Bug 742508

Since RHEL 6.2 External Beta has begun, and this bug remains
unresolved, it has been rejected as it is not proposed as
exception or blocker.

Red Hat invites you to ask your support representative to
propose this request, if appropriate and relevant, in the
next release of Red Hat Enterprise Linux.

This isn't a regression.  The papi-4.1.0 version also has the same intermittent failure.

Ran the following:

 ./ctests/sdsc-mpx; until test $? != 0 ; do ./ctests/sdsc-mpx; done

Eventually got the following failure:

Accuracy check of multiplexing routines.
Comparing a multiplex measurement with separate measurements.

Added PAPI_FP_INS
Added PAPI_TOT_INS
Added PAPI_TOT_CYC
Added PAPI_BR_INS
Added PAPI_SR_INS
Added PAPI_LD_INS
Added PAPI_TOT_IIS
Added PAPI_BR_MSP
Using 8 events

Modified iteration count to 20000000

PAPI reference measurements:
     FP instructions = 440000015
     Instr completed = 1460640287
        Total cycles = 3564032777
            Branches = 20114382
              Stores = 78416201
               Loads = 460106798
        Instr issued = 2358912392
  Cond br mspredictd = 5193

PAPI multiplexed measurements:
     FP instructions = 439949677
     Instr completed = 1460442005
        Total cycles = 3341776706
            Branches = 20107715
              Stores = 240081273
               Loads = 460141265
        Instr issued = 2100475688
  Cond br mspredictd = 5481

Relative accuracy:
   Event 01   Event 02   Event 03   Event 04   Event 05   Event 06   Event 07   Event 08
  0.000114   0.000136     0.0665   0.000332      0.673   7.49e-05      0.123     0.0525 

sdsc.c                                   FAILED
Line # 66
Error: Values outside threshold

PAPI reference measurements:
     FP instructions = 440000017
     Instr completed = 1460544480
        Total cycles = 3563427987
            Branches = 20096939
              Stores = 240064316
               Loads = 460105957
        Instr issued = 2358847685
  Cond br mspredictd = 5284

Relative accuracy:
   Event 01   Event 02   Event 03   Event 04   Event 05   Event 06   Event 07   Event 08
  0.000114   7.02e-05     0.0663   0.000536   7.06e-05   7.67e-05      0.123     0.0359

OK, removing the Regression keyword andd blocker flag, and proposing for 6.3. It could possibly go in 6.2 with the remaining regression, but I'll leave that up to you.

This request was not resolved in time for the current release.
Red Hat invites you to ask your support representative to
propose this request, if still desired, for consideration in
the next release of Red Hat Enterprise Linux.

This is in the testsuite and is rarely triggered.