Re: [perfmon2] Nehalem and PFMLIB_NHM_UMASK_NCOMBO

2010-01-15 Thread Dan Terpstra
Stephane - How was this confirmed? Was it in documentation or by example? We can burn two counters to implement this, but I'd really rather not :( - d > -Original Message- > From: Stephane Eranian [mailto:eran...@google.com] > Sent: Friday, January 15, 2010 5:22 PM > To: Dan Terpstra > Cc:

Re: [perfmon2] Nehalem and PFMLIB_NHM_UMASK_NCOMBO

2010-01-15 Thread Stephane Eranian
Dan, I confirm that you cannot combine unit mask neither FP_COMP_OS_EXE or SSEX_UOPS_RETIRED. Thus we have to maintain the restriction. You have to use two counters if you want to measure that in a single run. On Fri, Jan 15, 2010 at 5:10 PM, Stephane Eranian wrote: > On Fri, Jan 15, 2010 at

Re: [perfmon2] Nehalem and PFMLIB_NHM_UMASK_NCOMBO

2010-01-15 Thread Stephane Eranian
On Fri, Jan 15, 2010 at 1:27 PM, Dan Terpstra wrote: > Stephane - > >> -Original Message- >> From: Stephane Eranian [mailto:eran...@google.com] >> Sent: Friday, January 15, 2010 2:42 AM >> To: Dan Terpstra >> Cc: perfmon2-devel@lists.sourceforge.net; jag...@eecs.utk.edu >> Subject: Re: Neh

Re: [perfmon2] Nehalem and PFMLIB_NHM_UMASK_NCOMBO

2010-01-15 Thread Dan Terpstra
Stephane - > -Original Message- > From: Stephane Eranian [mailto:eran...@google.com] > Sent: Friday, January 15, 2010 2:42 AM > To: Dan Terpstra > Cc: perfmon2-devel@lists.sourceforge.net; jag...@eecs.utk.edu > Subject: Re: Nehalem and PFMLIB_NHM_UMASK_NCOMBO > > On Fri, Jan 15, 2010 at 2

Re: [perfmon2] Nehalem and PFMLIB_NHM_UMASK_NCOMBO

2010-01-14 Thread Stephane Eranian
On Fri, Jan 15, 2010 at 2:38 AM, Dan Terpstra wrote: > Yes. It actually did count without error and produce a result of 0. > We didn't exactly track the error handling to see if an error was returned > that PAPI didn't process (always possible :)), but no obvious errors > appeared. Our original as

Re: [perfmon2] Nehalem and PFMLIB_NHM_UMASK_NCOMBO

2010-01-14 Thread Dan Terpstra
Yes. It actually did count without error and produce a result of 0. We didn't exactly track the error handling to see if an error was returned that PAPI didn't process (always possible :)), but no obvious errors appeared. Our original assumption was that the second unit mask, SSE_SINGLE_PRECISION,

Re: [perfmon2] Nehalem and PFMLIB_NHM_UMASK_NCOMBO

2010-01-14 Thread Stephane Eranian
Dan, I made that change recently because I learned that on NHM, not all unit masks can be combined. In fact, it seems only unit masks of events counting cycles apparently can. But it may be that FP_COMP is an exception I missed. But something looks strange to me in your results. If you pass 2 un