aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/tools/ci_build/gpu_build/parallel_gpu_execute.sh
blob: 03a2a07fb1f3333ce12eab256d139e54deb0a5d1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
#!/usr/bin/env bash
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
#
#
# A script to run multiple GPU tests in parallel controlled with an environment
# variable.
#
# Required environment variables:
#     TF_GPU_COUNT = Number of GPUs available.

TF_GPU_COUNT=${TF_GPU_COUNT:-8}
TF_TESTS_PER_GPU=${TF_TESTS_PER_GPU:-4}
# We want to allow running one of the following configs:
#  - 4 tests per GPU on k80
#  - 8 tests per GPU on p100
# p100 has minimum 12G memory. Therefore, we should limit each test to 1.5G.
# To leave some room in case we want to run more tests in parallel in the
# future and to use a rounder number, we set it to 1G.
export TF_PER_DEVICE_MEMORY_LIMIT_MB=1024

# *******************************************************************
#         This section of the script is needed to
#         make things work on windows under msys.
# *******************************************************************
RUNFILES_MANIFEST_FILE="${TEST_SRCDIR}/MANIFEST"
function rlocation() {
  if is_absolute "$1" ; then
    # If the file path is already fully specified, simply return it.
    echo "$1"
  elif [[ -e "$TEST_SRCDIR/$1" ]]; then
    # If the file exists in the $TEST_SRCDIR then just use it.
    echo "$TEST_SRCDIR/$1"
  elif [[ -e "$RUNFILES_MANIFEST_FILE" ]]; then
    # If a runfiles manifest file exists then use it.
    echo "$(grep "^$1 " "$RUNFILES_MANIFEST_FILE" | sed 's/[^ ]* //')"
  fi
}

TEST_BINARY="$(rlocation $TEST_WORKSPACE/${1#./})"
shift
# *******************************************************************

mkdir -p /var/lock
# Try to acquire any of the TF_GPU_COUNT * TF_TESTS_PER_GPU
# slots to run a test at.
#
# Prefer to allocate 1 test per GPU over 4 tests on 1 GPU.
# So, we iterate over TF_TESTS_PER_GPU first.
for j in `seq 0 $((TF_TESTS_PER_GPU-1))`; do
  for i in `seq 0 $((TF_GPU_COUNT-1))`; do
    exec {lock_fd}>/var/lock/gpulock${i}_${j} || exit 1
    if flock -n "$lock_fd";
    then
      (
        # This export only works within the brackets, so it is isolated to one
        # single command.
        export CUDA_VISIBLE_DEVICES=$i
        echo "Running test $TEST_BINARY $* on GPU $CUDA_VISIBLE_DEVICES"
        "$TEST_BINARY" $@
      )
      return_code=$?
      flock -u "$lock_fd"
      exit $return_code
    fi
  done
done

echo "Cannot find a free GPU to run the test $* on, exiting with failure..."
exit 1