The foundation of the computing industry’s innovation is faltering. What can replace it? | | | | | |
| | | | | The foundation of the computing industry’s innovation is faltering. What can replace it? By Tom Simonite Shrinking transistors have powered 50 years of advances in computing—but now other ways must be found to make computers more capable. | | | | Sent from Yahoo Mail for iPhone On Wednesday, January 24, 2018, 9:06 AM, Mike Schwab <mike.a.sch...@gmail.com> wrote: With the Google, Amazon, and Microsoft/Bing search engines programming FPGAs with their algorythyms, aren't at that stage? I mean FPGAs are like a level below RISC instruction sets. https://www.forbes.com/sites/moorinsights/2017/08/28/microsoft-fpga-wins-versus-google-tpus-for-ai/#444247e39045 Has any IBM engineers considered experimenting with z/CPUs & z/Channels & Crypto cards built with FPGAs? Might be ready for z/16, z/15 would probably be too soon. Maybe a Micro z/15 on a 1U or 2U blade server with 16/32 FICON on the back? 2-4 LPARS max? Maybe even fits into a slot in a DS8xxx storage box? On Wed, Jan 24, 2018 at 7:51 AM, John McKown <john.archie.mck...@gmail.com> wrote: > On Wed, Jan 24, 2018 at 7:41 AM, Elardus Engelbrecht < > elardus.engelbre...@sita.co.za> wrote: > >> John McKown wrote: >> >> >Opinion article on Vulture Central about the end of an era for Moore's >> Law. >> >http://www.theregister.co.uk/2018/01/24/death_notice_for_moores_law/ >> >> Hmmmm, I usually read those register articles with a pinch of salt, but it >> seemed they have something today ... >> >> Shift is now apparently on software algoritms instead of hardware >> optimization and improvements ... >> > > I have a vague memory from long ago. When RISC machines were first coming > out (IIRC), it was said that the days of CISC machines were over because > the compilers on the RISC would do all the optimization needed for high > performance. I.e. a lot of the "out of order" sequencing (to avoid AGI & > optimize register usage) would be done by the compilers instead of the > hardware. That is one argument used by IBM for people to use Metal C > instead of HLASM. > > >> >> Ok, here is an interesting article describing that law 'number of >> transistors doubles in about 2 years'. >> >> https://en.wikipedia.org/wiki/Moore's_law >> >> Enjoy... >> >> Groete / Greetings >> Elardus Engelbrecht >> > > > -- > I have a theory that it's impossible to prove anything, but I can't prove > it. > > Maranatha! <>< > John McKown > > ---------------------------------------------------------------------- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- Mike A Schwab, Springfield IL USA Where do Forest Rangers go to get away from it all? ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
