I found I had forgotten to unplug the 2nd monitor from the built in
DRAM port. With that port not in use the measured figures are ~50MB/s
instead of ~35MB/s. Here are the new runs from the 7100/66. If you
care I can send ones from a 6100/66. I hope to get some other examples
later. I did reduce the memory use to fit in 4MByte so it would be
easier to find machines that could run the benchmark. I could supply
numbers for the 7100/66 with lots of memory if desired.
Want numbers with vitrual memory turned on? :-) The past report
does apply if the DRAM based video port is in use.
m_m
Code Warrier's DR8:
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 170000, Offset = 0
Total memory required = 3.9 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Your clock granularity/precision appears to be 73 microseconds.
Each test below will take on the order of 34584 microseconds.
(= 473 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) RMS time Min time Max time
Assignment: 50.1170 0.0566 0.0543 0.0643
Scaling : 49.8023 0.0564 0.0546 0.0630
Summing : 55.4981 0.0769 0.0735 0.0857
SAXPYing : 55.3078 0.0769 0.0738 0.0862
Motorola's MCC v2.0:
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
-------------------------------------------------------------
Array size = 170000, Offset = 0
Total memory required = 3.9 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Your clock granularity/precision appears to be 78 microseconds.
Each test below will take on the order of 34684 microseconds.
(= 444 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) RMS time Min time Max time
Assignment: 50.7292 0.0569 0.0536 0.0632
Scaling : 50.3573 0.0568 0.0540 0.0630
Summing : 55.4002 0.0782 0.0736 0.0869
SAXPYing : 55.4446 0.0778 0.0736 0.0865
Symantec's MrC (from v8):
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
Total memory required = 3.9 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Your clock granularity/precision appears to be 77 microseconds.
Each test below will take on the order of 38782 microseconds.
(= 503 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) RMS time Min time Max time
Assignment: 51.4265 0.0557 0.0529 0.0608
Scaling : 50.7519 0.0569 0.0536 0.0622
Summing : 55.9057 0.0778 0.0730 0.0835
SAXPYing : 55.7735 0.0774 0.0732 0.0855
Symantec's sC (from v8):
-------------------------------------------------------------
This system uses 8 bytes per DOUBLE PRECISION word.
Total memory required = 3.9 MB.
Each test is run 10 times, but only
the *best* time for each is used.
-------------------------------------------------------------
Your clock granularity/precision appears to be 74 microseconds.
Each test below will take on the order of 34492 microseconds.
(= 466 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) RMS time Min time Max time
Assignment: 50.1346 0.0552 0.0543 0.0599
Scaling : 49.7695 0.0550 0.0547 0.0563
Summing : 55.6086 0.0742 0.0734 0.0773
SAXPYing : 55.4830 0.0745 0.0735 0.0762
This archive was generated by hypermail 2b29 : Tue Apr 18 2000 - 05:23:05 CDT