I worked as a test technician on B6800 systems when Burroughs had a manufacturing plant in Mission Viejo, CA. It was cool. All MSI components on PCBs plugged into a wirewrapped backplane, big squirrel cage fans for cooling, a power rack with 1" X 2" thick copper bars sticking out to supply the beast. All bolted together it was the size of an automobile.
I would wear headphones with a radio in them due to the noise of the fans, and if I tuned to an empty AM band while running diagnostics I could tell by the pattern of electrical noise if the machine was running properly or it was going to fail.
Debugging was so interesting, using just an oscillisope we would walk along the backplane and probe internals of the ALU, accumulator, memory bus, etc.
Most common failures were a wirewrap that was too tight cutting the insulation and causing a short, stray wire clippings in the backframe, and MSI components that were failing at speed.
That last one was the most challenging and interesting to find, usually requiring entering some microcoded routine to run the failing sequence of instructions, handle the exception, and loop back again, then go around and probe with the scope to find the failing component.
There were also more dramatic failures now and then, like exploding capacitors - they were the size of coffee cans and exploded like an M80 when they shorted. There were a couple of machines that caught fire, too.
Relevant to this article was the microcoding that we did when we had to write debug routines. The tagged words and stack architecture seemed bizarre to me at first, but once I got the hang of it I could whip up small routines quickly. They were entered by toggling bits via a slick test and maintenance processor panel. This was accomplished via a built in serial test scan mode, similar to IBMS's LSSD but a different implementation.
I would wear headphones with a radio in them due to the noise of the fans, and if I tuned to an empty AM band while running diagnostics I could tell by the pattern of electrical noise if the machine was running properly or it was going to fail.
Debugging was so interesting, using just an oscillisope we would walk along the backplane and probe internals of the ALU, accumulator, memory bus, etc.
Most common failures were a wirewrap that was too tight cutting the insulation and causing a short, stray wire clippings in the backframe, and MSI components that were failing at speed.
That last one was the most challenging and interesting to find, usually requiring entering some microcoded routine to run the failing sequence of instructions, handle the exception, and loop back again, then go around and probe with the scope to find the failing component.
There were also more dramatic failures now and then, like exploding capacitors - they were the size of coffee cans and exploded like an M80 when they shorted. There were a couple of machines that caught fire, too.
Relevant to this article was the microcoding that we did when we had to write debug routines. The tagged words and stack architecture seemed bizarre to me at first, but once I got the hang of it I could whip up small routines quickly. They were entered by toggling bits via a slick test and maintenance processor panel. This was accomplished via a built in serial test scan mode, similar to IBMS's LSSD but a different implementation.