On 2015-09-18 7:06 AM, Pontus Pihlgren wrote:
On Fri, Sep 18, 2015 at 06:58:24AM -0400, Mouse wrote:
You have a lot of byte code virtual machines out there.
Such as every x86 processor since, what, the Pentium? They're all RISC
cores (designed for and) running an x86 emulator.
I've been told this more than a few times and read it in various places.
It always make me wonder, could we not allow a mode in modern Intel
processors that lets us bypass the x86 code emulation/translation and
run "directly on the metal" (if there were such a thing).
The purpose, of course, would be to gain performance. Certainly this
would already have been done if there was any significant gain to be
had?
Imho, there are some pretty big negatives to going this route that would
have to be weighed against possible performance difference:
Intel would be extremely reluctant to expose trade secrets, or have
customers tightly coupled to implementation details. It would impact
everything from product development process to roadmap simply to have a
customer using a non-x86 programmer model. The decoupling implied by an
instruction set/architecture has always been of great advantage to
chipmakers, as much as it is to end users.
Don't neglect the massive cost in supporting a new ISA or partial
compilers, in tools, design, testing, porting, etc.
I think you answered your own question - the cost/benefit rules it out :)
--Toby
/P
