ATI HD 5870 Scaling Performance: X58 vs P55 Showdown
by Gary Key on September 29, 2009 12:00 PM EST- Posted in
- Motherboards
We will start off our P55 coverage this week by answering a question that has been raised numerous times as of late, “Exactly how will the new DX11 cards perform on the Lynnfield/P55 platform compared to the Bloomfield/X58?”. The answer to that question depends on the game engine, settings, and processor choice for the most part. There has been much speculation that the Lynnfield/P55 platform would fail miserably with the next generation cards. That said, the difference in platform performance between the first DX11 capable cards available (ATI HD 5870/5850) is about the same as previous generation cards we tested in the Lynnfield launch article.
This means for single card performance both platforms trade blows for supremacy. However, for those running CF/SLI setups, the X58 continues to be the platform of choice for users wanting the best possible benchmark results. Does that mean the integrated dual x8 PCIe 2.0 logic on Lynnfield is a poor choice compared to the dual x16 PCIe 2.0 sporting X58? Absolutely not based on our initial tests. In fact, it should satisfy most users.
Now for those making an investment into an ultra high-end HD 5870 CrossFireX setup, the Core i7/X58 configuration will simply offer the best possible performance. Of course that performance comes at a cost, particularly power consumption. However, we have a feeling most owners sporting two HD 5870s are not that concerned about Al Gore knocking on their door in the middle of the night.
In the meantime, we have our first performance results comparing the Core i7/860 and P55 against the like priced Core i7/920 and X58 in a variety of games. We are going to state this upfront, this is not a GPU review of the HD 5870. Instead, we decided to pull this information out of the upcoming high-end P55 roundup so it did not get lost in the mix. Our resolution is limited to 1920x1080 that we use in the motherboard test suite. As such, the numbers speak for themselves. So let’s get right to the results today, but first, the test setup.
Test Setup-
For our test results we setup each board as closely as possible in regards to memory timings and sub-timings. The P55 motherboard utilized 8GB of DDR3, while the X58 platform contained 6GB. The P55 and X58 DDR3 timings were set to 7-7-7-20 1T at DDR3-1600 for the i7/920 and i7/860 processors at both stock and overclocked CPU settings. All power management features were enabled on each board and voltages were set at the lowest possible values when overclocking while still retaining 24/7 stability.
The image gallery below contains our Everest memory results with each processor overclocked at similar memory settings along with voltage/uncore/subtiming options. The 860/P55 offers slightly better throughput and overall latency numbers than the 920/X58 when overclocked. At stock, the latency numbers favor Lynnfield with assistance from the turbo mode.
Our game selection today is varied but is missing a couple of titles we wanted to show. We pulled Crysis Warhead as the CrossFireX scaling numbers were under 8% and Need For Speed: Shift does not have a CrossFire profile yet. AMD is currently working on updated CF profiles for the latest games. We also had some corruption problems when running Empire:Total War and Anno 1404 that is under investigation.
All of our gaming performance results are reported in average frame rates per second in the main bar graph with minimum frame rates reported in the text section. The results are sorted by the average frame rates. We are also reporting single card results with the HD 5870 running at PCIe 2.0 x8 speeds on the P55 platform to compare performance to the x16 single card setup. We installed an Intel CT Gigabit network card in the second physical x16 slot in order to force x8 operation.
Facebook
Twitter
RSS
85 Comments
View All Comments
tamalero - Thursday, October 1, 2009 - link
and whats your opinion about SiliconDoc Gary?it seems what the Zorro is for ATI, the SiliconDoc is for Nvidia (but weirder and more annoying)
Gary Key - Friday, October 2, 2009 - link
Honestly, I fully believe in trying to adhere to a no-ban policy as long as the discussions are constructive and do not turn into personal attacks. That said, SiliconDoc should be banned ASAP based on his "useless" spamming and he probably will be very shortly. His actions have ruined the last two articles.Our favorite the zorro, thezorro, aka SnakeOil has and will continue to be banned if his actions continue. Eventually he will run out of IP addresses or will control the Internet. :)
TA152H is a different animal, instead of simple shock jock posting, he tends to get extremely personal in his attacks not only against me, but also Anand and now other readers. He has not done this at other sites, which makes me believe I ran over his dog and Anand took out his cat recently. He is on a very short leash.
If I screw up and get called out on it, fine, I deserve it and the comments section is a way for people to communicate it. We do care what is said and pay attention in order to improve our articles. If you have a personal agenda with me, well, use the email or PM system and we will try to work it out.
