From: William C. <wc...@re...> - 2014-08-20 14:02:03
|
On 08/19/2014 07:47 PM, Andi Kleen wrote: >> Notice that the broadwell, haswell, sandybridge, and westmere have multiple definitions of INST_RETIRED, one from arch_perfmon which has a zero unit mask and another one that has a non-zero unit masks. How is the INST_RETIRED event suppose to work for processors that support the Intel architected performance events? Always allow a unit mask of 0? Any suggestions n how the testsuite lib/op_events.exp should properly exercise INST_RETIRED event to test that things are working? > > Intel doesn't have a single INST_RETIRED event. There are multiple > variants, both for fixed counter and different unit masks for different > purposes including PEBS. Unit mask 0 with perf means use the fixed counter. > > So both are needed and useful. > > -Andi > Has it been manually checked that multiple events (sucah as INST_RETIRED) with the same name works? That seems like something that should be verified. Sounds like the testsuite should verify that the different variants of INST_RETIRED are available. -Will |