On Wed, Jun 20, 2018 at 10:17:38PM +0200, Arnt Karlsen wrote: > On Wed, 20 Jun 2018 15:16:28 -0400, Steve wrote in message > <20180620151628.0e132...@mydesk.domain.cxm>: > > > There was a discussion of whether to retain 32 bit, and that brought > > up another question in my mind: When will we have 128 bit computing? > > ..2000?: https://en.wikipedia.org/wiki/Transmeta_Crusoe > 256bit?: https://en.wikipedia.org/wiki/Transmeta_Efficeon
We're talking about word size / pointer size, not machine instructions. Transmetas merely could pack multiple instructions for parallel execution. Itanic had the same: three parallel instructions packed into a 128-bit piece, yet no one calls it a 64-bit architecture. x86 on the other hand has variable size of opcodes, 1 to 15 bytes. This, by the way, is the biggest flaw of x86 instruction set: the rules to split code into opcodes are extremely hairy, requiring all the decoding work to be done twice if you want a pipeline. Meow! -- ⢀⣴⠾⠻⢶⣦⠀ There's an easy way to tell toy operating systems from real ones. ⣾⠁⢰⠒⠀⣿⡁ Just look at how their shipped fonts display U+1F52B, this makes ⢿⡄⠘⠷⠚⠋⠀ the intended audience obvious. It's also interesting to see OSes ⠈⠳⣄⠀⠀⠀⠀ go back and forth wrt their intended target. _______________________________________________ Dng mailing list Dng@lists.dyne.org https://mailinglists.dyne.org/cgi-bin/mailman/listinfo/dng