However, considering the fact that our testing methodology is extremely sound and we play by the book, I find his comments to be perplexing as he wants us to change system settings for one platform to make it look better but doing the same tuning on the other platform is forbidden. At first I thought he was just trying to drum up controversy or look good at Toms, until I spoke with the editors at Toms and lets just say, that was a conversation I cannot repeat in public. ;)
Scheme - Friday, October 2, 2009 - link
If people want to troll they'll troll, no matter how many times you ban an IP they've used to post.Maybe you should consider making the registration process more rigorous, perhaps have it use forum accounts, and start moderating comments. More effort required to circumvent a ban, combined with less reward if your posts quickly get deleted may mean less incentive to troll.
At the moment it feels like it's open season for a small number of idiots to ruin the comments sections.
strikeback03 - Thursday, October 1, 2009 - link
Will TA152H choose another failed German fighter aircraft to name himself after if banned?mesiah - Thursday, October 1, 2009 - link
Gary, I don't know how you guys can read some of the comments and not want to just flip out sometimes. Maybe what you should do to make things a little more entertaining is this... Just like clubs have muscle around to work over annoying guys and toss them out on the street, you should hire a full time bully to verbally harass trolls before you ban them. It wouldn't really fix anything, but it would make my day more entertaining :)james jwb - Wednesday, September 30, 2009 - link
Anandtech is a massive, respected technical site whose audience has always been well-rounded, unlike say, Engadget, who rely on fanboy comments to fuel large debate. This site has never been like this, it's not a core of anything around here.Rudeness should not be tolerated, and ta152h is a piece of work imo. He deserves a ban on multiple levels. This guy has some issue with this site, it's that simple.
Maybe toleration of trolls like this can be left to their demise once you have a comment system where the audience can vote down idiotic comments, like engadget or dailytech.
adam92682 - Wednesday, September 30, 2009 - link
How about testing a p55 system with the NF200 on it?TA152H - Tuesday, September 29, 2009 - link
Another bad review by Gary.I was hoping you'd have learned something about testing by now, but, apparently not.
For the rest of you, you'll notice Gary is up to his old tricks. He clocks the Lynnfield slightly higher, and, also, clocks the uncore considerably higher.
Keeping in mind this increases memory access, as well as L3 cache speed, this is a meaningful increase. Also keep in mind that the cores use this uncore to communicate with each other. So, the uncore clock speed isn't immaterial.
On the plus side, he did mention the fact the Lynnfield needs higher voltages to clock the same as the Bloomfield. Quite a bit higher. Makes you wonder why he never mentions maximum overclocks, since they would seem to favor Bloomfield.
This type of bad testing is shameful, for anyone who has any sense of shame. Even with his clear bias for the brain-damaged (yes, I know at least a few of you were waiting for me to say it) Lynnfield, with a higher clock speed (albeit slightly), and higher uncore, he still couldn't get it to go faster.
Don't waste your money on Lynnfield for gaming. In real world, where you weren't clocking the uncore much faster, the Bloomfield would win by more, can overclock higher, and has a six core coming out, compared to a two core. Yes, the six core will probably be too expensive, for now, but it's at least an upgrade, and will be cheaper in the future. It's hard to see moving from quad core to dual core as any upgrade.
By the way, is anyone else wondering what Intel will actually be making on 32nm? With only the Gulftown for x58, and only a dual core for P55, what are they going to do with all their 32nm capacity? The Gulftown is big, but shouldn't sell that great, the dual core with GPU should sell very, very well to the masses, but it's small, especially since it's only the processor that's 32nm. There's got to be something else that will be coming out we haven't heard of. There's too much capacity, and too few products.
Intel is doing a really bad job of things lately. They release a lobotomized processor that isn't segmented properly, still fail to release a decent chipset for Atom, don't announce a single quad core 32nm processor, and still haven't lowered the power use on the x58 chipset, which has been out for a year. They're so uneven.
PorscheRacer - Saturday, October 10, 2009 - link
I'm guessing Larrabee would be using 32nm production also...goinginstyle - Tuesday, September 29, 2009 - link
You have to be really brain damaged TA152H."For the rest of you, you'll notice Gary is up to his old tricks. He clocks the Lynnfield slightly higher, and, also, clocks the uncore considerably higher. "
Looking at the screenshots both of the boards are at their stock ratios with their Bclk at 133.5, the 920 hits a 21x multi with turbo enabled and the 860 hits a 22x multi with turbo enabled, as designed and implemented by Intel. Or is that a concept that is above your head?
When overclocked, the p55 bclk is at 200.7 and the x58 is at 200.4. That is due to the clock generator. It would be impossible for them to change that and the resulting 5Mhz advantage does nothing for any score at 4.2GHZ. The uncores are set to stock ratios based on the screen shots. This means he did not tamper with the settings.
If you actually owned either system you would know a 200MHz uncore clock improvement does nothing for the benchmarks. Once again, you are grasping at straws here trying to defend a platform that is the electric companies best friend.
Where is that review of yours showing how any of your comments have validity? All you do is trash every article here and I hope they just ban you tonight for obvious flame baiting. None of your comments are true dude. So go back to doing your cut and paste articles over at Toms.