From cf4533d0c099f84f9648ec74d5dc32079b378bd0 Mon Sep 17 00:00:00 2001 From: Jiabin Yang Date: Tue, 25 Jun 2019 21:43:39 +0800 Subject: [PATCH] Cherry pick install check (#18326) * test=release/1.5, add mutigpu install check * test=develop, refine code to use cuda_devices --- python/paddle/fluid/install_check.py | 123 +++++++++++++++++++++------ 1 file changed, 99 insertions(+), 24 deletions(-) diff --git a/python/paddle/fluid/install_check.py b/python/paddle/fluid/install_check.py index ce21d5753..05907562e 100644 --- a/python/paddle/fluid/install_check.py +++ b/python/paddle/fluid/install_check.py @@ -12,15 +12,18 @@ # See the License for the specific language governing permissions and # limitations under the License. -from .framework import Program, program_guard, unique_name, default_startup_program +import os +from .framework import Program, program_guard, unique_name, cuda_places, cpu_places from .param_attr import ParamAttr from .initializer import Constant from . import layers from . import backward from .dygraph import Layer, nn from . import executor - +from . import optimizer from . import core +from . import compiler +import logging import numpy as np __all__ = ['run_check'] @@ -45,25 +48,97 @@ def run_check(): This func should not be called only if you need to verify installation ''' print("Running Verify Fluid Program ... ") - prog = Program() - startup_prog = Program() - scope = core.Scope() - with executor.scope_guard(scope): - with program_guard(prog, startup_prog): - with unique_name.guard(): - np_inp = np.array([[1.0, 2.0], [3.0, 4.0]], dtype=np.float32) - inp = layers.data( - name="inp", shape=[2, 2], append_batch_size=False) - simple_layer = SimpleLayer("simple_layer") - out = simple_layer(inp) - param_grads = backward.append_backward( - out, parameter_list=[simple_layer._fc1._w.name])[0] - exe = executor.Executor(core.CPUPlace( - ) if not core.is_compiled_with_cuda() else core.CUDAPlace(0)) - exe.run(default_startup_program()) - exe.run(feed={inp.name: np_inp}, - fetch_list=[out.name, param_grads[1].name]) - - print( - "Your Paddle Fluid is installed successfully! Let's start deep Learning with Paddle Fluid now!" - ) + + device_list = [] + if core.is_compiled_with_cuda(): + try: + core.get_cuda_device_count() + except Exception as e: + logging.warning( + "You are using GPU version Paddle Fluid, But Your CUDA Device is not set properly" + "\n Original Error is {}".format(e)) + return 0 + device_list = cuda_places() + else: + device_list = [core.CPUPlace(), core.CPUPlace()] + + np_inp_single = np.array([[1.0, 2.0], [3.0, 4.0]], dtype=np.float32) + inp = [] + for i in range(len(device_list)): + inp.append(np_inp_single) + np_inp_muti = np.array(inp) + np_inp_muti = np_inp_muti.reshape(len(device_list), 2, 2) + + def test_parallerl_exe(): + train_prog = Program() + startup_prog = Program() + scope = core.Scope() + with executor.scope_guard(scope): + with program_guard(train_prog, startup_prog): + with unique_name.guard(): + build_strategy = compiler.BuildStrategy() + build_strategy.enable_inplace = True + build_strategy.memory_optimize = True + inp = layers.data(name="inp", shape=[2, 2]) + simple_layer = SimpleLayer("simple_layer") + out = simple_layer(inp) + exe = executor.Executor( + core.CUDAPlace(0) if core.is_compiled_with_cuda() and + (core.get_cuda_device_count() > 0) else core.CPUPlace()) + loss = layers.mean(out) + loss.persistable = True + optimizer.SGD(learning_rate=0.01).minimize(loss) + startup_prog.random_seed = 1 + compiled_prog = compiler.CompiledProgram( + train_prog).with_data_parallel( + build_strategy=build_strategy, + loss_name=loss.name, + places=device_list) + exe.run(startup_prog) + + exe.run(compiled_prog, + feed={inp.name: np_inp_muti}, + fetch_list=[loss.name]) + + def test_simple_exe(): + train_prog = Program() + startup_prog = Program() + scope = core.Scope() + with executor.scope_guard(scope): + with program_guard(train_prog, startup_prog): + with unique_name.guard(): + inp0 = layers.data( + name="inp", shape=[2, 2], append_batch_size=False) + simple_layer0 = SimpleLayer("simple_layer") + out0 = simple_layer0(inp0) + param_grads = backward.append_backward( + out0, parameter_list=[simple_layer0._fc1._w.name])[0] + exe0 = executor.Executor( + core.CUDAPlace(0) if core.is_compiled_with_cuda() and + (core.get_cuda_device_count() > 0) else core.CPUPlace()) + exe0.run(startup_prog) + exe0.run(feed={inp0.name: np_inp_single}, + fetch_list=[out0.name, param_grads[1].name]) + + test_simple_exe() + + print("Your Paddle Fluid works well on SINGLE GPU or CPU.") + try: + test_parallerl_exe() + print("Your Paddle Fluid works well on MUTIPLE GPU or CPU.") + print( + "Your Paddle Fluid is installed successfully! Let's start deep Learning with Paddle Fluid now" + ) + except Exception as e: + logging.warning( + "Your Paddle Fluid has some problem with multiple GPU. This may be caused by:" + "\n 1. There is only 1 or 0 GPU visible on your Device;" + "\n 2. No.1 or No.2 GPU or both of them are occupied now" + "\n 3. Wrong installation of NVIDIA-NCCL2, please follow instruction on https://github.com/NVIDIA/nccl-tests " + "\n to test your NCCL, or reinstall it following https://docs.nvidia.com/deeplearning/sdk/nccl-install-guide/index.html" + ) + + print("\n Original Error is: {}".format(e)) + print( + "Your Paddle Fluid is installed successfully ONLY for SINGLE GPU or CPU! " + "\n Let's start deep Learning with Paddle Fluid now") -- GitLab