YEEJJ@NUSDISCS.BITNET (07/31/90)
I have an Inmos B008 with a T800-20 as the root transputer. The host is a 386/25 with SCSI disk. I compiled the program by Vandana on the 3L parallel C. Since the PC has a turbo switch (20Mhz/25Mhz), I ran the test several times on each mode and used a software switch to change the memory between zeo and one wait state. Below are the results : 0 wait state 1 wait state 25 Mhz 7.90 s 8.81 s 20 Mhz 9.22 s 10.28 s The results are much worse than what Ken Koontz reported for his B008 with a B404-3 root and on Logical Systems C. Is the problem with 3L parallel C, or with SCSI disk? Hoping to hear results from others. I would like to know people with experiences on 3L C too. Jenn-Jong, Yee National University of Singapore email : YeeJJ@nusdiscs > YEE JEUU JONG (YEEJJ@NUSDISCS.BITNET) > National University of Singapore > Department of Information Systems and Computer Science