ExtremeTech: Does RAM Latency Matter?

[klah]

Is Low-Latency RAM Worth It?

Our tests show that improving RAM latency only makes a small difference in the performance of modern high-end PCs. The amount of improvement varies greatly depending on the application you're running, but it's safe to generally characterize the improvement by saying that, compared with CAS 3.0 RAM, CAS 2.5 will give you a 1% to 2% speed boost, and CAS 2.0 will give you 2% to 4%.
...
The real question is this: Is the marginal speed improvement of low-latency RAM worth its higher price? For most users, the answer is no. In a broad survey of online prices, we found that CAS 2.5 RAM costs about 30% more than CAS 3.0. If you're building a system with 1GB of RAM, you'll pay an additional $60 more for only one or two percentage points.

 

[brunswickite]

very good article..

 

[LordPhoenix]

"Anyway those timings are terrible AND will perform even worse on AMD because they use Samsung IC's see here...same IC's but differnt moduleshttp://www.anandtech.com/memory/showdoc.aspx?i=2145

... ballistix, on the other hand, can do 2.5-3-3 at that speed with AMD 64."


"hahahahhahah u talk about timings like they really mean something. timings dont matter. unless ur an idiot that cares about millliseconds. no timing is bad. unless its pre pc100. that's what i call bad timing."

yay guess im right .

 

[ponyo]

Yeah but try telling this to Muskin, Corsair, or OCZ fanboys.

Same can be said about Raptor harddrive but that's another thread.

 

[Lyfer]

Another reason to get Kingston/Mushkin/Corsair value ram.

 

[SonicIce]

Very interesting.

 

[Gerbil333]

Originally posted by: klah
Is Low-Latency RAM Worth It?

Our tests show that improving RAM latency only makes a small difference in the performance of modern high-end PCs. The amount of improvement varies greatly depending on the application you're running, but it's safe to generally characterize the improvement by saying that, compared with CAS 3.0 RAM, CAS 2.5 will give you a 1% to 2% speed boost, and CAS 2.0 will give you 2% to 4%.
...
The real question is this: Is the marginal speed improvement of low-latency RAM worth its higher price? For most users, the answer is no. In a broad survey of online prices, we found that CAS 2.5 RAM costs about 30% more than CAS 3.0. If you're building a system with 1GB of RAM, you'll pay an additional $60 more for only one or two percentage points.

The Halo scores in particular are worth pointing out. Our P4 system gains over 4% going from CAS 3.0 to 2.5, and over 10% going to 2.0. The Athlon 64 does even better, earning 7.5% moving from CAS 3.0 to 2.5 and 13.6% going to 2.0. In both cases, that's an absolutely enormous speed increase, but we were able to verify it with repeated testing. Something about the way Halo is coded makes it highly sensitive to RAM latency, and we wouldn't be surprised if there were other games out there with similar properties.

For most application, I can't tell a bit of a difference. I have 2x256mb's of Crucial PC2100 at 2.5-3-3-6 in an MSI K7N2G-L, and I have 2x256mb of Corsair TWINX3200LLPT at 2-2-2-11 in an Abit NF7-S 2.0. Until I upgraded the hard drive in the Abit machine, the computers felt identical in general apps (going from an old 2mb cache, 7200rpm drive to a new 8mb cache drive helped loading times a lot though).

Games are another story. When a game really stresses a CPU, I've seen the difference between 3-3-3-7 and 2-2-2-5 cause the framerate to jump from 20fps up to 25fps. That's noticeable.

Think about it this way. Low latency RAM timings are similar to upgrading to the next fastest processor model. For example, An Athlon 64 3200+ is going to be hardly any faster than an A64 3000+ (both with 512kb's of L2 cache). If the 3200+ ran at 3-3-3-7, and the 3000+ ran at 2-2-2-5, I bet they'd be about even in games.

For most users, I'd say go with some standard RAM: 2.5-3-3-6. Crucial/Corsair Value/Kingston Value works fine. For gamers, I think spending about 30-50% more on RAM (up to $75) is worth it. It really depends on the person though. Some people can't justify spending that extra $75 to gain 13% in Halo...I can though.

 

[ponyo]

Spend that extra $75-100 you saved by buying value ram into better videocard. You'll get good 25-75% boost in games and is something that you'll be able to notice. Or buy more value ram.

As for Halo, get something like 6800GT and you'll get 60+ frames with everything maxed at 1600x1200. Gamers are always better off spending the savings on better videocard. $75-100 could mean difference between something like 9600 vs 9800 pro or 6800nu vs 6800GT.

 

[klah]

Well they ran all of the gaming benchmarks at 640x480 to maximize the effects of cpu/ram. I imagine at a more reasonable level the results would be closer.