def updatestatus(fast=False):
progress.remaining(2*len(jobs_pending)+len(jobs_running))
if not fast:
for j in jobs_done[maxprinted[0]:]:
if j.id==maxprinted[0]:
print j.getmsg()
maxprinted[0]+=1
else:
break
def autotuneAlgchoice(tx, site, ctx, n, cutoffs):
progress.push()
cmd = mkcmd([
"--transform=" + nameof(ctx), "--autotune",
"--autotune-transform=" + nameof(tx),
"--autotune-site=%d" % site,
"--max=%d" % n,
"--max-sec=%d" % goodtimelimit()
])
for x in cutoffs:
cmd.append("--autotune-tunable=" + nameof(x))
if options.debug or options.justprint:
print ' '.join(cmd)
if options.justprint:
progress.pop()
return True
runsCur = 1
runsLast = 1
inputCur = 1
#progress formula assumes linear runtime of program
calcprog = lambda: 1.0 - (math.log(inputCur, 2) + min(
1.0, runsCur / float(runsLast))) / (math.log(n, 2) + 1)
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=substderr)
pfx = "tuning " + nameof(tx) + ":%d - " % site
if site == -1:
pfx = "tuning %d cutoffs in %s - " % (len(cutoffs), nameof(tx))
str = ""
progress.status(pfx)
while True:
line = p.stdout.readline()
if line == "":
break
#BEGIN ITERATION .... / 4096
m = iterRe.match(line)
if m:
inputCur = int(m.group(1))
runsLast = runsCur
runsCur = 0
progress.remaining(calcprog())
#SLOT[0] KEEP .... = 1.25
m = slotRe.match(line)
if m:
if m.group(1) == "0":
str = m.group(3)
progress.status(pfx + str)
# * TRY ...
m = runRe.match(line)
if m:
runsCur += 1
progress.remaining(calcprog())
progress.pop()
if p.wait() == 0:
print "* " + pfx + str
return True
else:
print 'FAILURE OF TUNING STEP:', ' '.join(cmd)
return False
def updatestatus(fast=False):
progress.remaining(2 * len(jobs_pending) + len(jobs_running))
if not fast:
for j in jobs_done[maxprinted[0]:]:
if j.id == maxprinted[0]:
print j.getmsg()
maxprinted[0] += 1
else:
break
def optimizeParam(ctx,
n,
param,
start=0,
stop=-1,
branchfactor=7,
best=(-1, maxint),
worst=(-1, -maxint)):
def timeat(x, thresh):
old = getConfigVal(param)
setConfigVal(param, x)
t = timingRun(ctx, n, thresh)
setConfigVal(param, old)
return t
if stop < 0:
stop = n
step = (stop - start) / float(branchfactor - 1)
progress.status(
"optimizing %s in %s, searching [%d,%d], impact=%.2f" %
(param, nameof(ctx), start, stop, max(0,
(worst[1] - best[1]) / best[1])))
if step >= 1:
xs = map(lambda i: start + int(round(step * i)), xrange(branchfactor))
ys = []
for i in xrange(len(xs)):
progress.remaining(
math.log(stop - start, branchfactor / 2.0) * branchfactor - i)
x = xs[i]
if x == best[0]:
y = best[1] # cached value
else:
try:
y = timeat(x, best[1] + 1)
except pbutil.TimingRunTimeout, e:
y = maxint
if y < best[1]:
best = (x, y)
ys.append(y)
minTime, minX = reduce(min,
map(lambda i: (ys[i], xs[i]), xrange(len(xs))))
maxTime, maxX = reduce(max,
map(lambda i: (ys[i], xs[i]), xrange(len(xs))))
improvement = (maxTime - minTime) / maxTime
newStart = max(int(round(minX - step)), start)
newStop = min(int(round(minX + step)), stop)
best = (minX, minTime)
if worst[1] < maxTime:
worst = (maxX, maxTime)
#print minX, start, stop, improvement
if improvement > 0.05:
return optimizeParam(ctx, n, param, newStart, newStop,
branchfactor, best, worst)
def runTimingTest(tx):
progress.push()
progress.remaining(1)
progress.status("running timing test")
t=timingRun(tx, options.n)
progress.remaining(0)
if len(results)>0:
speedup=results[-1]/t
print "* timing test... %.4f (%.2fx speedup)"%(t, speedup)
else:
print "* initial timing test... %.4lf s"%t
results.append(t)
progress.pop()
def runTimingTest(tx):
progress.push()
progress.remaining(1)
progress.status("running timing test")
t = timingRun(tx, options.n)
