Re: JavaMemoryModel: Is reordering of dependent reads on Alpha actually possible?

From: Keith Randall (randall@src.dec.com)
Date: Fri Feb 25 2000 - 14:03:17 EST


> We have written a short program to try to duplicate such a result, and
> run it on an AlphaServer 2100/A (this runs 4 21064A processors). This
> program is available at http://www.cs.umd.edu/users/jmanson/java.html.
>
> We tried it with both dependent and independent reads, and we have seen
> no results which would indicate that this read of a stale cache value /
> instruction reordering is occurring. Does anyone know of or have access
> to a SMP Alpha that might encounter these difficulties?

   The reordering does happen with 21164 and 21264 Alphas.

Alpha 21164
>testWeak
Bad things are happening 6062 6063
Bad things are happening 7575 7576
Bad things are happening 8441 8442
Bad things are happening 9962 9963
Bad things are happening 11308 11309
Bad things are happening 14191 14192
Bad things are happening 15825 15826
Bad things are happening 16662 16663
Bad things are happening 23632 23633
Bad things are happening 26287 26288
...

Alpha 21264
>testWeak
Bad things are happening 1396 1397
Bad things are happening 2535 2536
Bad things are happening 2930 2931
Bad things are happening 3123 3124
Bad things are happening 3346 3347
Bad things are happening 3644 3645
Bad things are happening 4011 4012
Bad things are happening 4206 4207
Bad things are happening 5329 5330
Bad things are happening 5875 5876
Bad things are happening 6228 6229
Bad things are happening 6642 6643
Bad things are happening 7875 7876
...

                                           -Keith
-------------------------------
JavaMemoryModel mailing list - http://www.cs.umd.edu/~pugh/java/memoryModel



This archive was generated by hypermail 2b29 : Thu Oct 13 2005 - 07:00:24 EDT