cavis/libnd4j/tests_cpu/layers_tests/DataBufferTestsCuda.cu

89 lines
3.3 KiB
Plaintext
Raw Normal View History

[WIP] Memory limits (#167) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one more initial commit Signed-off-by: raver119 <raver119@gmail.com> * additional initial commit Signed-off-by: raver119 <raver119@gmail.com> * subsequent initial commit Signed-off-by: raver119 <raver119@gmail.com> * initial commit testing Signed-off-by: raver119 <raver119@gmail.com> * initial commit per device Signed-off-by: raver119 <raver119@gmail.com> * initial commit per group Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + few missed lines Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + missed includes Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + one more missed include Signed-off-by: raver119 <raver119@gmail.com> * initial commit shouldn't count host mem as dev0 in cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit that tracks HOST group limits for CUDA Signed-off-by: raver119 <raver119@gmail.com> * initial commit with some Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with more Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit without maxMasterThreads exception Signed-off-by: raver119 <raver119@gmail.com> * initial commit without Nd4jULong in Environment Signed-off-by: raver119 <raver119@gmail.com> * add sleep and more iterations for OOM cases Signed-off-by: raver119 <raver119@gmail.com> * limits propagation from java side Signed-off-by: raver119 <raver119@gmail.com> * - consume ErrorCode every time - one test for memory limits Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * RSub op mapping fixed Signed-off-by: raver119 <raver119@gmail.com> * typo fixed Signed-off-by: raver119 <raver119@gmail.com> * one bad test fixed Signed-off-by: raver119 <raver119@gmail.com>
2020-01-24 08:11:09 +01:00
/*******************************************************************************
* Copyright (c) 2020 Konduit K.K.
*
* This program and the accompanying materials are made available under the
* terms of the Apache License, Version 2.0 which is available at
* https://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.
*
* SPDX-License-Identifier: Apache-2.0
******************************************************************************/
//
// @author raver119@gmail.com
//
#include "testlayers.h"
#include <array/NDArray.h>
#include <graph/Context.h>
#include <graph/Node.h>
[WIP] Memory limits (#167) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one more initial commit Signed-off-by: raver119 <raver119@gmail.com> * additional initial commit Signed-off-by: raver119 <raver119@gmail.com> * subsequent initial commit Signed-off-by: raver119 <raver119@gmail.com> * initial commit testing Signed-off-by: raver119 <raver119@gmail.com> * initial commit per device Signed-off-by: raver119 <raver119@gmail.com> * initial commit per group Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + few missed lines Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + missed includes Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + one more missed include Signed-off-by: raver119 <raver119@gmail.com> * initial commit shouldn't count host mem as dev0 in cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit that tracks HOST group limits for CUDA Signed-off-by: raver119 <raver119@gmail.com> * initial commit with some Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with more Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit without maxMasterThreads exception Signed-off-by: raver119 <raver119@gmail.com> * initial commit without Nd4jULong in Environment Signed-off-by: raver119 <raver119@gmail.com> * add sleep and more iterations for OOM cases Signed-off-by: raver119 <raver119@gmail.com> * limits propagation from java side Signed-off-by: raver119 <raver119@gmail.com> * - consume ErrorCode every time - one test for memory limits Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * RSub op mapping fixed Signed-off-by: raver119 <raver119@gmail.com> * typo fixed Signed-off-by: raver119 <raver119@gmail.com> * one bad test fixed Signed-off-by: raver119 <raver119@gmail.com>
2020-01-24 08:11:09 +01:00
#include <graph/Variable.h>
#include <graph/VariableSpace.h>
#include <ops/declarable/CustomOperations.h>
#include <ops/declarable/helpers/convolutions.h>
#include <ops/declarable/helpers/col2im.h>
#include <helpers/RandomLauncher.h>
using namespace sd;
using namespace sd::graph;
using namespace sd::memory;