progress.remaining(0)
if len(results) > 0:
speedup = results[-1] / t
print "* timing test... %.4f (%.2fx speedup)" % (t, speedup)
else:
print "* initial timing test... %.4lf s" % t
results.append(t)
progress.pop()
def autotuneAlgchoice(tx, site, ctx, n, cutoffs):
progress.push()
cmd=mkcmd(["--transform="+nameof(ctx), "--autotune", "--autotune-transform="+nameof(tx), "--autotune-site=%d"%site,
"--max=%d"%n, "--max-sec=%d"%goodtimelimit()])
for x in cutoffs:
cmd.append("--autotune-tunable="+nameof(x))
if options.debug or options.justprint:
print ' '.join(cmd)
if options.justprint:
progress.pop()
return True
runsCur=1
runsLast=1
inputCur=1
#progress formula assumes linear runtime of program
calcprog=lambda: 1.0 - (math.log(inputCur,2) + min(1.0,runsCur/float(runsLast)))/(math.log(n,2)+1)
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=substderr)
pfx="tuning "+nameof(tx)+":%d - "%site
if site == -1:
pfx="tuning %d cutoffs in %s - " % (len(cutoffs), nameof(tx))
str=""
progress.status(pfx)
while True:
line=p.stdout.readline()
if line == "":
break
#BEGIN ITERATION .... / 4096
m=iterRe.match(line)
if m:
inputCur=int(m.group(1))
runsLast=runsCur
runsCur=0
progress.remaining(calcprog())
#SLOT[0] KEEP .... = 1.25
m=slotRe.match(line)
if m:
if m.group(1)=="0":
str=m.group(3)
progress.status(pfx+str)
# * TRY ...
m=runRe.match(line)
if m:
runsCur+=1
progress.remaining(calcprog())
progress.pop()
if p.wait()==0:
print "* "+pfx+str
return True
else:
print 'FAILURE OF TUNING STEP:', ' '.join(cmd)
return False
def randomMutation(self, maxpopsize=None, mutatorFilter=lambda m: True):
'''grow the population using cloning and random mutation'''
originalPop = list(self.members)
totalMutators = self.countMutators(mutatorFilter)
tries = float(totalMutators)*config.mutations_per_mutator
while tries>0:
progress.remaining(tries)
check_timeout()
tries-=1
if maxpopsize and len(self.members) >= maxpopsize:
break
if config.multimutation:
p=random.choice(self.members)
else:
p=random.choice(originalPop)
try:
c=p.cloneAndMutate(self.inputSize(), mutatorFilter=mutatorFilter)
except candidatetester.NoMutators:
if self.countMutators(mutatorFilter)>0:
continue
else:
return tries
if c.config in self.triedConfigs and c.lastMutator:
c.lastMutator.result('fail')
continue
self.triedConfigs.add(c.config)
try:
self.testers[-1].testN(c, config.min_trials, limit=p.reasonableLimit(self.inputSize()))
if self.birthFilter(p,c):
self.members.append(c)
self.onMembersChanged(False)
else:
c.rmfiles()
self.notadded.append(c)
except candidatetester.CrashException, e:
c.rmfiles()
if c.lastMutator:
c.lastMutator.result('fail')
warnings.warn(NewProgramCrash(e))
def optimizeParam(ctx, n, param, start=0, stop=-1, branchfactor=7, best=(-1, maxint), worst=(-1, -maxint)):
def timeat(x, thresh):
old=getConfigVal(param)
setConfigVal(param, x)
t=timingRun(ctx, n, thresh)
setConfigVal(param, old)
return t
if stop<0:
stop=n
step=(stop-start)/float(branchfactor-1)
progress.status("optimizing %s in %s, searching [%d,%d], impact=%.2f" %(param,nameof(ctx),start,stop,max(0,(worst[1]-best[1])/best[1])))
if step>=1:
xs=map(lambda i: start+int(round(step*i)), xrange(branchfactor))
ys=[]
for i in xrange(len(xs)):
progress.remaining(math.log(stop-start, branchfactor/2.0)*branchfactor - i)
x=xs[i]
if x==best[0]:
y=best[1] # cached value
else:
try:
y=timeat(x, best[1]+1)
except pbutil.TimingRunTimeout, e:
y=maxint
if y<best[1]:
best=(x,y)
ys.append(y)
minTime, minX = reduce(min, map(lambda i: (ys[i], xs[i]), xrange(len(xs))))
maxTime, maxX = reduce(max, map(lambda i: (ys[i], xs[i]), xrange(len(xs))))
improvement=(maxTime-minTime)/maxTime
