Memory DDDR3-1600 11-11-11 is worse than 1333 9-9-9, right?

Chicken76 · 10 Nov 2012

If it were 10-10-10 for the 1600 module, it would be marginally faster, but at CL11 it is actually slower, right?

GeorgeStorm · 10 Nov 2012

Depends on the application I think, some programs prefer the speed, others the tighter timings.

Kodongo · 10 Nov 2012

I would recommend taking a look at the first page of this AnandTech article which pretty comprehensively outlines the workings and quirks of DDR3 memory.

The part which is most pertinent to you, I have added below.

So What Can I Do About Sub-Timings?

As a general rule, lower is better. Memory kits on the market will vary in their subtimings – you can purchase DDR3-1333 9-9-9, DDR3-1600 11-11-11 all the way up to DDR3-3000 12-14-14. The question then becomes whether you want to decide between two similar kits. Imagine the following kits:

DDR3-1333 9-9-9
DDR3-1600 10-10-10
DDR3-1866 11-11-11

In a lot of scenarios, an enthusiast may take one look at these numbers and tell a user that these kits are equivalent – boosting the memory speed but increasing the sub-timing latencies causes similar performance. There is one way to determine whether a kit might be better than another, and that is to look at the calculable latency of the kit.

Calculating this value is a simple enough formula:

2000 x (CL / Speed ) = Latency in nanoseconds (ns)

Thus for the three kits above:

DDR3-1333 9-9-9 has a latency of 13.5 ns
DDR3-1600 10-10-10 has a latency of 12.5 ns
DDR3-1866 11-11-11 has a latency of 11.79 ns

This latency essentially tells us which kit is fastest at non-sequential reads. Non-sequential reads are important in a lot of variable scenarios, such as video games whereby the user could perform one of a billion different actions and as such different elements of the memory have to be loaded.

The downside of this test is that it does not take into account consecutive reads. When dealing with conversion, video editing, or anything that requires a large dataset to be read sequentially, we have to look at how long reads are processed.

The way to check this with DDR3 is as follows:

Cycle time in ns = 1000 / (Memory Speed / 2)
Bit time in ns = 1000 / Memory Speed

The time to read a single word of data (word is a technical term meaning 64 bits) is given by the Cycle Time multiplied by the CL. The time to read eight words is the Cycle Time multiplied by the CL then add seven lots of Bit Time. Let us go through the memory kits above with this method.

DDR3-1333 9-9-9 has a Cycle Time of 1.5 ns and a Bit Time of 0.75 ns
The time to read one word is 1.5*9 = 13.5 ns
The time to read eight words is 13.5 + 7 * 0.75 = 18.75 ns

DDR3-1600 10-10-10 has a Cycle Time of 1.25 ns and a Bit Time of 0.625 ns
The time to read one word is 1.25 * 10 = 12.5 ns
The time to read eight words is 12.5 + 7 * 0.625 = 16.875 ns

DDR3-1866 11-11-11 has a Cycle Time of 1.07 ns and a Bit Time of 0.536 ns
The time to read one word is 1.08 * 11 = 11.79 ns
The time to read eight words is 11.79 + 7 * 0.536 = 15.54 ns

In both the sort reads and long reads, DDR3-1866 11-11-11 wins out of the three kits. But what if it was not so clear cut?

The following kits have the following timings and results:

DDR3-2000 at 9-9-9 reads one word in 9 ns and eight words in 12.5 ns
DDR3-1666 at 7-7-7 reads one word in 8.75 ns and eight words in 13.125 ns

This means that the DDR3-2000 kit should be better for longer reading workloads, whereas the DDR3-1666 kit should be better for random reads.

I should stress (and add a disclaimer) that this comparison is all at the high level, as we are only talking about memory speed and CAS Latency – everything else plays its part, and I highly suggest reading Rajinder’s memory article to get a deeper look as to how this all works.

Personally, I use these formulas when overclocking competitively – if I have two kits, one of which can do DDR3-2000 6-7-7 and the other is DDR3-2666 11-13-13, I can decide which one is more appropriate for the benchmark in question.

