One example where gcc 2.1 is worse than 1.37.1

Article View: gnu.gcc.help

Article #70

#70

From: Ajay Shah
Date: Tue, 07 Apr 1992 00:48

46 lines
1710 bytes

I have a problem here.
In short: on 100 runs, gcc 1.37.1 is 7.0 seconds on average,
gcc 2.1 is 8.5 seconds on average.

Performance of executable produced by gcc 1.37.1:
-------------------------------------------------

number of runs  = 100
sum             = 703.8  
mean            = 7.038  
variance        = 0.0587434
std. deviation  = 0.24237
minimum         = 6.8    
maximum         = 7.9    

Performance of executable produced by gcc 2.1
---------------------------------------------

number of runs  = 100
sum             = 845.5  
mean            = 8.455  
variance        = 0.0936111
std. deviation  = 0.305959
minimum         = 8.1    
maximum         = 9.4    

Info about benchmarking
-----------------------

Flags for old: -O
Flags for new: -static -O2 -funroll-loops

Program: ftp.uu.net: usenet/comp.sources.reviewed/volume01/ols

Test case: the ols distribution contains a file named 'data.1k'.
        I said
                cat `repeat 10 echo -n 'data.1k '` > data.10k
        Then I timed a given executable by saying
                repeat 100 ols data.1k

This computer is:
OS/MP 4.1A.1 Export(S5GENERIC/root)#0: Mon Sep 30 16:11:19 1991
System type is Solbourne Series5e/900 with 128 MB of memory.
-- 

Ajay Shah, (213)749-8133, ajayshah@usc.edu

Technical Details

Message-ID: <ku1sa7INNnl8@alhena.usc.edu>

Path: arc1-ca.pugleaf.net!sparky!uunet!usc!news

Show Full Headers

Complete Article Headers

Path: arc1-ca.pugleaf.net!sparky!uunet!usc!news
From: ajayshah@alhena.usc.edu (Ajay Shah)
Newsgroups: gnu.gcc.help
Subject: One example where gcc 2.1 is worse than 1.37.1
Date: 6 Apr 1992 17:48:07 -0700
Organization: University of Southern California, Los Angeles, CA
Lines: 46
Sender: ajayshah@alhena.usc.edu (Ajay Shah)
Message-ID: <ku1sa7INNnl8@alhena.usc.edu>
NNTP-Posting-Host: alhena.usc.edu