Archive for April, 2008

h1

Clock Domain Crossing – An Important Problem

April 21, 2008

Sometimes, when crossing clock domains, synchronizers are just not enough.

Imagine sending data serially over a single line and receiving it on the other side from the output of a common synchronizer as shown bellow.

Assuming one clock cycle is enough to recover from metastability under the given operating conditions, what seems to be the main problem is not the integrity of the signal – i.e. making sure it is not propagating metastability through the rest of the circuit – but rather the correctness of the data.

Let’s observe the waveform below. The red vertical lines represent the sampling point of the incoming signal. We see from the waveform that since sometimes we sample during a transition – in effect violating the setup-hold window – the output of the first sampling flop (marked “x“) goes metastable. This metastability does not propagate further into the circuit, it is effectively blocked by the second flop, but since the result of recovery from metastability is not certain (see previous post) the outcome might be a corrupt data.
In this specific example we see that net x goes metastable after sampling the 3rd bit but recovers correctly. In a later sampling, for the 6th bit we see that the recovered outcome is not correct and as a result the output data is wrong.

Another interesting case is when both the send clock and the receive clock are frequency locked but their phase might drift in time or the clock signals might experience occasional jitter.
In that case, a bit might “stretch” or “shrink” and can be accidentally sampled twice or not sampled at all.
The waveform below demonstrates the problem. Notice how bit 2, was stretched and sampled twice.

To sum up, never use a simple synchronizer structure to transfer information serially between clock domains, even if they are frequency locked. You might be in more trouble than you initially thought.

On the next post we will discuss how to solve this problem with ring buffers (sometimes mistakenly called FIFOs).

Advertisements
h1

Another FSM Design Tool

April 17, 2008

For those who don’t read through the comments. Harry the ASIC guy commented on the last post about an FSM design environment from Paul Zimmer. You can find more details here.

h1

Visual FSM Design Tool

April 9, 2008

I am still not convinced visual FSM design tools make such a big difference but this one looks pretty cool.
I haven’t really went through all the features and details, so if anyone has some more details/recommendations/complaints about it, just email me or simply comment on this post.

h1

The Principle Behind Multi-Vdd Designs

April 2, 2008

Multi-Vdd design is a sort of buzz word lately. There are still many issues involved before it could become a real accepted and supported design methodology, but I wanted to write a few words on the principle behind the multi-Vdd approach.

The basic idea is that by lowering the operating voltage of a logic gate we naturally also cut the power dissipation through the gate.
The price we pay is that gates operated by lower voltage are somewhat slower (exact factor is dependent on many factors).

The basic idea is to identify the non-critical paths and to power the gates in those paths with a lower voltage. Seen below are two paths, there is obviously less logic through the blue path than through the orange one and is therefore a candidate for being supplied with lower Vdd.

multivdd.png

The idea looks elegant but as always the devil is in the details. There are routing overheads for the different power grids, level shifters must be introduced when two different Vdd logic paths converge to create a new logical function, new power source for the new Vdd must be designed and most important of all, there has to be support present by the CAD tools – if that doesn’t exist this technique will be buried.