Chainerで100倍以上の性能比を確認

H.P.C. High Performance ComputingのVisual Technology.inc.は、ディープラーニングフレームワークのひとつである Chinerのサンプルプログラム”mnist”をIBM Power System S822LC for HPC(Minsky) で性能検証を行いました。
P100の単体性能に加えて、CPU⇔GPU、GPU⇔GPUとがNVLink接続された事による相乗効果でCPU比100倍以上の性能比を確認しました。

mnistのサンプルプログラムリスト

※55行目で args.gpu 指定することでGPUで計算されます
     1 #!/usr/bin/env python
     2 from __future__ import print_function
     3 import argparse
     4
     5 import chainer
     6 import chainer.functions as F
     7 import chainer.links as L
     8 from chainer import training
     9 from chainer.training import extensions
    10
    11
    12 # Network definition
    13 class MLP(chainer.Chain):
    14
    15      def __init__(self, n_units, n_out):
    16          super(MLP, self).__init__(
    17              # the size of the inputs to each layer will be inferred
    18              l1=L.Linear(None, n_units), # n_in -> n_units
    19              l2=L.Linear(None, n_units), # n_units -> n_units
    20              l3=L.Linear(None, n_out), # n_units -> n_out
    21          )
    22
    23      def __call__(self, x):
    24          h1 = F.relu(self.l1(x))
    25          h2 = F.relu(self.l2(h1))
    26          return self.l3(h2)
    27
    28
    29 def main():
    30      parser = argparse.ArgumentParser(description=’Chainer example: MNIST’)
    31      parser.add_argument(‘–batchsize’, ‘-b’, type=int, default=100,
    32                          help=’Number of images in each mini-batch’)
    33      parser.add_argument(‘–epoch’, ‘-e’, type=int, default=20,
    34                          help=’Number of sweeps over the dataset to train’)
    35      parser.add_argument(‘–gpu’, ‘-g’, type=int, default=-1,
    36                          help=’GPU ID (negative value indicates CPU)’)
    37      parser.add_argument(‘–out’, ‘-o’, default=’result’,
    38                          help=’Directory to output the result’)
    39      parser.add_argument(‘–resume’, ‘-r’, default=”,
    40                          help=’Resume the training from snapshot’)
    41      parser.add_argument(‘–unit’, ‘-u’, type=int, default=1000,
    42                          help=’Number of units’)
    43      args = parser.parse_args()
    44
    45      print(‘GPU: {}’.format(args.gpu))
    46      print(‘# unit: {}’.format(args.unit))
    47      print(‘# Minibatch-size: {}’.format(args.batchsize))
    48      print(‘# epoch: {}’.format(args.epoch))
    49      print(”)
    50
    51      # Set up a neural network to train
    52      # Classifier reports softmax cross entropy loss and accuracy at every
    53      # iteration, which will be used by the PrintReport extension below.
    54      model = L.Classifier(MLP(args.unit, 10))
    55      if args.gpu >= 0:
    56          chainer.cuda.get_device(args.gpu).use() # Make a specified GPU current
    57          model.to_gpu() # Copy the model to the GPU
    58
    59      # Setup an optimizer
    60      optimizer = chainer.optimizers.Adam()
    61      optimizer.setup(model)
    62
    63      # Load the MNIST dataset
    64      train, test = chainer.datasets.get_mnist()
    65
    66      train_iter = chainer.iterators.SerialIterator(train, args.batchsize)
    67      test_iter = chainer.iterators.SerialIterator(test, args.batchsize,
    68                                                   repeat=False, shuffle=False)
    69
    70      # Set up a trainer
    71      updater = training.StandardUpdater(train_iter, optimizer, device=args.gpu)
    72      trainer = training.Trainer(updater, (args.epoch, ‘epoch’), out=args.out)
    73
    74      # Evaluate the model with the test dataset for each epoch
    75      trainer.extend(extensions.Evaluator(test_iter, model, device=args.gpu))
    76
    77      # Dump a computational graph from ‘loss’ variable at the first iteration
    78      # The “main” refers to the target link of the “main” optimizer.
    79      trainer.extend(extensions.dump_graph(‘main/loss’))
    80
    81      # Take a snapshot at each epoch
    82      trainer.extend(extensions.snapshot(), trigger=(args.epoch, ‘epoch’))
    83
    84      # Write a log of evaluation statistics for each epoch
    85      trainer.extend(extensions.LogReport())
    86
    87      # Save two plot images to the result dir
    88      trainer.extend(
    89          extensions.PlotReport([‘main/loss’, ‘validation/main/loss’], ‘epoch’,
    90                                file_name=’loss.png’))
    91      trainer.extend(
    92          extensions.PlotReport([‘main/accuracy’, ‘validation/main/accuracy’],
    93                                ‘epoch’, file_name=’accuracy.png’))
    94
    95      # Print selected entries of the log to stdout
    96      # Here “main” refers to the target link of the “main” optimizer again, and
    97      # “validation” refers to the default name of the Evaluator extension.
    98      # Entries other than ‘epoch’ are reported by the Classifier link, called by
    99      # either the updater or the evaluator.
   100      trainer.extend(extensions.PrintReport(
   101          [‘epoch’, ‘main/loss’, ‘validation/main/loss’,
   102           ‘main/accuracy’, ‘validation/main/accuracy’, ‘elapsed_time’]))
   103
   104      # Print a progress bar to stdout
   105      trainer.extend(extensions.ProgressBar())
   106
   107      if args.resume:
   108          # Resume from a snapshot
   109          chainer.serializers.load_npz(args.resume, trainer)
   110
   111      # Run the training
   112      trainer.run()
   113
   114 if __name__ == ‘__main__’:
   115      main()