Stepanov results with development gcc

[Mike Stump]

> Date: Fri, 08 Dec 2000 14:42:00 -0500
> From: David Edelsohn <dje@watson.ibm.com>

> 	Something seems strange with these results.  2.95.1 was perfect?
> 2.95.2 was perfect?

> 	My results for abstraction penalty using gcc -O2 on AIX are:

> 	gcc-2.95.2 = 1.23-1.24
> 	gcc-2.95.3 = 1.22-1.29

> 	I do not have a current development gcc to test.

I tried the compile from last night on a PIII, and got:

.[mrs@helium mrs]$ stepanov_v1p2  200000

test      absolute   additions      ratio with
number    time       per second     test0

 0        2.02sec    198.02M         1.00
 1        2.25sec    177.78M         1.11
 2        2.09sec    191.39M         1.03
 3        2.66sec    150.38M         1.32
 4        2.42sec    165.29M         1.20
 5        2.65sec    150.94M         1.31
 6        2.42sec    165.29M         1.20
 7        2.66sec    150.38M         1.32
 8        2.35sec    170.21M         1.16
 9        2.67sec    149.81M         1.32
10        2.36sec    169.49M         1.17
11        2.69sec    148.70M         1.33
12        2.70sec    148.15M         1.34
mean:     2.45sec    163.53M         1.21

Total absolute time: 31.94 sec

Abstraction Penalty: 1.21