[m-dev.] preliminary MLDS performance comparisons

[Fergus Henderson]

On 24-May-2000, Fergus Henderson <fjh at cs.mu.OZ.AU> wrote:
> Some more benchmark results, this time with `-O4 --opt-space' for mmc,
> (but still `-O2' for gcc):
> 
> Compiled with         Input file     Options	Slowdown	user time (s)
> -O4 --opt-space       table_gen.m    -C -O5	   		24.1
> -O4 --opt-space -H    table_gen.m    -C -O5	13%   		21.4
> -O4 --opt-space       table_gen.m    -C -O0	   		9.0
> -O4 --opt-space -H    table_gen.m    -C -O0	11%   		9.9

Sorry, that table may have been confusing -- I got the numbers in the
"user time" column the wrong way around.  It should be

Compiled with         Input file     Options	Slowdown	user time (s)
-O4 --opt-space       table_gen.m    -C -O5	   		21.4
-O4 --opt-space -H    table_gen.m    -C -O5	13%   		24.1
-O4 --opt-space       table_gen.m    -C -O0	   		9.9
-O4 --opt-space -H    table_gen.m    -C -O0	11%   		9.0

In short, the MLDS back-end still generates code that is a bit slower than
that generated by the LLDS back-end.

-- 
Fergus Henderson <fjh at cs.mu.oz.au>  |  "I have always known that the pursuit
WWW: <http://www.cs.mu.oz.au/~fjh>  |  of excellence is a lethal habit"
PGP: finger fjh at 128.250.37.3        |     -- the last words of T. S. Garp.
--------------------------------------------------------------------------
mercury-developers mailing list
Post messages to:       mercury-developers at cs.mu.oz.au
Administrative Queries: owner-mercury-developers at cs.mu.oz.au
Subscriptions:          mercury-developers-request at cs.mu.oz.au
--------------------------------------------------------------------------