[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [MiNT] MiNT lib 55



Johan Klockars <rand@cd.chalmers.se> writes:

|> I'd assume that m68020-60 generates code that's relatively good for the
|> '020/'030 and reasonably so for the '060 (it probably doesn't take
|> advantage of the quick integer multiply, since that would hurt the older
|> processors), but somewhat worse for the '040.

-m68020-60 means: generate code that runs on all '020/30/40/60.  It does
especially mean, don't use the new insns that were introduced on '040/60,
or that must be emulated.  The latter means that it is somewhat
pessimising for '020/30.

-m68020-40 is similar, except it does not take the '060 into account.

|> There are actually a great many differences that are important when
|> it comes to optimization. Sure, the available user mode instructions
|> are more or less the same (I believe the '020 is the only one with
|> CALLM, and some things were removed in the '060), but the timings and
|> the cache behaviour vary significantly. And, after all, the timings are
|> usually what's interesting when you're talking about optimization.

gcc on m68k does not do any insn scheduling, so the generated code is
effectively the same for all variants from '020 to '060, except for the
differences outlined above.

Andreas.

-- 
Andreas Schwab                                  "And now for something
SuSE Labs                                        completely different."
Andreas.Schwab@suse.de
SuSE GmbH, Schanzäckerstr. 10, D-90443 Nürnberg