The stream_l binary was compiled using g++ (egcs-2.91.66)
	 g++ -O3 -march=pentiumpro stream_l.cpp -funroll-loops 
under Red Hat linux 2.2.9




Results on a 500 MHz Pentium III/Xeon system are typically:

-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 999936, Offset = 0
Total memory required = 24.9 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Function      Rate (MB/s)   RMS time     Min time     Max time
Copy:         325.1209       0.0495       0.0492       0.0497
Scale:        333.0638       0.0481       0.0480       0.0482
Add:          348.6444       0.0689       0.0688       0.0690
Triad:        354.0417       0.0679       0.0678       0.0681
-------------------------------------------------------------

