On 06/01/18 15:40, Lew Wolfgang wrote:
On 01/06/2018 05:11 AM, Carlos E. R. wrote:
Besides, I now consider open sourced CPUs a very interesting idea. Not trusting Intel anymore. Never.
I haven't trusted them since their FPU bug coverup!
Companies aren't good - or bad. It's the people in them (usually set by direction from the top). That's why I trust Google, but not Facebook. Not that I trust them implicitly, but if Google messes me up I expect it to be a genuine accident. Facebook is far more likely to be "accidentally on purpose".
Yes, an open-sourced CPU design would be great. Perhaps Sun's SPARC could be used as a starting point? I believe they open-sourced it before they were subsumed by Oracle.
Surely it's not beyond the wit of the Open Source crowd to define a basic VLW RISC instruction set, and then put a CISC interpreter layer on top ...
Will this dust-up also re-awaken the CISC/RISC debates? Complexity and security are inversely proportional, and Intel's complex instruction set CPU's set the standard for complexity. They hide whole CPU's inside the CPU facade they publicly display!
For very good reason, unfortunately :-( Modern CPUs can be clocked to what - 5GHz? That means that - per instruction cycle - a signal can move approximately two inches. Meanwhile, a motherboard is about a foot square ... Today's fast chips *need* to have pretty much an entire computer inside the die simply to be able to work at speed.
Reduced instruction set CPU's are consistent with the UNIX Philosophy: a function should do only a few basic things, but it should do them very well.
That's great, but don't forget the SECOND half of Einstein's great dictum - make things as simple as possible BUT NO SIMPLER. (Don't get me started - relational theory is great but as the basis of a database engine IT'S TOO SIMPLE.) The following makes interesting reading ... https://science.ksc.nasa.gov/shuttle/missions/51-l/docs/rogers-commission/Ap... One of Feynmann's key points is that management has a habit of fooling itself, and I have no doubt that Intel are sincere. Whether they are, like the best conmen, fooling themselves is open to debate. And actually, why should I assume other companies are any different? Who remembers the Lenovo root certificate scandal? There are too many people in positions of influence who, in all sincerity, push for decisions whose consequences they have no clue about. And unfortunately usually the people who DO have a clue are in no position to influence the decision. What's that saying? "Trust but verify". What's that alleged saying by Churchill? "The Americans can always be trusted to do the right thing. After they've tried all the alternatives, of course". Companies are no different. Which is why the loss of so many engineers in senior management is a technological tragedy :-( Cheers, Wol -- To unsubscribe, e-mail: opensuse+unsubscribe@opensuse.org To contact the owner, e-mail: opensuse+owner@opensuse.org