On Sat, Dec 29, 2001 at 07:39:33PM +0100, Thierry Godefroy wrote: > On Sat, 29 Dec 2001 19:13:48 +0100 (CET), [EMAIL PROTECTED] wrote: > > > Hi! > > > > I have measured the time it takes to boot Linux on Q40 (starting at the > > penguin): > > > > Kernel 2.2.17 : 62 sec > > Kernel 2.4.17 : 36 sec > > > > I used the same installation, of course. > > Thierry, your kernel seems to be mega fast. > > Well, Linux v2.4 is known (and designed) to be faster than v2.2, but > beyong that, I used the 68060 optimisation flag (-m68060) to compile > the Q60 kernel and the -m68040 flag for the Q40 kernel: the proper > flag can be selected when configuring the kernel (make menuconfig > or make xconfig), by selecting ONLY ONE of the 68020 / 68030 / 68040 / > 68060 support options.
It alwasy worth doing that. > If you select two of them (e.g. 68040 & 68060 > for the Qx0), then no optimization flag is used at all (!) for the > compilation (thus defaulting to a 68000-compatible code and also > probably avoiding any 68000 instruction that would not work on higher > processor, e.g MOVE.W SR,Dn which is priviledged on 68020+). not correct, we use gcc configured for linux-m68k which has DEFAULT_TARGET set to 68020. So the effect of actually using -m68040 will be next to zero for non-FPU code. The reason why selecting a single CPU variant makes the kernel faster is that the differences between the m68k CPU's wrt cache, MMU, FPU and exception handling are rather big, so each CPU needs its own cache and MMU handling code. This code is mostly inlined and if support for more CPU variants is compiled in the distinction has to happen at runtime. It has also significant impact on code size. Bye Richard