[WIP] Memory limits (#167) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one more initial commit Signed-off-by: raver119 <raver119@gmail.com> * additional initial commit Signed-off-by: raver119 <raver119@gmail.com> * subsequent initial commit Signed-off-by: raver119 <raver119@gmail.com> * initial commit testing Signed-off-by: raver119 <raver119@gmail.com> * initial commit per device Signed-off-by: raver119 <raver119@gmail.com> * initial commit per group Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + few missed lines Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + missed includes Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + one more missed include Signed-off-by: raver119 <raver119@gmail.com> * initial commit shouldn't count host mem as dev0 in cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit that tracks HOST group limits for CUDA Signed-off-by: raver119 <raver119@gmail.com> * initial commit with some Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with more Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit without maxMasterThreads exception Signed-off-by: raver119 <raver119@gmail.com> * initial commit without Nd4jULong in Environment Signed-off-by: raver119 <raver119@gmail.com> * add sleep and more iterations for OOM cases Signed-off-by: raver119 <raver119@gmail.com> * limits propagation from java side Signed-off-by: raver119 <raver119@gmail.com> * - consume ErrorCode every time - one test for memory limits Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * RSub op mapping fixed Signed-off-by: raver119 <raver119@gmail.com> * typo fixed Signed-off-by: raver119 <raver119@gmail.com> * one bad test fixed Signed-off-by: raver119 <raver119@gmail.com>
2020-01-24 08:11:09 +01:00
class DataBufferTestsCuda : public testing::Test {
public:
};
/*
[WIP] Memory limits (#167) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one more initial commit Signed-off-by: raver119 <raver119@gmail.com> * additional initial commit Signed-off-by: raver119 <raver119@gmail.com> * subsequent initial commit Signed-off-by: raver119 <raver119@gmail.com> * initial commit testing Signed-off-by: raver119 <raver119@gmail.com> * initial commit per device Signed-off-by: raver119 <raver119@gmail.com> * initial commit per group Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + few missed lines Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + missed includes Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + one more missed include Signed-off-by: raver119 <raver119@gmail.com> * initial commit shouldn't count host mem as dev0 in cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit that tracks HOST group limits for CUDA Signed-off-by: raver119 <raver119@gmail.com> * initial commit with some Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with more Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit without maxMasterThreads exception Signed-off-by: raver119 <raver119@gmail.com> * initial commit without Nd4jULong in Environment Signed-off-by: raver119 <raver119@gmail.com> * add sleep and more iterations for OOM cases Signed-off-by: raver119 <raver119@gmail.com> * limits propagation from java side Signed-off-by: raver119 <raver119@gmail.com> * - consume ErrorCode every time - one test for memory limits Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * RSub op mapping fixed Signed-off-by: raver119 <raver119@gmail.com> * typo fixed Signed-off-by: raver119 <raver119@gmail.com> * one bad test fixed Signed-off-by: raver119 <raver119@gmail.com>
2020-01-24 08:11:09 +01:00
TEST_F(DataBufferTestsCuda, test_alloc_limit_1) {
auto deviceId = AffinityManager::currentDeviceId();
auto odLimit = MemoryCounter::getInstance()->deviceLimit(deviceId);
auto opLimit = MemoryCounter::getInstance()->groupLimit(MemoryType::HOST);
auto osLimit = MemoryCounter::getInstance()->groupLimit(MemoryType::DEVICE);
auto odUse = MemoryCounter::getInstance()->allocatedDevice(deviceId);
auto opUse = MemoryCounter::getInstance()->allocatedGroup(MemoryType::HOST);
auto osUse = MemoryCounter::getInstance()->allocatedGroup(MemoryType::DEVICE);
auto limitSize = odUse + 150000000;
