(Vector * Vector) Multiplication Timing Results:
 
Non-optimized builds (SRT_QUAL = default) Optimized builds (SRT_QUAL = maxopt)
5-element Vectors 6-element Vectors 5-element Vectors 6-element Vectors
LinearAlgebra
ColumnVector * RowVector
[tsnmul08]
Min: 4.7 secs (4.7 µsecs)
Max: 4.79 secs (4.79 µsecs)
Min: 6.01 secs (6.12 µsecs)
Max: 6.01 secs (6.12 µsecs)
Min: 4.93 secs (4.93 µsecs)
Max: 5.1 secs (5.1 µsecs)
Min: 6.3 secs (6.3 µsecs)
Max: 6.33 secs (6.33 ``µsecs)
CLHEP
HepVector * HepVector (*)
[tsnmul09]
Min: 3.49 secs (3.49 µsecs)
Max: 3.56 secs (3.56 µsecs)
Min: 5.33 secs (5.33 µsecs)
Max: 5.45 secs (5.45 µsecs)
Min: 3.48 secs (3.48 µsecs)
Max: 3.51 secs (3.51 µsecs)
Min: 5.36 secs (5.36 µsecs)
Max: 5.56 secs (5.56 µsecs)

All timings are based on 1,000,000 multiplications.
The first number is the time for all the inversions while the time in parenthesis is the time for 1 multiplication.
The string in the bracket is the name of the test module build for the particular test.
When the results say "Non-Optimized builds," then all the libraries and the test module were build with the "SRT_QUAL" variable having the "default" value.
When the results say "Optimized builds," then all the libraries and the test module were build with the "SRT_QUAL" variable having the "maxopt" value.

(*) In order to perform vector*vector in CLHEP, we have to transpose one of the two vectors. However, when we transpose a HepVector we get back a HepMatrix. Thus, we end up
performing vector*matrix multiplication and not vector*vector.

Vectors used in the tests:

LinearAlgebra:
5-element ColumnVector:
          2
          4
          6
          8
        10
5-element RowVector:
         2               4               6               8              10
6-element ColumnVector:
          2
          4
          6
          8
        10
        12
6-element RowVector:
         2               4               6               8              10              12

CLHEP:
5-element vector:
          2
          4
          6
          8
        10
1x5 matrix:
            2             4             6             8            10
6-element vector:
          2
          4
          6
          8
        10
        12
1x6 matrix:
            2             4             6             8            10            12
 

Testing system specs:
CPU: 500 MHz PentiumIII (Katmai)
Memory: 128MB SDRAM
Cache: 512KB
Hard Disk: IBM 13677MB
Video Card: 16MB Diamond Viper TNT 1.95E

OS: Fermi Linux Release 6.1.1 (Strange)
Kernel: 2.2.16-3 on an i686
X-Server: XFree86 Version 11.0 Release 3360

Tests were compiled and build using GCC 3.0.1

Nick Macks