[cc65] Some 2.13 Benchmarks

From: Egan Ford <egan1sense.net>
Date: 2009-10-18 21:40:25
Here are the results of a few tests:

                        Apple //e
          --------------------------------------
          INT    FP     MAF    Aztec  cc65  cc65
Benchmark  BASIC  BASIC  Forth  C 3.2  2.12  2.13
=========  =====  =====  =====  =====  ====  ====
pi (atan)  ~40hr          1496   2180  1764  1514
e (euler)                         670   559   501
NQ struct    N/A    N/A     16   2.98  1.93  1.33
NQ goto       37     55    N/A   2.93  1.54  1.32
Savage       N/A    470    N/A   2664   N/A   N/A

NOTE:

1.  All times reported in seconds unless otherwise noted.
2.  N/A = Not Applicable.  Environment does not natively support this benchmark.

If you have problems with the formatting, use this URL:
http://sense.net/~egan/perf2e.txt

Observations:

1.  The poor FP performance with Aztec C may be due to higher precision.
2.  2.13 is measurably faster than 2.12.
3.  NQ struct/goto with 2.13 perform the same.  Optimization improvements.
----------------------------------------------------------------------
To unsubscribe from the list send mail to majordomo@musoftware.de with
the string "unsubscribe cc65" in the body(!) of the mail.
Received on Sun Oct 18 21:40:49 2009

This archive was generated by hypermail 2.1.8 : 2009-10-18 21:40:51 CEST