newStart = max(int(round(minX-step)), start)
newStop = min(int(round(minX+step)), stop)
best=(minX, minTime)
if worst[1]<maxTime:
worst=(maxX, maxTime)
#print minX, start, stop, improvement
if improvement > 0.05:
return optimizeParam(ctx, n, param, newStart, newStop, branchfactor, best, worst)
def main(argv):
t1=time.time()
global app
global cfg
global ignore_list
global defaultArgs
global substderr
global options
config_tool_path = os.path.split(argv[0])[0] + "/configtool.py"
fast = False
parser = optparse.OptionParser(usage="usage: %prog [options] BENCHMARK")
parser.add_option("--min", type="int", dest="min", default=1)
parser.add_option("-n", "--random", "--max", type="int", dest="n", default=-1)
parser.add_option("--offset", type="int", dest="offset", default=0)
parser.add_option("--max-sec", type="float", dest="maxsec", default=0)
parser.add_option("-d", "--debug", action="store_true", dest="debug", default=False)
parser.add_option("-f", "--fast", action="store_true", dest="fast", default=False)
parser.add_option("--threads", type="int", dest="threads", default=pbutil.cpuCount())
parser.add_option("-c", "--config", dest="config", default=None)
parser.add_option("--noisolation", action="store_true", dest="noisolation", default=False)
parser.add_option("--print", action="store_true", dest="justprint", default=False)
parser.add_option("--time", action="store_true", dest="time", default=False)
parser.add_option("--acctrials", type="int", dest="acctrials", default=None)
parser.add_option("--accimprovetries", type="int", dest="accimprovetries", default=None)
parser.add_option("--trials", type="int", dest="trials", default=None)
parser.add_option("--trials-sec", type="float", dest="trialssec", default=None)
parser.add_option("--trials-max", type="int", dest="trialsmax", default=None)
parser.add_option("--transform", dest="transform", default=None)
options,args = parser.parse_args()
if len(args) != 1:
parser.error("expected benchmark name as arg")
cfg=options.config
app=args[0]
pbutil.chdirToPetabricksRoot()
pbutil.compilePetabricks()
app = pbutil.normalizeBenchmarkName(app)
pbutil.compileBenchmarks([app])
if options.debug:
substderr = sys.__stderr__
if cfg is None:
cfg = pbutil.benchmarkToCfg(app)
defaultArgs = ['--config='+cfg, '--threads=%d'%options.threads, '--offset=%d'%options.offset, '--min=%d'%options.min]
if options.noisolation:
defaultArgs.append("--noisolation")
if options.acctrials is not None:
defaultArgs.append("--acctrials=%d"%options.acctrials)
if options.trials is not None:
defaultArgs.append("--trials=%d"%options.trials)
if options.trialssec is not None:
defaultArgs.append("--trials-sec=%f"%options.trialssec)
if options.trialsmax is not None:
defaultArgs.append("--trials-max=%d"%options.trialsmax)
if options.accimprovetries is not None:
defaultArgs.append("--accimprovetries=%d"%options.accimprovetries)
getIgnoreList()
try:
infoxml = parse(pbutil.benchmarkToInfo(app))
except:
print "Cannot parse:", pbutil.benchmarkToInfo(app)
sys.exit(-1)
#print "Reseting config entries"
#reset()
#build index of transforms
for t in infoxml.getElementsByTagName("transform"):
transforms[nameof(t)]=t
if t.getAttribute("templateChoice")=="0":
transforms[t.getAttribute("templateName")] = t
if options.transform is None:
maintx = transforms[mainname()]
else:
maintx = transforms[options.transform]
print "Call tree:"
walkCallTree(maintx, fnup=printTx)
print
print "Autotuning:"
progress.status("building work queue")
if options.n <= 0:
tasks.append(TuneTask("determineInputSizes", determineInputSizes))
if options.time:
