def main():
import sys
log.init(verbose=True)
m = model.from_json(clgen.load_json_file(sys.argv[1]))
s = sampler.from_json({
"kernels": {
"args": [
"__global float*", "__global float*", "__global float*",
"const int"
],
"max_length":
5000,
"temperature":
1
},
"sampler": {
"batch_size": 1000,
"max_batches": 1,
"static_checker": False,
"dynamic_checker": False
}
})
print("Corpus size:", m.corpus.size)
print("Vocab size: ", m.corpus.vocab_size)
print()
clgen.platform_info()
print()
outpath = "./benchmark-" + fs.basename(sys.argv[1])
info = evaluate(m, s)
clgen.write_file(outpath, clgen.format_json(info))
def main():
import sys
log.init(verbose=True)
m = model.from_json(clgen.load_json_file(sys.argv[1]))
s = sampler.from_json({
"kernels": {
"args": [
"__global float*",
"__global float*",
"__global float*",
"const int"
],
"max_length": 5000,
"temperature": 1
},
"sampler": {
"batch_size": 1000,
"max_batches": 1,
"static_checker": False,
"dynamic_checker": False
}
})
print("Corpus size:", m.corpus.size)
print("Vocab size: ", m.corpus.vocab_size)
print()
clgen.platform_info()
print()
outpath = "./benchmark-" + fs.basename(sys.argv[1])
info = evaluate(m, s)
clgen.write_file(outpath, clgen.format_json(info))
def main():
log.init(verbose=True)
m = model.from_json(clgen.load_json_file(sys.argv[1]))
c = corpus.Corpus.from_json({"path": "~/data/github"})
print("CLgen: ", clgen.version())
print("Corpus size:", c.size)
print("Vocab size: ", c.vocab_size)
m.train()
p, _ = corpus.most_common_prototypes(c, 20)
for i, row in enumerate(p):
outpath = "./inference-p" + str(i + 1) + "-" + fs.basename(sys.argv[1])
if fs.exists(outpath):
continue
_, prototype = row
argspec = [' '.join(x.split()[:-1]) for x in prototype.split(',')]
print("argspec", ','.join([str(x) for x in argspec]))
s = sampler.from_json({
"kernels": {
"args": argspec,
"max_length": 5000
},
"sampler": {
"batch_size": 2000,
"max_batches": 1,
"static_checker": False,
"dynamic_checker": False
}
})
info = evaluate(m, s)
clgen.write_file(outpath, clgen.format_json(info))
def to_dist(self, distpath: str, author: str = None) -> str:
"""
Create a dist file.
Arguments:
distpath (str): Path to dist file.
author (str, optional): Author name.
Returns:
str: Path to generated distfile.
"""
outpath = fs.abspath(distpath) + ".tar.bz2"
if fs.exists(outpath):
raise DistError("file {} exists".format(outpath))
meta = self.meta
if author is not None:
meta["author"] = author
log.debug(clgen.format_json(meta))
try:
tar = tarfile.open(outpath, 'w:bz2')
# write meta
metapath = mktemp(prefix="clgen-", suffix=".json")
clgen.write_file(metapath, clgen.format_json(meta))
log.debug("metafile:", metapath)
# create tarball
tar.add(metapath, arcname="meta.json")
# pack contents:
for path in meta["contents"]:
abspath = fs.path(cache.ROOT, path)
log.verbose("packing", abspath)
tar.add(abspath, arcname=fs.path("contents", path))
# tidy up
fs.rm(metapath)
tar.close()
except Exception as e:
tar.close()
fs.rm(metapath)
fs.rm(outpath)
raise e
return outpath
def main():
log.init(verbose=True)
m = model.from_json(clgen.load_json_file(sys.argv[1]))
c = corpus.Corpus.from_json({"path": "~/data/github"})
print("CLgen: ", clgen.version())
print("Corpus size:", c.size)
print("Vocab size: ", c.vocab_size)
m.train()
p, _ = corpus.most_common_prototypes(c, 20)
for i, row in enumerate(p):
outpath = "./inference-p" + str(i + 1) + "-" + fs.basename(sys.argv[1])
if fs.exists(outpath):
print("skipped result for", outpath)
continue
else:
print("starting result for", outpath)
_, prototype = row
argspec = [' '.join(x.split()[:-1]) for x in prototype.split(',')]
print("argspec", ','.join([str(x) for x in argspec]))
s = sampler.from_json({
"kernels": {
"args": argspec,
"max_length": 5000
},
"sampler": {
"batch_size": 2000,
"max_batches": 1,
"static_checker": False,
"dynamic_checker": False
}
})
info = evaluate(m, s)
clgen.write_file(outpath, clgen.format_json(info))
def write_log(log, logpath):
clgen.write_file(logpath, clgen.format_json(log))
def write_log(log, logpath):
clgen.write_file(logpath, clgen.format_json(log))
def __repr__(self) -> str:
"""
String representation.
"""
return "{hash}: {data}".format(hash=self.hash,
data=clgen.format_json(self.opts))
