Worked on the CM-1 and CM2. I felt they were awful buggy. At one point they asked if they could use my code to run as a diagnostic, it would break the log() function on occasion.
The Cray fluorinert fountains were way cooler :)
The Cray fluorinert fountains were way cooler :)
It's also the computer that powered the Chevrolet Navlab self-driving car in 1986.
Excluding the bug side of things. If they did everything they were supposed to how hard was it to get them to perform a task that distributed the work through the machine.
I read some stuff on, I forget, maybe *lisp? I found it rather impenetrable.
On top of this, have there been any advances pin software development in the subsequent years that would have been a good fit for the architecture.
I always thought it was an under explored idea, having to compete with architectures that were supported by a sotware environment that had much longer to develop.
If the problem was very data-parallel, one could get nearly perfect linear speedups.