The next Apple chip

By: David Hess (davidwhess.delete@this.gmail.com), November 21, 2020 8:17 pm
Room: Moderated Discussions
Brett (ggtgp.delete@this.yahoo.com) on November 20, 2020 8:56 pm wrote:
>
> I have long brow beated Intel for not designing a 3 GHz chip for mobile, cheap
> ass morons they are. But to go wider x86 decoding becomes expensive in area and
> heat. x86 is stuck between a rock and a hard place, something has to give.

Even before Smartphones, I thought Intel's abandonment of the low power embedded market was a mistake because it would allow someone else, ARM in this case, to do to Intel what Intel did to the RISC workstation and server markets. They later made a token defense but it was too little and too late to do more than delay.

> If x86 stays stuck then ARM will pass it by in the next half decade.
>
> Will x86 be forced to change to a fixed width instruction format, or at least something easier to decode?

I suspect the effects of instruction format and decoding will be minor compared to other factors and less so with micro-operation cache.

> 32 bit opcodes are getting tight, how about 3+3 byte opcodes page aligned, 3 bytes is good for integer opcodes
> and 6 bytes gives you a big FPU register file with 4 operands, and all the oddball x86 add from memory stuff
> with bigger offsets. Yes you can do add from memory as two 3 byte opcodes but that burns a visible register,
> etc. RISC is stupid today, the way forward is more complex instructions to reduce code path lengths, etc.

It would not be the first time Intel extended an instruction set in a way that old programs could be translated at the level of assembly language. For full backwards compatibility, legacy operating modes could be replaced with firmware based emulation in some form.
< Previous Post in ThreadNext Post in Thread >
TopicPosted ByDate
The next Apple chipMaynard Handley2020/11/19 09:22 PM
  The next Apple chipanon22020/11/19 09:59 PM
    The next Apple chipMaynard Handley2020/11/20 10:45 AM
  The next Apple chipAndrei F2020/11/20 01:47 AM
    The next Apple chipdmcq2020/11/20 05:37 AM
      The next Apple chipAndrei F2020/11/20 07:31 AM
        The next Apple chipdmcq2020/11/20 10:57 AM
    The next Apple chipRonald Maas2020/11/20 09:54 AM
      The next Apple chipAnon2020/11/20 12:30 PM
        The next Apple chipWes Felter2020/11/22 09:50 PM
    The next Apple chipMaynard Handley2020/11/20 10:46 AM
    The next Apple chipJan Vlietinck2020/11/21 06:14 AM
      The next Apple chipDoug S2020/11/21 09:34 AM
  The next Apple chipDoug S2020/11/20 09:07 AM
    The next Apple chipMaynard Handley2020/11/20 10:51 AM
      The next Apple chipDoug S2020/11/20 12:07 PM
        The next Apple chipMaynard Handley2020/11/20 12:54 PM
          The next Apple chipDoug S2020/11/20 02:34 PM
  The next Apple chipRichard S2020/11/20 06:38 PM
  The next Apple chipDavid Hess2020/11/20 07:35 PM
    The next Apple chipBrett2020/11/20 09:56 PM
      The next Apple chipJames2020/11/21 08:18 AM
        The next Apple chipBrett2020/11/21 08:38 AM
      The next Apple chipDavid Hess2020/11/21 08:17 PM
      The next Apple chipHoward Chu2020/11/22 02:52 PM
        The next Apple chipBrett2020/11/25 06:27 PM
    The next Apple chipNaNon2020/11/21 04:01 AM
      The next Apple chipMaynard Handley2020/11/21 11:30 AM
      The next Apple chipDavid Hess2020/11/21 08:43 PM
        The next Apple chipJukka Larja2020/11/21 09:16 PM
          The next Apple chipDavid Hess2020/11/21 09:47 PM
          The next Apple chipDoug S2020/11/22 11:17 AM
            The next Apple chipJukka Larja2020/11/23 06:57 AM
        The next Apple chipMaynard Handley2020/11/22 11:12 AM
          The next Apple chipJukka Larja2020/11/23 07:13 AM
          The next Apple chipdmcq2020/11/23 09:18 AM
    The next Apple chipDoug S2020/11/21 09:53 AM
      The next Apple chipDavid Hess2020/11/21 08:40 PM
    The next Apple chipJacob Marley2020/11/21 12:40 PM
Reply to this Topic
Name:
Email:
Topic:
Body: No Text
How do you spell avocado?