← Back to context

Comment by lmc

4 days ago

> My favourite: "audiophile-grade" audio players which allocate a single contignuous buffer of RAM into which they load/decode the whole .WAV/.FLAC file, because supposedly the CPU "jumping" between "fragmented memory" causes audible "jitter".

Thanks for the laugh... this is absolutely bonkers. In case anyone is wondering, before sound hits our ears it has to go through a digital to analog conversion, which takes place on hardware independent of the CPU, operating with its own clock and buffers etc.

In addition to that, while it is possible to hit a delay and run out of buffer because memory access is slow (the most obvious would be if the input got swapped to disk at an inopportune moment), but the audible effect is really obvious. This isn't some subtle "oh my music sounds ineffably worse" effect, it's "my computer is glitching and my music is unlistenable."

Am486DX/100 was enough to decode and listen an MP3 at 22KHz (and maybe mono?) and was more than enough to listen for 44/16/2 PCM. It's 31 y.o. today.

  • I remember playing 44khz 16-bit stereo MP3s encoded at 128 kbit/sec on a 133 Mhz 486.

    It gobbled like 90% of the CPU and I had to make sure I gave it a pretty large buffer so it didn't stutter when an app claimed CPU for more than a second, but it worked.

    • Depends on the vendor and a cache amount. But yes, 22KHz was a thing for a simple Notepad activities at best and at 11KHz you didn't care much 'cuz it wasn't that different from the usual.