. Anand will provide a more in-depth analysis next week along with an updated look at the Core i7/860. He might even have a surprise announcement from AMD. In the meantime, I have just about completed this additional testing and will return my focus on completing the first (of many) P55 motherboard article(s) that will be up in a couple of days. Our first review will cover the Gigabyte GA-P55M-UD2 among others. We recently received several other micro-ATX P55 motherboards and will look at those shortly. For now, this board is a perfect match for the Core i5/750 for our mainstream audience looking to upgrade an older platform.
Our graph below is an example of the information we will provide late today. Hopefully, this type of information will be useful for your purchasing decision along with our commentary about the results. I know there is not a Core 2 product listed, that will be forthcoming in the near future.
9/11 Update - I am still working on the FarCry 2 and H.A.W.X. benchmarks so the short update will be delayed until tomorrow morning.
Facebook
Twitter
RSS
159 Comments
View All Comments
Inkie - Sunday, September 13, 2009 - link
So, what you are essentially saying is that the cores have to be loaded just right: not too much and not too little, for the non-turbo score to be really representative of actual performance in a given task. For me, that's trying too hard to make it interesting. Not that I'm criticising your interest. I just don't really share it.Eeqmcsq - Sunday, September 13, 2009 - link
That's sort of what I'm saying. I'm interested in getting a scoring "range" that Turbo capable CPUs can provide to give a more complete picture. It's kind of analogous to how hard drives have a read speed range, example: 60MB to 80MB, depending on whether the data sits on the inside or outside areas of the platter. In normal usage, you're going to get various read speeds, but you won't read any worse than 60 MB/s, assuming no other external factors, but you also won't ALWAYS get 80 MB/s either.Likewise, Turbo capable CPUs have a performance range from no Turbo to best possible Turbo. That's why I'm interested in the no Turbo scores, to get the bottom end of this range.
Inkie - Sunday, September 13, 2009 - link
Look, you can get a range of performance from crawling along because of other things go on to performing at maximum with turbo-on (and reaching the maximum level of turbo) relatively isolated. I use my computer in the real world and don't choose combinations of tasks to make the turbo-off-relatively-isolated-figure especially significant. It might happen by chance that I get something like that sometimes, but it is no more interesting or significant than anything else.Just about the only useful thing that sites can benchmark is the maximum performance that can be expected. It is understood that if you multi-task you can have a whole range of lesser performances for a particular task, depending on how heavy you multitask. The turbo-off-relatively-isolated figure is just an arbitrary figure plucked out of that range that might happen by chance sometime. It's pretty much a waste of time benchmarking it if the goal is to give people an expectation of what they will get in the real world.
Mr Perfect - Saturday, September 12, 2009 - link
That's a reasonable request, I'd be interested in seeing that too. Like Eeqmcsq says, Turbo is like a free bonus.Also really looking forward to the expanded i7/860 tests. In the original article, it looked like a great balance between the pricey models and the cheap alternatives. It's a shame you didn't have more time with it then.
strikeback03 - Friday, September 11, 2009 - link
When looking at their review of the ASRock X58 Extreme I saw that in the comments snakeoil (the site's biggest AMD fanboi) and SiliconDoc (the site's biggest Nvidia fanboi) went at each other.Gary Key - Friday, September 11, 2009 - link
I am running the Turbo off numbers on the 750 today, which means getting these motherboard articles out is taking just that much longer. ;) However, we understand the importance of the request and I will show a few results late today. Anand will followup next week with a full analysis. Thank you for the suggestions.Eeqmcsq - Friday, September 11, 2009 - link
You, sir, gets a THUMBS UP! Thank you.Other suggestions I thought of that you might try for Turbo capable CPUs: Run a varied number of concurrent instances of a single threaded test. For example, run 1 instance of a single threaded test, then run 2 separate instances of the test at the same time, then 3, then 4. See what the numbers look like and how much Turbo contributes based on the # of busy cores.
yacoub - Friday, September 11, 2009 - link
You know, that's a really good point about a "guaranteed minimum". I hadn't thought of that when i defended the use of testing with Turbo on "because that's how it comes out of the box". I can appreciate your reasoning and agree with you that it would be helpful to also have Turbo Off numbers for the benchmarks. Looks like Gary will be doing that, so that's cool.Also, Gary is awesome. :)
jonup - Friday, September 11, 2009 - link
Gary, can you also add some results of OC with Turbo On. I know that the final OC will be lower, but in the initial review Anand pointed out that in a lesser threaded circumstances the effective maximum overclock with Turbo On is higher (i5/750 and i7/860) than the maximum OC with Turbo Off.The benfits of running lower OC with Turbo On will not only be in single and dual threaded app's but also power consumtion => lower temps. Good for 24/7 OC.
I am intrested in the socket 1156 and I run my systems OC 24/7.
Thanks Gary!
Gary Key - Friday, September 11, 2009 - link
I have been working on that also. :) I just received another retail 860 today that on a clock for clock basis needs about 0.06V less than our first sample, so the results should be more in alignment with the retail processors on sale now.