An increasingly critical aspect of machine design is handling the
waste heat and acoustic noise of operation. This may seem like a boring
subject, but cooling is a centrally important one if you want your ULB to
last -- because thermal stress from the electronics' own waste heat is
almost certainly what will kill it. You want that fatal moment to happen
later rather than sooner. On the other hand, cooling makes acoustic noise,
which human beings don't tolerate well.
This tradeoff bites harder than you think; it's the fundamental
reason that, despite our money-is-no-object premise, we're not going to
relatively exotic technologies like liquid-cooled overclocking or RAID disk
arrays for a performance boost. Sure, they may initially look attractive
-- but overclocked chips and banks of disk drives require massive cooling
with lots of moving parts, and it's not good to be trying to do creative
work like programming with anything that sounds quite so much like an
idling jet engine sitting beside one's desk.
It's fair to say we've already reached the point at which the thermal
load vs. cooling-noise tradeoff is the effective limiting factor in the
performance of personal machines. Ten or even five years ago, even low-end
and medium "server" machines differed from personal-PC designs in fairly
important ways (different processor and bus types, different speed ranges,
etc.) Nowadays specialized server architectures are in retreat at the high
end of the market and everything else looks like a PC. And the difference
between a "PC" and a "server" is mainly that servers live in server rooms,
and are allowed to have monster cases with lots of noisy fans.
So how do we manage this tradeoff for a personal, desktop or
desk-side machine? Careful choice of components and being willing to pay
some price premium for cool-running and low-noise characteristics can help
a lot. Even exceptionally clueful system integrators (such as the late
great and beloved hardware business of VA Linux Systems -- ouch!) can't
generally afford to do this, because they're under constant competitive
pressure to cut price and costs by using generic components. But we aren't
economizing here; we get to do it right.
Reducing expected noise and heat in a design call for different
strategies. It's relatively easy to find decibel figures for the
noisemaking parts in a PC design. And, once you know a little basic
audiometry and a few basic rules of thumb, it's not hard to form a fair
estimate of your design's noisiness. Estimating a design's heat
dissipation is harder, partly because the waste-heat emission of a PC's
subsystems tends to vary in a more complex way than the acoustic emissions
of the mechanical parts. This means that you can and should try to design
ahead for low noise, but on the other hand expect to have to monitor for
heat-dissipation problems in your prototype and solve them by building
in more cooling.
Here's the basic audiometry you need to know to control your
design's noise emissions:
Sound is measured in decibels, abbreviated dB,
relative to the threshold of audibility, "A". (Thus, sound levels above
that threshold are written "dBA".) The scale is logarithmic, with every
3dB increment roughly doubling sound intensity.
For sounds that are not phase-related, decibel levels add as a
logarithmic sum. Thus if X and Y are uncorrelated sound sources,
dBA(X + Y) = 10 * log(10 ^ (dBA(X)/10) + 10 ^ (dBA(Y)/10))
A consequence of the above formula is that dBA(X + Y) cannot be
more than 3dB above the greater of dBA(X) and dBA(Y) for uncorrelated
sources (6dB for perfectly correlated ones).
Sound from a point source decays by an inverse-square law,
roughly 6dB for each doubling of distance.
Important thresholds on the decibel scale:
The acoustic noise emitted by PCs is normally a combination of
white noise produced by airflow and high-frequency noise produced by
bearing friction in drive spindles and (mostly) fans.
The best low-noise ball-bearing case fans emit around 20dBA.
Typical sleeve-bearing fans emit 30-50dBA.
According to the indispensable Tom's Hardware site, you can expect
to cut at least 5dB off the interior noise level of the computer with a
good choice of case.
We'll use these facts to estimate the design's noisiness later
on.