OCZ 3500EB: The Importance of Balanced Memory Timings
by Wesley Fink on April 7, 2004 12:04 AM EST- Posted in
- Memory
Enhanced Bandwidth Technology
So, what does OCZ mean by Enhanced Bandwidth? How does it work?Basically, Enhanced Bandwidth (EB) is a means of increasing memory bandwidth by optimizing memory latencies for the best interaction between the memory and the chipset and memory controller. By analyzing memory traffic and benchmark results under varying memory latency settings in the CMOS setup of the BIOS, OCZ claims to have pinpointed the bottlenecks that most affect performance. They further claim that conventional wisdom regarding some memory latencies, namely that the lowest CAS latency yields the best performance, were found to no longer hold true in the higher speed memory of today.
|
|
| Timing diagram for two modules, one running at TRCD-4, CL-2.5, tRP-4 (bottom) and the second with tRCD-3, CL-2.5, tRP-2 (top) showing two consecutive bursts of 8 from two different pages - one of the most common scenarios in real world applications. The effective bandwidth is the ratio between data transfers (black diamonds):NoOps (red arrows). In the case of EB this ratio is 8:7, while without EB it is 8:10, meaning that every transfer of 16 bits is penalized with either 7 or 10 subsequent bus idle cycles. (Clk: clock; Act: row activate command; Rd: read command; Pr: Precharge command, NoOp: No Operation) |
OCZ further explains that their EB series uses low tRP (RAS Precharge, which has a value of 2 in EB) and tRCD (RAS-to-Cas Delay, with a value of 3 in EB) latencies to enhance performance. This is then combined with a Variable Early Read Command to allow for the highest possible effective data bandwidth. Using these optimizations, OCZ says that in most applications, the 2.5-2-3 (CL-tRP-tRCD) will deliver bandwidth that is indistinguishable from CL-2 modules.
|
|
| The effect of issuing an early Read Command on back-to-back transactions of consecutively requested data blocks within the same page. Following one Row Activate Command, three Read commands are given at a CAS Latency of either 2, 2.5 or 3. The colored diamonds are the data transfers that belong to the Read Command in the same color. The graph shows that the net effect of increasing the CAS latency is a single cycle delay within a string of (in this case) 12 consecutive transfers, but no degradation of bandwidth. The double-arrows indicate the CAS latency which is amended by moving the read command further to the left (relative to the end of the previous burst). (Clk: clock; Act: row activate command; Rd: read command; Pr: Precharge command, CL: CAS Latency) |
OCZ says that they have redesigned their memory products using these findings to deliver the highest possible bandwidth to any computer system, and they call these new products EB or Enhanced Bandwidth.
A more technical explanation is beyond the scope of this memory review, but those of you who would like more information on the theories behind Enhanced Bandwidth should take a look at the OCZ Enhanced Bandwidth white paper.
Is OCZ correct: can memory timings of 2.5-2-3 perform just as well as CAS 2 in many applications? Our goal is to find out.
Facebook
Twitter
RSS
13 Comments
View All Comments
Pumpkinierre - Sunday, April 11, 2004 - link
Still waiting for my OCZ IC7 link WesleyTrogdorJW - Thursday, April 8, 2004 - link
bldkc... Not really. Only people overclocking their CPUs to extreme highs are pushing memory at the 500+ MHz range. The fastest official speeds are still DDR400, and DDR2 will probably be necessary before we gain official support for DDR466 and/or DDR533. I'm just waiting for DDR666.... eeeevil! Oh, wait, they'll call it DDR667 to appease the Bible thumpers.On a tangent, I'm an active Christian, and I find this "fear" of 666 to be rather absurd. "The number of the beast shall be six hundred sixty-six." Yeah, and the beast is apparently some computer part... or it would be if we had a 666 MHz CPU/RAM/Bus/whatever. Okay, on with life....
bldkc - Wednesday, April 7, 2004 - link
It wasn't long ago that we were asking the Processor Gods when they were going to catch up to the RAM Gods and use all that big bandwidth they were selling. Well here we are. Now we must pray that the Ram Gods will treat us kindly, and return the favor.Wesley Fink - Wednesday, April 7, 2004 - link
Adul -I will include some Athlon 64 results in an upcoming A64 board review. I did check compatibility with A64, which was excellent even on VIA K8T800, which can be very picky about memory and timings. Also took a brief look at A64 performance, and found best performance timings on A64 nF3 were 2.5-2-3-9 as mentioned in the review.
RyanVM - Wednesday, April 7, 2004 - link
And what if due to past transgressions, many (including myself) still don't trust anything OCZ puts their name on?Adul - Wednesday, April 7, 2004 - link
Any chance to get some test results on a Athlon 64 wes?grunjee - Wednesday, April 7, 2004 - link
Where the heck can I get some of this stuff??? Been looking and haven't been able to find any.Great review btw Wesley.
bigtoe33 - Wednesday, April 7, 2004 - link
I have an unbuffered available on bleedinedge forum.http://www.bleedinedge.com/forum/showthread.php?t=...
this shows turbo enabled on an IC7.
Spacecomber - Wednesday, April 7, 2004 - link
I was left wondering if you would see the same benefit from the enhanced bandwidth with Athlon Systems as you do with the Pentium 4 system that was used in the benchmarks.I've gathered that the rule of thumb is that Pentium 4s enjoy all the memory bandwidth that you can feed them, while Athlon XP systems are less bandwidth starved and do better with the lowest latencies you can run.
So, I'm wondering if this new OCZ memory will be of most benefit to people running Pentium 4 systems, especially overclocked 800MHz systems, but less (if any advantage) to Athlon users. I also wonder if there is any difference in benefits between an Athlon 64 and the regular Athlon with this memory, for that matter.
These are the kind of practical questions I'm still left with after reading the article. On the other hand, the article gets high praise for bringing this new memory to our attention.
Wesley Fink - Wednesday, April 7, 2004 - link
Pumkinierre -Our memory test bed is the Asus P4C800-E, and we have not tested EB on the Abit IC7. However, OCZ Tech Support tells us they achieve even better benchmark results with EB on the Abit IC7. I will try to provide a link to their test results on the IC7 later today.