Re: upc_all_reduce behaviour

Date view Thread view Subject view Author view Attachment view

From: Nikita Andreev (lestat_at_kemsu.ru)
Date: Sat Apr 17 2010 - 03:08:32 PDT

  • Next message: Paul H. Hargrove: "Re: upc_all_reduce behaviour" 
    > collectives as if passed UPC_IN_ALLSYNC|UPC_OUT_ALLSYNC.  This is true of 
> ANY collective - the sync flags BOUNDS when a thread may exit but does not 
> DEFINE it.

That's perfect remark. Didn't think about it in the first place.

> If, for instance, the prefix reduction is computed by a Gather of all the 
> values to Thread 0, which then does all the arithmetic and sends out the 
> results, then one would expect Thread 0 to leave LAST rather than first.

Paul, could you please point me to anyone who is particularly familiar with 
current Berkeley implementation of UPC collectives?

Nikita
  • Next message: Paul H. Hargrove: "Re: upc_all_reduce behaviour"
    Date view Thread view Subject view Author view Attachment view