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 print_tunables(benchmark, choice2id2label):
cfg_file = pbutil.benchmarkToCfg(benchmark)
def fix_rule_numbers(key, val):
"""If the tunable is an algorithm choice, convert the index to the label."""
if key in choice2id2label:
return (key, choice2id2label[key][int(val)])
else:
return (key, val)
configtool.processConfigFile(cfg_file, "/dev/stdout", [fix_rule_numbers])
def testBenchmark(b):
name=b[0]
bin=pbutil.benchmarkToBin(name)
cfg=pbutil.benchmarkToCfg(name)
if not os.path.isfile(bin):
return False
#build cmd
hash=name
iofiles=[]
for x in b[1:]:
iofiles.append(resolveInputPath(x))
hash+=" "+os.path.basename(x)
outfile="./testdata/.output/"+re.sub("[ /.]",'_',hash)
iofiles.append(outfile+".latest")
try:
cmd=[bin, '--fixedrandom', '--config=%s.cfg'%outfile, '--reset']
if run(cmd) != 0:
print "ERROR: reset config failed"
return False
except OSError:
print "ERROR: program not runnable"
return False
if os.path.isfile("%s.cfg.default"%outfile):
shutil.copy("%s.cfg.default"%outfile, "%s.cfg"%outfile)
try:
infoxml=parse(pbutil.benchmarkToInfo(name))
except:
print "invalid *.info file"
return False
def test():
cmd=[bin, '--fixedrandom', '--config=%s.cfg'%outfile]
cmd.extend(iofiles)
rv = run(cmd)
if rv != 0:
print "run FAILED (status=%d, cmd=%s)"%(rv, ' '.join(cmd))
return False
if diffFiles(outfile, outfile+".latest"):
time.sleep(0.1) #try letting the filesystem settle down
if diffFiles(outfile, outfile+".latest"):
print "run FAILED (wrong output)"
return False
print "run PASSED"
return True
return test()
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 testBenchmark(b):
name = b[0]
bin = pbutil.benchmarkToBin(name)
cfg = pbutil.benchmarkToCfg(name)
if not os.path.isfile(bin):
return False
#build cmd
hash = name
iofiles = []
for x in b[1:]:
iofiles.append(resolveInputPath(x))
hash += " " + os.path.basename(x)
outfile = "./testdata/.output/" + re.sub("[ /.]", '_', hash)
iofiles.append(outfile + ".latest")
try:
cmd = [bin, '--fixedrandom', '--config=%s.cfg' % outfile, '--reset']
if run(cmd) != 0:
print "ERROR: reset config failed"
return False
except OSError:
print "ERROR: program not runnable"
return False
if os.path.isfile("%s.cfg.default" % outfile):
shutil.copy("%s.cfg.default" % outfile, "%s.cfg" % outfile)
try:
infoxml = parse(pbutil.benchmarkToInfo(name))
except:
print "invalid *.info file"
return False
def test():
if isFloatingPoint() and os.path.exists(outfile + ".float"):
ext = ".float"
print "FLOAT"
else:
ext = ""
#run cpu config
cmd = [bin, '--fixedrandom', '--config=%s.cfg' % outfile]
cmd.extend(iofiles)
t1 = time.time()
rv = run(cmd)
t2 = time.time()
if rv != 0:
print "run FAILED (status=%d, cmd=%s)" % (rv, ' '.join(cmd))
return False
if diffFiles(outfile + ext, outfile + ".latest"):
time.sleep(0.1) #try letting the filesystem settle down
if diffFiles(outfile + ext, outfile + ".latest"):
print "run FAILED (wrong output)"
return False
print "run PASSED (took %.2fs)" % (t2 - t1)
if (not haveOpenCL()) or (not os.path.exists(outfile + ".gpucfg")):
return True
#run gpu config
cmd = [bin, '--fixedrandom', '--config=%s.gpucfg' % outfile]
cmd.extend(iofiles)
t1 = time.time()
rv = run(cmd)
t2 = time.time()
if rv != 0:
print "gpu FAILED (status=%d, cmd=%s)" % (rv, ' '.join(cmd))
return False
if diffFiles(outfile + ext, outfile + ".latest"):
time.sleep(0.1) #try letting the filesystem settle down
if diffFiles(outfile + ext, outfile + ".latest"):
print "gpu FAILED (wrong output)"
return False
print "gpu PASSED (took %.2fs)" % (t2 - t1)
return True
return test()
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)))) + "}"
