perf events: Add generic front-end and back-end stalled cycle event definitions
Add two generic hardware events: front-end and back-end stalled cycles. These events measure conditions when the CPU is executing code but its capabilities are not fully utilized. Understanding such situations and analyzing them is an important sub-task of code optimization workflows. Both events limit performance: most front end stalls tend to be caused by branch misprediction or instruction fetch cachemisses, backend stalls can be caused by various resource shortages or inefficient instruction scheduling. Front-end stalls are the more important ones: code cannot run fast if the instruction stream is not being kept up. An over-utilized back-end can cause front-end stalls and thus has to be kept an eye on as well. The exact composition is very program logic and instruction mix dependent. We use the terms 'stall', 'front-end' and 'back-end' loosely and try to use the best available events from specific CPUs that approximate these concepts. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-7y40wib8n000io7hjpn1dsrm@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
parent
ede7029004
commit
8f62242246
|
@ -1414,7 +1414,7 @@ static __init int intel_pmu_init(void)
|
||||||
x86_pmu.extra_regs = intel_nehalem_extra_regs;
|
x86_pmu.extra_regs = intel_nehalem_extra_regs;
|
||||||
|
|
||||||
/* Install the stalled-cycles event: UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
|
/* Install the stalled-cycles event: UOPS_EXECUTED.CORE_ACTIVE_CYCLES,c=1,i=1 */
|
||||||
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES] = 0x1803fb1;
|
intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x1803fb1;
|
||||||
|
|
||||||
if (ebx & 0x40) {
|
if (ebx & 0x40) {
|
||||||
/*
|
/*
|
||||||
|
|
|
@ -52,7 +52,8 @@ enum perf_hw_id {
|
||||||
PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4,
|
PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4,
|
||||||
PERF_COUNT_HW_BRANCH_MISSES = 5,
|
PERF_COUNT_HW_BRANCH_MISSES = 5,
|
||||||
PERF_COUNT_HW_BUS_CYCLES = 6,
|
PERF_COUNT_HW_BUS_CYCLES = 6,
|
||||||
PERF_COUNT_HW_STALLED_CYCLES = 7,
|
PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7,
|
||||||
|
PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8,
|
||||||
|
|
||||||
PERF_COUNT_HW_MAX, /* non-ABI */
|
PERF_COUNT_HW_MAX, /* non-ABI */
|
||||||
};
|
};
|
||||||
|
|
Loading…
Reference in New Issue