def recompile():
pbutil.chdirToPetabricksRoot()
config.benchmark = pbutil.normalizeBenchmarkName(config.benchmark)
config.output_cfg = pbutil.benchmarkToCfg(config.benchmark)
if config.recompile:
pbutil.compilePetabricks()
pbutil.compileBenchmarks([config.benchmark])
def recompile():
pbutil.chdirToPetabricksRoot();
config.benchmark = pbutil.normalizeBenchmarkName(config.benchmark)
config.output_cfg = pbutil.benchmarkToCfg(config.benchmark)
if config.recompile:
pbutil.compilePetabricks();
pbutil.compileBenchmarks([config.benchmark])
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():
warnings.simplefilter('ignore', tunerwarnings.NewProgramCrash)
warnings.simplefilter('ignore', tunerwarnings.TargetNotMet)
warnings.simplefilter('ignore', tunerwarnings.NanAccuracy)
progress.push()
progress.status("compiling benchmarks")
pbutil.chdirToPetabricksRoot()
pbutil.compilePetabricks();
r, lines = pbutil.loadAndCompileBenchmarks("./scripts/pbbenchmark.tests")
if filter(lambda x: x.rv!=0, r):
print "compile failed"
sys.exit(1)
print
print "All scores are relative performance to a baseline system."
print "Higher is better."
print
baselines = dict()
for line in csv.reader(open("./testdata/configs/baselines.csv")):
if len(line)>=3:
baselines[line[0]] = line[1:]
benchmarks=[]
for benchmark, cfg, n, accTarg in lines:
try:
baseline = baselines[benchmark]
except KeyError:
baseline = (1.0, 1.0)
benchmarks.append(Benchmark(benchmark, cfg, n, accTarg, baseline[0], baseline[1]))
print LONGBAR
print "Fixed (no autotuning) scores:"
print SHORTBAR
progress.remainingTicks(len(benchmarks)+3)
progress.tick()
for b in benchmarks:
progress.status("running fixed "+fmtCfg(b.cfg))
b.runFixed()
b.printFixed()
progress.tick()
score_fixed = geomean(map(Benchmark.scoreFixed, benchmarks))
print SHORTBAR
print "Fixed Score (pbbenchmark v%s): %.2f" % (VERSION, geomean(map(Benchmark.scoreFixed, benchmarks)))
print LONGBAR
print
print LONGBAR
print "Tuned scores:"
print SHORTBAR
for b in benchmarks:
progress.status("running tuned "+fmtCfg(b.cfg))
progress.status("autotuning")
b.autotune()
b.runTuned()
b.printTuned()
progress.tick()
score_tuned = geomean(map(Benchmark.scoreTuned, benchmarks))
score_training_time = geomean(map(Benchmark.scoreTrainingTime, benchmarks))
print SHORTBAR
print "Tuned Score (pbbenchmark v%s): %.2f" % (VERSION, score_tuned)
print "Training Time Score (pbbenchmark v%s): %.2f" % (VERSION, score_training_time)
print LONGBAR
print
if DEBUG:
print LONGBAR
print "Debug:"
print SHORTBAR
for b in benchmarks:
b.printDebug()
print LONGBAR
print
fd = open("./testdata/configs/baselines.csv.latest", "w")
for b in benchmarks:
print >>fd, "%s, %f, %f" % (b.benchmark, b.tuned_perf['average'], b.tuning_time)
fd.close()
if not os.path.isdir(LOGDIR):
os.mkdir(LOGDIR)
for b in benchmarks:
writelog(expandLog(b.cfg), b.logEntry())
writelog(expandLog('scores.log'), {
'version' : VERSION,
'score_fixed' : score_fixed,
'score_tuned' : score_tuned,
'score_training_time' : score_training_time,
'hostname' : socket.gethostname(),
'timestamp' : TIMESTAMP,
})
progress.tick()
progress.status("done")
progress.pop()
def main():
warnings.simplefilter('ignore', tunerwarnings.NewProgramCrash)
warnings.simplefilter('ignore', tunerwarnings.SmallInputProgramCrash)
warnings.simplefilter('ignore', tunerwarnings.TargetNotMet)
warnings.simplefilter('ignore', tunerwarnings.NanAccuracy)
#Parse input options
from optparse import OptionParser
parser = OptionParser(usage="usage: pbbenchmark [options]")
parser.add_option("--learning",
action="store_true",
dest="learning",
default=False,
help="enable heuristics learning")
parser.add_option(
"--heuristics",
type="string",
help=
"name of the file containing the set of heuristics to use. Automatically enables --learning",
default=None)
(options, args) = parser.parse_args()
if options.heuristics:
options.learning = True
if options.learning:
print "Learning of heuristics is ACTIVE"
if options.heuristics:
print "Using heuristics file: " + str(options.heuristics)
else:
print "Using only heuristics in the database"
progress.push()
progress.status("compiling benchmarks")
pbutil.chdirToPetabricksRoot()
pbutil.compilePetabricks()
global REV
try:
REV = pbutil.getRevision()
except:
pass
r, lines = pbutil.loadAndCompileBenchmarks(
"./scripts/pbbenchmark.tests",
searchterms=sys.argv[1:],
learning=options.learning,
heuristicSetFileName=options.heuristics)
if filter(lambda x: x.rv != 0, r):
print "compile failed"
sys.exit(1)
print
print "All scores are relative performance to a baseline system."
