muziq

This was standard on the PC-Engine, and I think the majority of VDC type display controllers of the time.. Personally, I’d take a bank switching scheme whereby CPU reads come from RAM as standard and CPU writes go to graphics memory.. Even as simple as 1 bit mapping of writes to either CPU RAM or VDC RAM would suffice well.. Though more complex is possible..

Iomart DC4 Leicester is actually at: Berkley St, Leicester LE1 4AT

You’ve not done this before have you ?

I did a prototype of a 3D low-latency server side mixing system, based on a hypothetical 4k clients, @48k each being mixed with the 64 loudest clients.. Using Opus, forced to Celt mode only and running 256 stereo sample frames at 128kbps.. Worked well, using only 6 cores for that workload.. The mixing was trivial, but the decode and encode of 4k streams was entirely doable.. This issue at that rate was 1.5M network packets a second.. If I was to revisit it, I’d look at using a simple MDCT based codec, with a simple Psychacoustic model based on MPC (minus CVD) and modified for shorter frames + Mdct behaviour versus PQMF behaviour, without any Huffman coding or entropy coding.. And put that codec on the GPU.. Small tests I did using a 1080ti indicated ~1M clients could be decoded, mixed and encoded (same specs as above) problem is then how to handle ~370M network packets a second :)

Edit: Had high hopes for High Fidelity, and came very close to asking for a job there ;) Shame it’s kaput, didn’t know that :(

PS3 was Cell processor.. PS2 Emotion Engine..

No, that’s very definitely a C64C, which was released in 1986.. But kudos to its little capacitors hanging on for so long ;)

Excellent read, especially all the comments of handling weird hardware behaviour.. Especially the ones about <14 channels on Max resulting in > 44.1k output.. Amazing how much you can do on that little chip with its PIO..

The 747 CMCA.. https://www.sandboxx.us/blog/americas-plan-to-build-747-arse...

If you’re not dividing greater than 2^23 numbers then can’t you just use the FP divide ? I’m sure I’ve done this in CUDA many years back.. Worked a treat :) If you are then you have my sympathies..

Yeah, I’ve spent five minutes scrolling a thread before someone says the obvious… Cepstrum for the win ;)

M!lk..

This afternoon, discussing with my boss, why issuing two x 64 byte loads per cycle is pushing it; to the point where l1 says no.. 400GB of l1 bandwidth is all we have.. Is all we have.. I remember when we could move maybe 50KB/s.. Ans that was more than enough..

The joys of writing sound drivers for these back in the day :)

Absolutely.. Currently working with a new HD audio codec and although I know it’s nonsense, it sounds and feels better than ever at times, in fact I can relate to his description of the clarity with his new gadget.. A simple 3 minute ABX test tells me I’m smoking crack and 1:1 normality is once again restored..

A 2011 era 27” iMac, that never booted to OSX, instead was installed from new with Windows.. Sheer, and unexpectedly, pure blissful experience..

Have you listened to early Jega ?