home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!cs.utexas.edu!sun-barr!news2me.EBay.Sun.COM!exodus.Eng.Sun.COM!flayout.Eng.Sun.COM!tremblay
- From: tremblay@flayout.Eng.Sun.COM (Marc Tremblay)
- Newsgroups: comp.arch
- Subject: Re: RISC goes CISC?
- Date: 7 Nov 1992 18:55:11 GMT
- Organization: Sun Microsystems, Mt. View, Ca.
- Lines: 25
- Message-ID: <lfo48fINNsvc@exodus.Eng.Sun.COM>
- References: <1992Nov6.092012.19239@rhein-main.de>
- NNTP-Posting-Host: flayout
-
- In article <1992Nov6.092012.19239@rhein-main.de> vhs@rhein-main.de writes:
- >Under this assumption, how does e.g. SuperSPARC fit this principle? As far
- >as I know the processor does a lot of cross-checking between pipelines,
- >squashing instructions depending on non-trivial conditions, etc. Is that done
- >just to maintain compatibility with previous implementations?
- >Could, theoretically, the most recent compilers take care of this
- >at compile-time, thus eliminating the need for run time
- >checking (again theoretically since people want to run their old code).
-
- Considering that Sun has the largest base of applications running on
- workstations, it is very important to improve the performance of existing
- binaries running on SuperSPARC without having to re-compile the source.
- The increase in performance for existing binary is around 2x-3x for
- SuperSPARC running at the same clock frequency (vs. Cypress 40MHz SPARC).
-
- Notice that the fact that SuperSPARC takes care of all the interlocks between
- instructions does not mean that the compiler cannot help improve the
- performance. SuperSPARC is an in-order processor which means that
- incoming instructions do not bypass older instructions even if older
- instructions are stalled. Thus it is important for new compilers
- to perform scheduling based on instruction latencies and on the
- functional units available.
-
- - Marc Tremblay.
- Sun Microsystems.
-