print "Higher is better."
print
baselines = dict()
for line in csv.reader(open("./testdata/configs/baselines.csv")):
if len(line) >= 3:
baselines[line[0]] = line[1:]
benchmarks = []
for benchmark, cfg, n, accTarg in lines:
try:
baseline = baselines[benchmark]
except KeyError:
baseline = (1.0, 1.0)
benchmarks.append(
Benchmark(benchmark, cfg, n, accTarg, baseline[0], baseline[1]))
progress.remainingTicks(len(benchmarks))
#print LONGBAR
#print "Fixed (no autotuning) scores:"
#print SHORTBAR
#for b in benchmarks:
# progress.status("running fixed "+fmtCfg(b.cfg))
# b.runFixed()
# b.printFixed()
#score_fixed = geomean(map(Benchmark.scoreFixed, benchmarks))
#print SHORTBAR
#print "Fixed Score (pbbenchmark v%s): %.2f" % (VERSION, geomean(map(Benchmark.scoreFixed, benchmarks)))
#print LONGBAR
#print
print LONGBAR
print "Tuned scores:"
print SHORTBAR
for b in benchmarks:
progress.status("running tuned " + fmtCfg(b.cfg))
progress.status("autotuning")
b.autotune()
b.runTuned()
b.printTuned()
progress.tick()
score_tuned = geomean(map(Benchmark.scoreTuned, benchmarks))
score_training_time = geomean(map(Benchmark.scoreTrainingTime, benchmarks))
print SHORTBAR
print "Tuned Score (pbbenchmark v%s): %.2f" % (VERSION, score_tuned)
print "Training Time Score (pbbenchmark v%s): %.2f" % (VERSION,
score_training_time)
print LONGBAR
print
if DEBUG:
print LONGBAR
print "Debug:"
print SHORTBAR
for b in benchmarks:
b.printDebug()
print LONGBAR
print
fd = open("./testdata/configs/baselines.csv.latest", "w")
for b in benchmarks:
print >> fd, "%s, %f, %f" % (b.benchmark, b.tuned_perf['average'],
b.tuning_time)
fd.close()
if not os.path.isdir(LOGDIR):
os.mkdir(LOGDIR)
for b in benchmarks:
writelog(expandLog(b.cfg), b.logEntry())
writelog(
expandLog('scores.log'),
{
'version': VERSION,
'score_fixed': -1, #score_fixed,
'score_tuned': score_tuned,
'score_training_time': score_training_time,
'hostname': socket.gethostname(),
'timestamp': TIMESTAMP,
'revision': REV,
})
progress.status("done")
progress.pop()
self.test(a)
else:
break
warnings.warn(ComparisonFailed(self.n, a, b))
return 0
return compare
def cleanup(self):
if config.cleanup_inputs:
storagedirs.clearInputs();
self.inputs=[]
if __name__ == "__main__":
print "TESTING CANDIDATETESTER"
pbutil.chdirToPetabricksRoot();
pbutil.compilePetabricks();
benchmark=pbutil.normalizeBenchmarkName('multiply')
pbutil.compileBenchmarks([benchmark])
tester = CandidateTester(benchmark, 768)
try:
candidate = Candidate(defaultConfigFile(pbutil.benchmarkToBin(tester.app)))
candidate2 = Candidate(defaultConfigFile(pbutil.benchmarkToBin(tester.app)))
candidate2.config['MatrixMultiplyTransposed_0_lvl1_rule']=1
tester.test(candidate)
tester.test(candidate)
tester.test(candidate)
tester.test(candidate2)
tester.test(candidate2)
tester.test(candidate2)
print candidate.metrics[0]
print candidate2.metrics[0]
def main():
warnings.simplefilter('ignore', tunerwarnings.NewProgramCrash)
warnings.simplefilter('ignore', tunerwarnings.SmallInputProgramCrash)
warnings.simplefilter('ignore', tunerwarnings.TargetNotMet)
warnings.simplefilter('ignore', tunerwarnings.NanAccuracy)
#Parse input options
from optparse import OptionParser
parser = OptionParser(usage="usage: pbbenchmark [options]")
parser.add_option("--learning", action="store_true", dest="learning", default=False, help="enable heuristics learning")
parser.add_option("--heuristics", type="string", help="name of the file containing the set of heuristics to use. Automatically enables --learning", default=None)
(options, args) = parser.parse_args()
if options.heuristics:
options.learning = True
if options.learning:
print "Learning of heuristics is ACTIVE"
if options.heuristics:
print "Using heuristics file: "+ str(options.heuristics)
else:
print "Using only heuristics in the database"
progress.push()
progress.status("compiling benchmarks")
pbutil.chdirToPetabricksRoot()
pbutil.compilePetabricks()
global REV
try:
REV=pbutil.getRevision()
except:
pass
r, lines = pbutil.loadAndCompileBenchmarks("./scripts/pbbenchmark.tests", searchterms=sys.argv[1:], learning=options.learning, heuristicSetFileName=options.heuristics)
if filter(lambda x: x.rv!=0, r):
print "compile failed"
sys.exit(1)
print
print "All scores are relative performance to a baseline system."
