My next step was to do some benchmarks under Linux to check the RAM performance. I used the Stream test against Pegasos and Sam440ep board.

EFIKA Linux 2.6.19

-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 2000000, Offset = 0
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Printing one line per active thread....
-------------------------------------------------------------
Your clock granularity/precision appears to be 2 microseconds.
Each test below will take on the order of 183141 microseconds.
(= 91570 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function----Rate (MB/s)---Avg time----Min time----Max time
Copy:--------192.4569------0.1978------0.1663------0.3896
Scale:--------187.5988------0.1855------0.1706------0.2254
Add:----------195.1688------0.2569------0.2459------0.2920
Triad:---------188.3092------0.3100------0.2549------0.4959
-------------------------------------------------------------
Solution Validates
-------------------------------------------------------------

Pegasos II G4/1GHz Linux 2.6.17

-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 2000000, Offset = 0
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Printing one line per active thread....
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 90864 microseconds.
(= 90864 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function----Rate (MB/s)---Avg time----Min time----Max time
Copy:--------376.0548------0.0869------0.0851------0.0907
Scale:--------361.1246------0.0907------0.0886------0.0929
Add:----------359.3918------0.1359------0.1336------0.1376
Triad:---------361.1680------0.1357------0.1329------0.1394
-------------------------------------------------------------
Solution Validates
-------------------------------------------------------------

Pegasos II G3/600MHz

-------------------------------------------------------------
STREAM version $Revision: 5.6 $
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 2000000, Offset = 0
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Printing one line per active thread....
-------------------------------------------------------------
Your clock granularity/precision appears to be 2 microseconds.
Each test below will take on the order of 251755 microseconds.
(= 125877 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function----Rate (MB/s)---Avg time---Min time---Max time
Copy:--------132.6981------0.2416-----0.2411-----0.2421
Scale:-------112.7054------0.2849-----0.2839-----0.2859
Add:---------118.6606------0.4054-----0.4045-----0.4063
Triad:-------118.7202------0.4056-----0.4043-----0.4065
-------------------------------------------------------------
Solution Validates
-------------------------------------------------------------


AMCC 440EP 533 Mhz Evaluation Board Linux 2.6.18

-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 2000000, Offset = 0
Total memory required = 45.8 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Printing one line per active thread....
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 112887 microseconds.
(= 112887 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function----Rate (MB/s)---Avg time----Min time----Max time
Copy:--------262.6503------0.1221------0.1218------0.1223
Scale:--------245.8928------0.1302------0.1301------0.1303
Add:----------253.5979------0.1893------0.1893------0.1893
Triad:---------251.2734------0.1911------0.1910------0.1912
-------------------------------------------------------------
Solution Validates
-------------------------------------------------------------

For further tests, Application optimizations and guides I am waiting now for a MorphOS Release.