Excellent catch. I'll try to have it ready to discuss Thursday so we can get it in for reading by the Monday 2/15 deadline. Thanks! Kathryn _________________________________________________________________ Kathryn Mohror, [email protected], http://scalability.llnl.gov/ Scalability Team @ Lawrence Livermore National Laboratory, Livermore, CA, USA
-----Original Message----- From: mpiwg-tools [mailto:[email protected]] On Behalf Of Schulz, Martin Sent: Friday, February 5, 2016 5:24 PM To: [email protected] Subject: Re: [mpiwg-tools] MPI_T question about cvar value guarantees
Yes, I agree, we should probably submit an errata for this text.
Martin
On 2/5/16, 4:50 PM, "mpiwg-tools on behalf of Jeff Squyres (jsquyres)" <[email protected] on behalf of [email protected]> wrote:
On Feb 5, 2016, at 4:26 PM, Schulz, Martin <[email protected]> wrote:
That¹s a good question and I don¹t think we say - my original intent when writing the document (based on my personal model that I had in my head for this) was to provide no guarantees once MPI_T gets uninitialized, so in this case both versions would be OK. In fact, it could be even worse - what happens in case 1 if the component is not reloaded? Do you still have access to the variable at all? This is probably more likely if the MPI_T only block is after MPI_Finalize (since this would unload components), but the principle is the same.
For the discovery/query routines we state that the numbering is not allowed to change between ³runs², which may have been the wrong thing to say - it probably should say ³while MPI_T is initialized². In this case, there would really not be any guarantees at all. If you wanted guarantees, you would have to keep MPI_T initialized.
That sounds fine to me. I think that this is worth an errata.
-- Jeff Squyres [email protected] For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
_______________________________________________ mpiwg-tools mailing list [email protected] http://secure-web.cisco.com/1YQzVZ9p1gLekoVYv9VGQ_- CNEYsPlQQtkva9wBeUEu V5I NONI4Nm-vTVCCxm4xjArNq97pldPUVCOWShL7- hhjDh_0uYjZ9MYdA28tvg1pIvOl8shxbR xZh 3FbapA2wu5Q99HsmgPLjCxBBGktJijRvb9BIcaGKHBzMAFlDIX_mz5BZNMo2JR mvTX1neOf byF PTV_rVef2O7blagdgDD7YOeu54XlV9ImkS8qcvLeGLcxfmzeu1pPNMN4IoiiAao7I z2Xh9y 7MM dtqOZi6XcylO9kxyregmJifR44SqEhZukURI8THsglPLQvSmkYM0iVJuc9ZlEXl9nru au-A FKa VH8WgAzBQkDzVeG2StEuxo/http%3A%2F%2Flists.mpi- forum.org%2Fmailman%2Flis tin fo.cgi%2Fmpiwg-tools
_______________________________________________ mpiwg-tools mailing list [email protected] http://secure- web.cisco.com/1RsFhgnyhJqbl3e3u1W6tmBFwlbZcXXlimgtJ1E7tDwUt3VZ96biQz 4_-IVFynNm- cO3cyxVRGHEZ2_OySkm1e63TxATLQaJLPPZByzyLF0sq1VN11SXNfPvyvXsOkMPN VB9z6XPPa25CTesfw0HpSrJsg-ThVxy3IIvUbR_rQHOLuMdmbS- ffFmqsw9A7FD1uJMxPWMB7HMyflXJpSCgKCNJ5myWylldNAnIALjyjtsJnn7KTWv puf3XPhClSCzvRwur9iQEZJmC7goyLuHzB01moGDZ_0AWo1GNaMuYSwkfjZlrsRY nyqTiQs3CDyL2H4oup0366qOpXPHY_oZGNJ2AVj4UMvKx65oMXzEP9Vk/http%3 A%2F%2Flists.mpi-forum.org%2Fmailman%2Flistinfo.cgi%2Fmpiwg-tools