Command Rate

This funny little number at the end is often quoted as 1T or 2T depending on the memory kit, how many modules are installed, and the motherboard settings. The command rate is the address and command decode latency, essentially the delay between accessing and decoding data - this delay allows the memory time to be accessed without errors.

In an ideal world there should be no latency, but in performance tests using a setting of 1T is shown to be quicker than 2T for synthetic benchmarks. Whether a user can feel the difference (in essence it adjusts peak bandwidth as well) is debatable, but the slower the kit as standard, the more of a difference will be felt between the two options. The argument also exists that a setting of 2T will allow the kit to be overclocked higher.

By default 2T is usually selected for memory kits that contain more modules - on the off chance that one module of the kit cannot perform at the stated speed using 1T timings, defaulting to 2T will make sure more modules pass the binning process.
Click to expand...

Chicken76 · 10 Nov 2012

Thanks Kodongo. Have forgotten about that article.
It seems 1333 9-9-9 is better than 1600 11-11-11 in every regard.

Frohicky1 · 10 Nov 2012

Or in a different form, this:

http://www.google.co.uk/imgres?hl=e...&ndsp=28&ved=1t:429,r:1,s:0,i:69&tx=186&ty=38

Deders · 11 Nov 2012

In terms of actual latency there isn't much in it:
9/1333 = 0.006751
11/1600 = 0.006875

adam_bagpuss · 11 Nov 2012

in real world speed is better than timings nowadays, however anything 1600mhz is wasted unless you have an amd setup using the on board gpu

mm vr · 12 Nov 2012

Also check out this article (pages 3-6): http://www.bit-tech.net/hardware/memory/2011/01/11/the-best-memory-for-sandy-bridge/1

Pookeyhead · 12 Nov 2012

When I was playing around with Geekbench last year, I found that 2133MHz with 10-11-10 1T was measurably faster than 1800MHz with 9-9-9 1T. So reality and paper calculations didn't quite match up for me.

Deders · 12 Nov 2012

It will be faster. it's just that as the mhz increases, the timings don't need to be as tight to get the same latency. So you get the benefit of increased bandwidth without losing out so much in terms of latency:

10/2133 = 0.00469
9 / 1800 = 0.005

So the higher clocked ram actually has less latency even though the timings look looser.

Pookeyhead · 12 Nov 2012

Well... I got the same numbers on paper, which led me to think they would perform similarly. That .00031 must make more of a difference than I thought.

Deders · 12 Nov 2012

It was probably the extra 333MHz Bandwidth that made the most difference, it's just that the extra .00031 didn't make the latency any less than before.

Pookeyhead · 12 Nov 2012

Deders said: ↑

It was probably the extra 333MHz Bandwidth that made the most difference, it's just that the extra .00031 didn't make the latency any less than before.
Click to expand...

Hmm.. yeah.. You're right me thinks. Interesting stuff!

mm vr · 12 Nov 2012

...and real world performance, particularly in games, is not affected at all by RAM settings as the article I posted shows.

Log in or Sign up

Memory DDDR3-1600 11-11-11 is worse than 1333 9-9-9, right?

Chicken76 Minimodder

GeorgeStorm Aggressive PC Builder

Kodongo What's a Dremel?

Chicken76 Minimodder

Frohicky1 Awaits his moosey fate . . .

Deders Modder

adam_bagpuss Have you tried turning it off/on ?

mm vr The cheesecake is a lie

Pookeyhead It's big, and it's clever.

Deders Modder

Pookeyhead It's big, and it's clever.

Deders Modder

Pookeyhead It's big, and it's clever.

mm vr The cheesecake is a lie

Share This Page

Log in or Sign up

Memory DDDR3-1600 11-11-11 is worse than 1333 9-9-9, right?

Chicken76 Minimodder

GeorgeStorm Aggressive PC Builder

Kodongo What's a Dremel?

Chicken76 Minimodder

Frohicky1 Awaits his moosey fate . . .

Deders Modder

adam_bagpuss Have you tried turning it off/on ?

mm vr The cheesecake is a lie

Pookeyhead It's big, and it's clever.

Deders Modder

Pookeyhead It's big, and it's clever.

Deders Modder

Pookeyhead It's big, and it's clever.

mm vr The cheesecake is a lie

Share This Page

Useful Searches