forked from OSchip/llvm-project
[llvm-exegesis] Delegate the decision of cycle counter name to the target
Currently the cycle counter is taken from the subtarget schedule model, which isn't any use if the subtarget doesn't have one. Delegate the decision to the target benchmark runner, as it may know better what to do in that case, with the default being the current behaviour. Differential Revision: https://reviews.llvm.org/D48779 llvm-svn: 336099
This commit is contained in:
parent
4ebba909a2
commit
8fc5ec78d5
|
@ -94,6 +94,18 @@ LatencyBenchmarkRunner::generatePrototype(unsigned Opcode) const {
|
|||
return generateTwoInstructionPrototype(Instr);
|
||||
}
|
||||
|
||||
const char *LatencyBenchmarkRunner::getCounterName() const {
|
||||
if (!State.getSubtargetInfo().getSchedModel().hasExtraProcessorInfo())
|
||||
llvm::report_fatal_error("sched model is missing extra processor info!");
|
||||
const char *CounterName = State.getSubtargetInfo()
|
||||
.getSchedModel()
|
||||
.getExtraProcessorInfo()
|
||||
.PfmCounters.CycleCounter;
|
||||
if (!CounterName)
|
||||
llvm::report_fatal_error("sched model does not define a cycle counter");
|
||||
return CounterName;
|
||||
}
|
||||
|
||||
std::vector<BenchmarkMeasure>
|
||||
LatencyBenchmarkRunner::runMeasurements(const ExecutableFunction &Function,
|
||||
const unsigned NumRepetitions) const {
|
||||
|
@ -101,12 +113,9 @@ LatencyBenchmarkRunner::runMeasurements(const ExecutableFunction &Function,
|
|||
// measure several times and take the minimum value.
|
||||
constexpr const int NumMeasurements = 30;
|
||||
int64_t MinLatency = std::numeric_limits<int64_t>::max();
|
||||
const char *CounterName = State.getSubtargetInfo()
|
||||
.getSchedModel()
|
||||
.getExtraProcessorInfo()
|
||||
.PfmCounters.CycleCounter;
|
||||
const char *CounterName = getCounterName();
|
||||
if (!CounterName)
|
||||
llvm::report_fatal_error("sched model does not define a cycle counter");
|
||||
llvm::report_fatal_error("could not determine cycle counter name");
|
||||
const pfm::PerfEvent CyclesPerfEvent(CounterName);
|
||||
if (!CyclesPerfEvent.valid())
|
||||
llvm::report_fatal_error("invalid perf event");
|
||||
|
|
|
@ -38,6 +38,8 @@ private:
|
|||
std::vector<BenchmarkMeasure>
|
||||
runMeasurements(const ExecutableFunction &EF,
|
||||
const unsigned NumRepetitions) const override;
|
||||
|
||||
virtual const char *getCounterName() const;
|
||||
};
|
||||
|
||||
} // namespace exegesis
|
||||
|
|
|
@ -140,10 +140,6 @@ void benchmarkMain() {
|
|||
return;
|
||||
}
|
||||
|
||||
// FIXME: Do not require SchedModel for latency.
|
||||
if (!State.getSubtargetInfo().getSchedModel().hasExtraProcessorInfo())
|
||||
llvm::report_fatal_error("sched model is missing extra processor info!");
|
||||
|
||||
const std::unique_ptr<BenchmarkRunner> Runner =
|
||||
State.getExegesisTarget().createBenchmarkRunner(BenchmarkMode, State);
|
||||
if (!Runner) {
|
||||
|
|
Loading…
Reference in New Issue