tasks.append(TuneTask("runTimingTest", lambda:runTimingTest(maintx)))
#build list of tasks
if not options.fast:
walkCallTree(maintx, lambda tx, depth, loops: enqueueAutotuneCmds(tx, maintx, 1, depth, loops))
walkCallTree(maintx, lambda tx, depth, loops: enqueueAutotuneCmds(tx, maintx, 2, depth, loops))
if options.time:
tasks.append(TuneTask("runTimingTest", lambda:runTimingTest(maintx)))
progress.status("autotuning")
while len(tasks)>0:
w1=remainingTaskWeight()
task=tasks.pop(0)
w2=remainingTaskWeight()
progress.remaining(w1, w2)
task.run()
progress.clear()
t2=time.time()
sec=t2-t1
print "autotuning took %.2f sec"%(t2-t1)
for k,v in taskStats.items():
print " %.2f sec in %s"%(v.sec, k)
sec -= v.sec
print " %.2f sec in unknown"%sec
names=taskStats.keys()
weights=map(lambda x: x.sec/float(max(x.count, 1)), taskStats.values())
scale=len(weights)/sum(weights)
print "Suggested weights:"
print "taskStats = {" + ", ".join(map(lambda i: "'%s':TaskStats(%.2f)"%(names[i], scale*weights[i]), xrange(len(names)))) + "}"
def main(argv):
t1 = time.time()
global app
global cfg
global ignore_list
global defaultArgs
global substderr
global options
config_tool_path = os.path.split(argv[0])[0] + "/configtool.py"
fast = False
parser = optparse.OptionParser(usage="usage: %prog [options] BENCHMARK")
parser.add_option("--min", type="int", dest="min", default=1)
parser.add_option("-n",
"--random",
"--max",
type="int",
dest="n",
default=-1)
parser.add_option("--offset", type="int", dest="offset", default=0)
parser.add_option("--max-sec", type="float", dest="maxsec", default=0)
parser.add_option("-d",
"--debug",
action="store_true",
dest="debug",
default=False)
parser.add_option("-f",
"--fast",
action="store_true",
dest="fast",
default=False)
parser.add_option("--threads",
type="int",
dest="threads",
default=pbutil.cpuCount())
parser.add_option("-c", "--config", dest="config", default=None)
parser.add_option("--noisolation",
action="store_true",
dest="noisolation",
default=False)
parser.add_option("--print",
action="store_true",
dest="justprint",
default=False)
parser.add_option("--time",
action="store_true",
dest="time",
default=False)
parser.add_option("--acctrials",
type="int",
dest="acctrials",
default=None)
parser.add_option("--accimprovetries",
type="int",
dest="accimprovetries",
default=None)
parser.add_option("--trials", type="int", dest="trials", default=None)
parser.add_option("--trials-sec",
type="float",
dest="trialssec",
default=None)
parser.add_option("--trials-max",
type="int",
dest="trialsmax",
default=None)
parser.add_option("--transform", dest="transform", default=None)
options, args = parser.parse_args()
if len(args) != 1:
parser.error("expected benchmark name as arg")
cfg = options.config
app = args[0]
pbutil.chdirToPetabricksRoot()
pbutil.compilePetabricks()
app = pbutil.normalizeBenchmarkName(app)
pbutil.compileBenchmarks([app])
if options.debug:
substderr = sys.__stderr__
if cfg is None:
cfg = pbutil.benchmarkToCfg(app)
defaultArgs = [
'--config=' + cfg,
'--threads=%d' % options.threads,
'--offset=%d' % options.offset,
'--min=%d' % options.min
]
if options.noisolation:
defaultArgs.append("--noisolation")
if options.acctrials is not None:
defaultArgs.append("--acctrials=%d" % options.acctrials)
if options.trials is not None:
defaultArgs.append("--trials=%d" % options.trials)
if options.trialssec is not None:
defaultArgs.append("--trials-sec=%f" % options.trialssec)
if options.trialsmax is not None:
defaultArgs.append("--trials-max=%d" % options.trialsmax)
if options.accimprovetries is not None:
defaultArgs.append("--accimprovetries=%d" % options.accimprovetries)
getIgnoreList()
