Real Review of DDR Mobo

An anonymous reader sent us an overview of the AMD 760 chipset, and benchmarks to give some real numbers to DDR RAM. (10-15% speed increase over comparable SDRAM systems)

Comments

Yay.

[yawhcihw]

Lets look at this objectively: a 10% increase in speed over SDRAM, which is already way behind what modern processors need in terms of speed/bandwith. Looking at the leaps and bounds with which processor speed is growing, a 10% increase is a drop in the bucket. It's a waste of time and money.
Intel and AMD need to stop their Mhz/Ghz race and prod some chip maker into making decent, fast RAM. Otherwise, we're gonna be running 2Ghz machines bottlenecked to 133Mhz bus. And that will not be cool.

Re:Yay.

[substrate]

It would take more than a gentle or even vicious prod to RAM chip developers. Processor speeds are getting faster because of pipelining and architecture first and process technology second. The pipelining allows the CPU to trade off additional latency for a higher clock rate. It takes a little longer for the first result to come out but after that there is only an incremental delay before the next one. The performance gained by process improvement (improvements in silicon) are miniscule compared to the improvements due to architecture... except that process improvements have enabled the archictectual improvements (designers can cram more transistors onto a die, more wire etc)

Unfortunately RAM doesn't work that way. People don't want to trade off latency for overall throughput. RAMBUS traded off latency for throughput. It has theoretically higher throughput than SDRAM but more latency, as a result in a certain class of performance measurements it does significantly worse than SDRAM.

Re:Yay.

[sethgecko]

Let's look at what you said objectively.

Lets look at this objectively: a 10% increase in speed over SDRAM, which is already way behind what modern processors need in terms of speed/bandwith.

Actually, it's a 100% increase in speed over SDRAM. It delivers data twice as fast. 100MHz clock speed * twice the data. Or another way, it yields 1600MB/s bandwidth.

Looking at the leaps and bounds with which processor speed is growing, a 10% increase is a drop in the bucket.

Yes, it is a drop in the bucket. But you're comparing apples to commodores. It's a 10% system performance increase over systems that use PC100 RAM. That's quite respectable without changing the processor. Wouldn't you like to make your processor run 10% faster without buying a new one?

Intel and AMD need to stop their Mhz/Ghz race and prod some chip maker into making decent, fast RAM.

Considering that Intel is pushing RDRAM running at 800 MHz and that still runs worse than DDR RAM, don't you think that this statement is a little off target? I understand that your and my idea of decent RAM is not Rambus. But as far as numbers on paper goes, RDRAM is quite fast.

Also, I take issue with what you say about modern processors needing more speed/bandwidth in memory. I thought I agreed with you until I took a look at Tom's Hardware. A 533 PIII gets a 126 sysmark rating. A 1 Ghz PIII gets a 194 rating, nearly twice as fast when thechip is nearly twice as fast! If modern processors are really waiting for RAM so much, why is processor speed a linear progression up the performance chart? It would be tailing off, with performance gains of a 1GHz PIII only marginally faster than a 700 or 800Mhz at the top of the chart.

It looks as if the fast cache on chip is the answer to slow RAM, and at least according to this chart, RAM speed does not make such a difference to fast processors.

Real PREview

[levendis]

This is not a review, its a preview. The distinction is important, because many initial revs of chipset and mobos have numerous performance and compatibility bugs. I wouldn't be suprised if memory throughput increases by 10-15% after a few "mature" revs of the BIOS and chipset. (Didn't something similar happen with the AMD750 "super-bypass" feature, as well as new BIOS revs on Via KX113 based boards?) At any rate, I'm glad to see some improvement in memory bandwidth without a disproportionate increase in cost. Running with an 11x multiplier (on Athlon 1.1ghz chips) is just way too ridiculous.
----

Meaningless article

[MobyDisk]

The final results here look like the old RDRAM tests - slower sometimes, faster other times, with no real conclusion. People gave up on RDRAM because it didn't deliver what it promised, results varied, and price was too high.
But these results make no sense. DDR has the same latency, higher bandwidth, but results in speed increases from -5% to +6%? It should be consistently faster, never slower

Either this mb is POC or...

[marat]

... or I understand nothing in modern computers. Look: for a long time (since ~200 MHz) I was told that current computers are limited by memory bandwidth. Every improvement in CPU speed gave too little gain in real life performance (even while not limited by disk io). Finally we've got amazing memory technology that should be twice as fast as before. If we have really had bottleneck in memory IO, we should have experienced at least 50% performance increment. What we see? Nothing. Only real difference in their benchmark caused by better IDE interface and hd.

So, I conclude that:

1. This motherboard is a piece of crap, or
2. DDR SDRAM idea is bullshit, or
3. This report is bullshit, or
4. We are not actually limited by RAM bandwidth but, say, by real instructions per second (as opposite to tics per second) CPU speed, or
5. I missed something, or
6. All of the above.

---
Every secretary using MSWord wastes enough resources