Some Compliments

comp.arch Newsgroup

I think the lack of response (at least from me) has two reasons:

1) Your postings are too complete. You put a lot of thought into them, and I generally don't find any point to comment on; certainly not on the level of thought you put into it, and anything less would not do them justice.

2) Sometimes I have too little time to read your (pretty long) postings, and with all the exploration of side aspects, it's sometimes not clear whether the main idea is of interest to me (but even if it is, I probably would not have the time to reply to it in a worthy way, see above.

[Anton Ertl, 17 September 2013]

To your credit, you are the first person to have noted this.

But, ESM grew out of ASF and ASF had no predicates, indeed, when I did the ESM stuff (circa 2007) I did not have a PRED in my ISA.

You have a sharp thinking cap !!

[Mitch Alsup, 12 August 2021, after my mentioning the possibility of using a mechanism like his My 66000's PRED instruction modifier (which adds bits to following instructions for the sake of predication) to "extend the semantics of memory access instructions" in an Exotic Synchonization Mechanism code region.]

Tech Websites

So yeah, I think you've got a very good point (as usual).

[Real World Technologies, 23 January 2014]

Paul A. Clayton posted some good insights on the geometry of the caches and the data path lengths / transfer latency on RWT

[Lost Circuits, 28 October 2011 (link is dead)]

He is probably the only poster who still consistently attempts to start discussions related to the technical aspects of the CPU microarchitecture.

[Real World Technologies, 19 October 2003]


Sorry, you're pushing too close to what I do at work. So I'm afraid that even if I knew the answers, and I'm not saying I do or don't, I shouldn't tell you.

But it's cool that you are thinking about these things "the way the pros do".

[D.O., a professional computer architect then at Intel]

You are one of the best new posters on comp.arch in years. I'd like to meet you. I hope that we can work together at some time.

[A.G., professional computer architect]

You have the sort of obsessive attention to tradeoffs in computer architecture that is typical of some of us computer architects. By no means the entire team - a team full of people like you and me would probably never get the job done. But you have some talent.

If this was an Open Source project, I'd try to drag you in.

For a company, yeah, your resume scares me. But I still see promise in your posts.

[A.G., professional computer architect]

If we are ever in the same area, I'd love to meet you. I think that we could have some good brainstorming sessions with a whiteboard.

[A.G., professional computer architect]

I always enjoy your posts.

Unfortunately, I am not always free to respond to them, because I can't talk about stuff I am working on.

[A.G., professional computer architect, 17 September 2013]

You're a smart guy (if a little too self-deprecating perhaps). I get the sense that you haven't yet done a major project. Have you interviewed with IBM, Intel, AMD, etc?


Meantime, keep posting. It's good stuff.

PS: I'm as curious as the others as to why you don't have a hugely paying hi-tech job with more patents to your name than one can shake a stick at!

I read your posting ("Subject: branch pred. ideas--comments PLEASE") to the comp.arch newsgroup, and I'm very impressed with your knowledge. I'm with Motorola, and I'm working on filling two positions which require just the type of expertise that you seem to have.

[a desperate headhunter (Paul DeMone mentioned receiving a similar email)]

Because it was yet another well-written, good idea which you reinvented ;)

And I guess you are way above average -- or could become so quite easily. You have clearly demonstrated many times that you are bright and understand difficult things.

You write great articles, but could you slow down a bit?

It is delightful to hear from you. I have long admired your excellent fresh insights on comp.arch. Thank you very much for the mail. I don't have time to respond immediately, but will get back to you soon.

Smart or not, you are a scholar, i.e. a source of long forgotten information and overlooked connections. I've worked with a couple of those, and they are invaluable on teams bigger than a dozen or so.

[1 March 2013]

Back when I worked at Burroughs there was a guy who wrote no code and built no hardware. But he read every paper there was and knew what was going on in all parts of the machine and the development process, and his job was to wander around and say "have you read this?" or "you should talk to him".

You would be ideal for that post. I'm impressed.

[27 December 2012]

A letter

In a figurative sense get your derrière out of the chair in front of that terminal (I assume you're not kneeling) and earnestly seek some application of that admirably acute intellect of yours (NO REBUTTAL, I'm not FINISHED YET), creative spirit and brilliant argumentative ability.

[27 January 1991]