Having worked in parallel computing for decades, I’ve seen a number of interesting processors arrive and then die due to lack of a usable software methodology or a way to run legacy code. GPUs and FPGAs have squeezed by, but are not invulnerable.
I thought I’d do a list, and if you don’t want to join it you can ask Cameron EDA for some help on your compiler and run-time systems. Feel free to suggest additions and corrections.
Dead…
+ AI
Uncertain…
These are likely DOA unless they die-stack memory and use wandering-threads…
I’m primarily interested in the transputer, which seems a good fit for present-day technology (multi-core dies, cache on chip, hyperfabric). I know there was (is?) a project to put the T8 on an FPGA but it didn’t seem to go anywhere (and why not go for the T9000)?
Apparently some of the technology is still used in ST embedded products?
The T8 was simple processor, well designed for its time, the T9000 was an exercise in over-reaching which forgot what the premise of the T8 was – using more simple processors rather than a bigger/faster one.
The T8 was a MISC machine, which being stack-based lost out in speed to RISC for single-threaded work.