try:
infoxml = parse(pbutil.benchmarkToInfo(app))
except:
print "Cannot parse:", pbutil.benchmarkToInfo(app)
sys.exit(-1)
#print "Reseting config entries"
#reset()
#build index of transforms
for t in infoxml.getElementsByTagName("transform"):
transforms[nameof(t)] = t
if t.getAttribute("templateChoice") == "0":
transforms[t.getAttribute("templateName")] = t
if options.transform is None:
maintx = transforms[mainname()]
else:
maintx = transforms[options.transform]
print "Call tree:"
walkCallTree(maintx, fnup=printTx)
print
print "Autotuning:"
progress.status("building work queue")
if options.n <= 0:
tasks.append(TuneTask("determineInputSizes", determineInputSizes))
if options.time:
tasks.append(TuneTask("runTimingTest", lambda: runTimingTest(maintx)))
#build list of tasks
if not options.fast:
walkCallTree(
maintx, lambda tx, depth, loops: enqueueAutotuneCmds(
tx, maintx, 1, depth, loops))
walkCallTree(
maintx, lambda tx, depth, loops: enqueueAutotuneCmds(
tx, maintx, 2, depth, loops))
if options.time:
tasks.append(TuneTask("runTimingTest", lambda: runTimingTest(maintx)))
progress.status("autotuning")
while len(tasks) > 0:
w1 = remainingTaskWeight()
task = tasks.pop(0)
w2 = remainingTaskWeight()
progress.remaining(w1, w2)
task.run()
progress.clear()
t2 = time.time()
sec = t2 - t1
print "autotuning took %.2f sec" % (t2 - t1)
for k, v in taskStats.items():
print " %.2f sec in %s" % (v.sec, k)
sec -= v.sec
print " %.2f sec in unknown" % sec
names = taskStats.keys()
weights = map(lambda x: x.sec / float(max(x.count, 1)), taskStats.values())
scale = len(weights) / sum(weights)
print "Suggested weights:"
print "taskStats = {" + ", ".join(
map(lambda i: "'%s':TaskStats(%.2f)" %
(names[i], scale * weights[i]), xrange(len(names)))) + "}"
def autotuneInner(benchmark):
progress.push()
config.benchmark = benchmark
candidate, tester = init(benchmark)
try:
pop = Population(candidate, tester, None)
if not pop.isVariableAccuracy() and config.accuracy_target:
logging.info("clearing accuracy_target")
config.accuracy_target = None
stats = storagedirs.openCsvStats("roundstats",
("round",
"input_size",
"cumulative_sec",
"incremental_sec",
"testing_sec",
"inputgen_sec")+pop.statsHeader())
timers.total.start()
config.end_time = time.time() + config.max_time
try:
progress.remaining(config.max_input_size*(1+config.final_rounds))
while pop.inputSize() < config.max_input_size:
progress.status("autotuning %s: input %d of %d" % (config.benchmark, pop.inputSize(), config.max_input_size))
pop.generation()
stats.writerow((pop.roundNumber,
pop.inputSize(),
timers.total.total(),
timers.total.lap(),
timers.testing.lap(),
timers.inputgen.lap())+pop.stats())
pop.nextInputSize()
progress.remaining(config.max_input_size - pop.inputSize() + config.max_input_size*config.final_rounds)
for z in xrange(config.final_rounds):
pop.generation()
stats.writerow((pop.roundNumber,
pop.inputSize(),
timers.total.total(),
timers.total.lap(),
timers.testing.lap(),
timers.inputgen.lap())+pop.stats())
progress.remaining((config.final_rounds - z)*config.max_input_size)
except TrainingTimeout:
pass
timers.total.stop()
#check to make sure we did something:
if pop.firstRound:
warnings.warn(tunerwarnings.AlwaysCrashes())
logging.info("TODO: using acc target: "+str(config.accuracy_target))
return pop.best
finally:
if pop.best and config.output_cfg:
print pop.best.cfgfile(),"=>" , config.output_cfg
shutil.copyfile(pop.best.cfgfile(), config.output_cfg)
at = storagedirs.getactivetimers()
if len(at):
storagedirs.openCsvStats("timers", at.keys()).writerow(at.values())
if tester:
tester.cleanup()
progress.pop()
