Hacker News Reader

Comment by formerly_proven | Hacker News Reader

> This is made possible by placing a mux between the memory and the CPU that combines the two 64-bit accesses into a single 128-bit data path for the CPU.

This does not seem to be correct. Modules with an 128-bit data bus would obviously require a lot more pins. Instead what this actually seems to be about is placing a buffer between the two ranks (essentially two completely independent modules) and the data bus (presumably it buffers the command bus as well). The "128 bit" data bus on the host side is achieved by running QDR over the 64 bit wide bus.

Basically an evolution of LRDIMMs with a pinch of FBDIMM.

View on HN

> Instead what this actually seems to be about is placing a buffer between the two ranks (essentially two completely independent modules) and the data bus

AKA a Mux - or Multiplexer

The part that’s inaccurate is calling it a 128-bit data path. It’s not, it’s just a higher speed 64-bit path

No, multiplexers are more or less just dumb analog switches, though more specialized ones like e.g. PCIe muxes can include redrivers.

Multiplexers can be analog or digital

https://en.wikipedia.org/wiki/Multiplexer

> In electronics, a multiplexer (or mux; spelled sometimes as multiplexor), also known as a data selector, is a device that selects between several analog or digital input signals and forwards the selected input to a single output line.

An example of a common digital multiplexer would be the 74HC157 but if you think they're really not multiplexers I'm sure NXP and Texas Instruments would love to hear from you

Multiplexing is a concept anyway, the medium doesn't matter - you can multiplex radio signals, light, sound etc.

I certainly don't know, but I think what the guy is saying is that they are necessarily analog switches here because of the speed they have to operate at.

In some ways that’s true of a lot of modern digital computing. Kind of wild when you think about it…

It is, and it leads me to wonder what the differences between analogue and digital actually is, by definition. As Latches and a Clock? Serious question.

By definition, an analog signal encodes an “infinite” amount of information in whatever value it is taking on at the time point in question, while a digital signal encodes information in discrete states. For binary that is typically two states, but sometimes you can divide things finer, like multilevel flash cells or PAM4 signaling.

Digital the values “round-to-nearest”, so if supply is 1 V, then 0.6 V, 0.9 V, and 1 V all mean logical 1. Whereas for analog those different values mean different things.

Also, for digital you want to push the signals to the extremes so they are easier to read, while for analog that would be destroying information, you want to preserve the value.

(In practice there are fundamental limits to how much useful information you get out of analog signals due to noise.)

The answer's appreciated, but I'm afraid I didn't ask a very good question. What I was really getting at was, from the perspective of an EE, what would make an expert call one type of circuitry digital and the other analog?

Clearly the output signal has to be 0 or 1, which must mean the signal is boosted or reduced to an appropriate level (assuming we not trying to encode multiple values onto a signal; I'm just talking binary). So I guess the signal has to be captured (latched?) then modified. I don't think a clock is absolutely necessary as there have been asynchronous digital CPUs, but the presence of a clock clock is very typical as well.

Analog circuits are ones that primarily deal with the processing and manipulation of analog signals, while digital circuits are those that primarily deal with digital signals. Refer to my prior reply for the difference between analog and digital signals.

A clock is not necessary in this definition. For example a simple logic AND gate is digital and has no clock. The input is not captured or latched before being modified; nevertheless it is a digital circuit.

There is a real difference between an analog and digital multiplexer regardless of speed. For an analog mux, whatever voltage you put in you get out, including mid-rail voltages. For a digital mux, any input < VDD/2 causes an output of 0 V, and any input > VDD/2 causes an output of VDD volts.

You can use an analog mux on digital signals, but it probably won’t be as good as a digital one. However, you can’t use a digital mux to switch analog signals, it won’t work.

Edit: the one exception to this is for bidirectional digital signals you may want to use an analog mux, since you don’t know which side may be driving the lines. This would apply to DRAM since the data lines are bidirectional, so probably using an analog mux.

If you look at the image, it seems that the "mux" is actually a data buffer (probably much larger than a single transaction's worth), that would mean more latency for a transfer, but less time holding up the bus. At least that is my interpretation.

I can't tell if it's a buffer in the CS sense like you're saying, or a buffer in the EE sense, which is a device which simply boosts weak signals when they have too many taps in exchange for a slight delay.

Reply on news.ycombinator.com