[WIP] Memory limits (#167) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one more initial commit Signed-off-by: raver119 <raver119@gmail.com> * additional initial commit Signed-off-by: raver119 <raver119@gmail.com> * subsequent initial commit Signed-off-by: raver119 <raver119@gmail.com> * initial commit testing Signed-off-by: raver119 <raver119@gmail.com> * initial commit per device Signed-off-by: raver119 <raver119@gmail.com> * initial commit per group Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + few missed lines Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + missed includes Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + one more missed include Signed-off-by: raver119 <raver119@gmail.com> * initial commit shouldn't count host mem as dev0 in cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit that tracks HOST group limits for CUDA Signed-off-by: raver119 <raver119@gmail.com> * initial commit with some Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with more Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit without maxMasterThreads exception Signed-off-by: raver119 <raver119@gmail.com> * initial commit without Nd4jULong in Environment Signed-off-by: raver119 <raver119@gmail.com> * add sleep and more iterations for OOM cases Signed-off-by: raver119 <raver119@gmail.com> * limits propagation from java side Signed-off-by: raver119 <raver119@gmail.com> * - consume ErrorCode every time - one test for memory limits Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * RSub op mapping fixed Signed-off-by: raver119 <raver119@gmail.com> * typo fixed Signed-off-by: raver119 <raver119@gmail.com> * one bad test fixed Signed-off-by: raver119 <raver119@gmail.com>
2020-01-24 08:11:09 +01:00
auto allocSize = 100000000;
MemoryCounter::getInstance()->setDeviceLimit(deviceId, odLimit + limitSize);
MemoryCounter::getInstance()->setGroupLimit(MemoryType::HOST, opLimit + limitSize);
MemoryCounter::getInstance()->setGroupLimit(MemoryType::DEVICE, osLimit + limitSize);
DataBuffer buffer(allocSize, DataType::INT32, nullptr, true);
// separately testing per-device limits and group limits
ASSERT_EQ(odUse + allocSize, MemoryCounter::getInstance()->allocatedDevice(deviceId));
ASSERT_EQ(opUse + allocSize, MemoryCounter::getInstance()->allocatedGroup(MemoryType::HOST));
ASSERT_EQ(osUse + allocSize, MemoryCounter::getInstance()->allocatedGroup(MemoryType::DEVICE));
// setting smaller limits, to make sure next allocation fails with OOM exception
MemoryCounter::getInstance()->setDeviceLimit(deviceId, allocSize - 100);
MemoryCounter::getInstance()->setGroupLimit(MemoryType::DEVICE, allocSize - 100);
// this allocation should fail, since we're allocating too much
try {
DataBuffer bufferFailed(allocSize + 1, DataType::INT32);
[WIP] Memory limits (#167) * initial commit Signed-off-by: raver119 <raver119@gmail.com> * one more initial commit Signed-off-by: raver119 <raver119@gmail.com> * additional initial commit Signed-off-by: raver119 <raver119@gmail.com> * subsequent initial commit Signed-off-by: raver119 <raver119@gmail.com> * initial commit testing Signed-off-by: raver119 <raver119@gmail.com> * initial commit per device Signed-off-by: raver119 <raver119@gmail.com> * initial commit per group Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + few missed lines Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + missed includes Signed-off-by: raver119 <raver119@gmail.com> * initial commit for cuda + one more missed include Signed-off-by: raver119 <raver119@gmail.com> * initial commit shouldn't count host mem as dev0 in cuda Signed-off-by: raver119 <raver119@gmail.com> * initial commit that tracks HOST group limits for CUDA Signed-off-by: raver119 <raver119@gmail.com> * initial commit with some Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with more Environment changes Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit with maxMasterThreads fix Signed-off-by: raver119 <raver119@gmail.com> * initial commit without maxMasterThreads exception Signed-off-by: raver119 <raver119@gmail.com> * initial commit without Nd4jULong in Environment Signed-off-by: raver119 <raver119@gmail.com> * add sleep and more iterations for OOM cases Signed-off-by: raver119 <raver119@gmail.com> * limits propagation from java side Signed-off-by: raver119 <raver119@gmail.com> * - consume ErrorCode every time - one test for memory limits Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * unordered_map Signed-off-by: raver119 <raver119@gmail.com> * RSub op mapping fixed Signed-off-by: raver119 <raver119@gmail.com> * typo fixed Signed-off-by: raver119 <raver119@gmail.com> * one bad test fixed Signed-off-by: raver119 <raver119@gmail.com>
2020-01-24 08:11:09 +01:00
ASSERT_TRUE(false);
} catch (allocation_exception &e) {
// we expect exception here
}
//
// restore original limits, so subsequent tests do not fail
MemoryCounter::getInstance()->setDeviceLimit(deviceId, odLimit);
MemoryCounter::getInstance()->setGroupLimit(MemoryType::HOST, opLimit);
MemoryCounter::getInstance()->setGroupLimit(MemoryType::DEVICE, osLimit);
}
*/