Microcoded 1401 from TTL ??

Hi,

My first job as a student worker in college was as a 1401 programmer. I came to deeply admire its amazing architecture, which accomplished so much with so little. When it came time to upgrade, I very much missed it. Since then I have always wanted to own one, but the responsibilities of raising a family and a career always came first. I retired in 2011 and went back to school in 2013, eventually getting my Ph.D. in 2018. Since then I have taught and mentored students at Ole Miss as a volunteer in the Heterogeneous Systems Research Lab.

A while back a friend called my attention to your work on the 1401 at CHM. That rekindled my interest in the 1401. As part of my course work in architecture, I picked up microcoding skills, and built a lab at my house capable of realizing my efforts. Eventually, my ability to do it and my fondness for the 1401 resulted in my taking on a microcoded 1401 project.

My strategy is to construct a simulator in C++ structured to reveal and ease correct microcode implementation. My biggest challenge will be correctly implementing the details missing in the surviving manuals. Here are two examples I have discovered so far:

1. The documentation is silent on where instruction fetch places a d-modifier. I suspect it is left in the A-Reg based on my feel for the IF cycles.

2. The 'Skip and Blank Tape" documentation in A24-3069-2 p. F-4 is missing the register contents after execution. Again, that is fairly easily inferred from other similar instructions.

This gets me to the point of my email. From time to time I could benefit from some help validating my guesses on fuzzy or undocumented details. I would only ask for help after doing reasonable and appropriate research on my own. Also, I would appreciate feedback on design decisions.

I plan on an initial build of 5 identical systems. In return, I would, up to 3, give a system to those who have helped. I will keep one for myself, and donate one to the 1401 exhibit at CHM. I am open to adding interfaces to real devices such as the 1402, 1403, and 729 as follow-on projects.

If I were you, I would be pretty skeptical at this point and have several "how you plan to" questions, and would be pretty unwilling to go any further before getting reasonable answers. So, I am willing to take on any questions you may have. It is pretty easy to anticipate some obvious ones:

1. Are you crazy?: No, but very obsessive. It helps.

2. What will the system look like?: My current plan is a series of up to 8, 8.5" x 11" boards on a 9" X 11" backplane, with each board being a 4-layers (Vcc and ground on the inner layers). Three slots are dedicated: Front panel, micro-sequencer, and interface.

3. How do you plan on doing I/O?: I/O would be handled via a Raspberry Pi mounted to the interface board. Access to the Pi would be via wi-fi and NOMACHINE remote desktop sharing to a GUI application. Simulated devices would not implement any media-related errors. Tapes would appear as arbitrarily long and rewind or backspace instantly. I have not thought through the RAMAC details yet, but will probably implement as a 1311.

4. What will the front panel look like?: My personal nostalgia is a strong driving force. It will be as close to the original as I can make it. (But my mechanical skills are not very good.) The board will have white silk screening on a black background. The front panel resides in the first slot on the backplane. The look and feel of the board will be scaled down to those dimensions. Bits would be implemented with two-color LEDs -- white for normal and red for error. The register push buttons would be implemented with a push button and yellow LED instead of the illuminated push buttons. Only the front panel with the switch flap closed would be rendered. The switches would be via the GUI interface running on the Pi. One of the last things I would do is shadow the front panel in the GUI. I feel the lights on the front panel are part of the charm of the 1401. So, I would like a physical front panel.

5. What do you anticipate the clock speed to be?: I expect 5MHz. I plan on implementing as a Mealy FSM with a simple two-phase clock with 100ns for each phase. During one phase the next state is computed from the current state, and during the other phase, the register transfers occur. All parts can complete their work in well under 100ns. (E.G. the microcode EPROMs are 50ns parts.)

6. Do you plan to sell these?: No. It would be easier selling used Toyotas to the Ford or GM board of directors than selling these. I will place everything in the public domain. Once I have the simulator substantially working, and am sure I can author the microcode, I will create an evolving repository that contains the current versions of all the necessary components: Full simulator source, KiCad files, PCB Gerber files, the source for the microcode compiler, and microcode for all EPROMs. I plan on using commonly available 74HCxx 74LSxx parts. The only exception is the initial version will use 27C160 1MBx16 EPROMs because I am not sure how big the microcode will be. Once I know, I will redo using EPROMs of appropriate speed and size. I am open to an FPGA implementation, but a TTL implementation is closer to an actual machine.

7. Have you worked on other projects of similar size?: Yep, lots. One of the best examples is I lead the technical team that installed the PeopleSoft Financial, HR, and Student modules at LSU Health Sciences Center (9 public hospitals and 2 academic campuses) on time and on budget. There were others such as Y2K and Katrina recovery. (We purchased new hardware (150 plus servers), relocated to a site in Baton Rouge, and restored all systems at the new site in 2 very long weeks. We did not miss a payroll nor miss a vendor payment.)

8. Is all this worth it?: No, not really. You have to have a deep fondness for the 1401 to make it worthwhile. I suspect that universe is pretty much the CHM 1401 team and a handful of 1401 enthusiasts. It is my hope you see it as I do, and that is why I reached out to you.

David