print "Higher is better."
print
baselines = dict()
for line in csv.reader(open("./testdata/configs/baselines.csv")):
if len(line)>=3:
baselines[line[0]] = line[1:]
benchmarks=[]
for benchmark, cfg, n, accTarg in lines:
try:
baseline = baselines[benchmark]
except KeyError:
baseline = (1.0, 1.0)
benchmarks.append(Benchmark(benchmark, cfg, n, accTarg, baseline[0], baseline[1]))
progress.remainingTicks(len(benchmarks))
#print LONGBAR
#print "Fixed (no autotuning) scores:"
#print SHORTBAR
#for b in benchmarks:
# progress.status("running fixed "+fmtCfg(b.cfg))
# b.runFixed()
# b.printFixed()
#score_fixed = geomean(map(Benchmark.scoreFixed, benchmarks))
#print SHORTBAR
#print "Fixed Score (pbbenchmark v%s): %.2f" % (VERSION, geomean(map(Benchmark.scoreFixed, benchmarks)))
#print LONGBAR
#print
print LONGBAR
print "Tuned scores:"
print SHORTBAR
for b in benchmarks:
progress.status("running tuned "+fmtCfg(b.cfg))
progress.status("autotuning")
b.autotune()
b.runTuned()
b.printTuned()
progress.tick()
score_tuned = geomean(map(Benchmark.scoreTuned, benchmarks))
score_training_time = geomean(map(Benchmark.scoreTrainingTime, benchmarks))
print SHORTBAR
print "Tuned Score (pbbenchmark v%s): %.2f" % (VERSION, score_tuned)
print "Training Time Score (pbbenchmark v%s): %.2f" % (VERSION, score_training_time)
print LONGBAR
print
if DEBUG:
print LONGBAR
print "Debug:"
print SHORTBAR
for b in benchmarks:
b.printDebug()
print LONGBAR
print
fd = open("./testdata/configs/baselines.csv.latest", "w")
for b in benchmarks:
print >>fd, "%s, %f, %f" % (b.benchmark, b.tuned_perf['average'], b.tuning_time)
fd.close()
if not os.path.isdir(LOGDIR):
os.mkdir(LOGDIR)
for b in benchmarks:
writelog(expandLog(b.cfg), b.logEntry())
writelog(expandLog('scores.log'), {
'version' : VERSION,
'score_fixed' : -1,#score_fixed,
'score_tuned' : score_tuned,
'score_training_time' : score_training_time,
'hostname' : socket.gethostname(),
'timestamp' : TIMESTAMP,
'revision' : REV,
})
progress.status("done")
progress.pop()
'''
cmpobj = self.comparer(config.timing_metric_idx,
config.confidence_pct,
config.max_trials,
limit)
return cmpobj(a,b)
def cleanup(self):
if config.cleanup_inputs:
storagedirs.clearInputs();
self.inputs=[]
if __name__ == "__main__":
print "TESTING CANDIDATETESTER"
pbutil.chdirToPetabricksRoot();
pbutil.compilePetabricks();
benchmark=pbutil.normalizeBenchmarkName('multiply')
pbutil.compileBenchmarks([benchmark])
tester = CandidateTester(benchmark, 768)
try:
candidate = Candidate(defaultConfigFile(pbutil.benchmarkToBin(tester.app)))
candidate2 = Candidate(defaultConfigFile(pbutil.benchmarkToBin(tester.app)))
candidate2.config['MatrixMultiplyTransposed_0_lvl1_rule']=1
tester.test(candidate)
tester.test(candidate)
tester.test(candidate)
tester.test(candidate2)
tester.test(candidate2)
tester.test(candidate2)
print candidate.metrics[0]
print candidate2.metrics[0]
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)))) + "}"