Thread View: comp.hypercube
1 messages
1 total messages
Started by Wen-King
Tue, 14 Jul 1987 12:24
Re: Question on hypercube routing (channel usage)
Author: Wen-King
Date: Tue, 14 Jul 1987 12:24
Date: Tue, 14 Jul 1987 12:24
29 lines
1829 bytes
1829 bytes
In article <278@hubcap.UUCP> pase%oregon-grad.csnet@RELAY.CS.NET (Douglas M. Pase) writes:
> 000 -> 001
< 000 -> 010
> 000 -> 001 -> 011
... etc
<The channel between nodes 0 and 1 is used in four different cases, between 0
>and 2 in two cases, and 0 and 4 in only one case. This exponential piling
<of messages into the lower numbered channels (which is compounded if one
>considers similar usage of channels by other nodes as well) means that in
<heavy message traffic there will be a lot of contention for the lower numbered
>channels where the channels corresponding to the higher bits go unused.
000 -(0)-> 001
000 -(1)-> 010
000 -(0)-> 001 -(1)-> 011
000 -(2)-> 100
000 -(0)-> 001 -(2)-> 101
000 -(1)-> 010 -(2)-> 110
000 -(0)-> 001 -(1)-> 011 -(2)-> 111
On the countrary, I counted that channels 0, 1, and 2 are each used
exactly 4 times, though they are not all channels coming out of node
0. The composite usage, assuming all nodes in the cube are doing
similar things, will be the same for all of the individual channels.
+--------------------------------------------------------------------------+
| Wen-King Su wen-king@vlsi.caltech.edu Caltech Corp of Cosmic Engineers |
+--------------------------------------------------------------------------+
Thread Navigation
This is a paginated view of messages in the thread with full content displayed inline.
Messages are displayed in chronological order, with the original post highlighted in green.
Use pagination controls to navigate through all messages in large threads.
Back to All Threads