Front page | perl.perl5.porters |
Postings from January 2001
Alan Burlison <Alan.Burlison@uk.sun.com> writes: >Tim Bunce wrote: > >> > That is a 30% performance improvement, without changing a single line of >> > code. This is the main reason I intend ditching siglongjmp when I >> > integrate 5.6.1 into Solaris. >> >> But that 30% is a mix of the effects of -Ud_sigsetjmp and the effects >> of optimize='-xO4 -xdepend'. How much does performance boost does each >> give by itself? > >the setjmp change gives about 18%, the optimiser gives about 12%. A bit >more can be squeezed out if you use the perl malloc, but it is broken >above 2Gb, so I don't use it. How do I get a measure of what sigsetjmp() is costing. A very simplistic test gave With sigsetjmp(): All tests successful. u=0.9 s=0.85 cu=72.37 cs=34.45 scripts=275 tests=21137 With setjmp(): All tests successful. u=1 s=0.75 cu=74.35 cs=35.23 scripts=275 tests=21137 Which is counter-inutitive. This is SunOS fatima 5.7 Generic_106541-04 sun4u sparc SUNW,Ultra-Enterprise (Wall clock times are useless as it is a shared machine.) -- Nick Ing-Simmons <nik@tiuk.ti.com> Via, but not speaking for: Texas Instruments Ltd.Thread Previous | Thread Next