2019-06-06 14:21:15 +02:00
|
|
|
/*******************************************************************************
|
|
|
|
|
* Copyright (c) 2015-2018 Skymind, Inc.
|
|
|
|
|
*
|
|
|
|
|
* 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 <NDArray.h>
|
|
|
|
|
#include <NDArrayFactory.h>
|
|
|
|
|
#include <Context.h>
|
|
|
|
|
#include <Node.h>
|
|
|
|
|
#include <graph/Variable.h>
|
|
|
|
|
#include <graph/VariableSpace.h>
|
|
|
|
|
#include <specials_cuda.h>
|
|
|
|
|
#include <TAD.h>
|
|
|
|
|
#include <MmulHelper.h>
|
|
|
|
|
|
|
|
|
|
#include <cuda.h>
|
|
|
|
|
|
|
|
|
|
using namespace nd4j;
|
|
|
|
|
using namespace nd4j::graph;
|
|
|
|
|
|
|
|
|
|
class CudaBasicsTests2 : public testing::Test {
|
|
|
|
|
public:
|
|
|
|
|
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
TEST_F(CudaBasicsTests2, test_devices_1) {
|
|
|
|
|
auto caps = Environment::getInstance()->capabilities();
|
|
|
|
|
ASSERT_FALSE(caps.empty());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_1) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray b('f', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {0.1, 0.3, 0.5, 2.5, 2.7, 2.9, 4.9, 5.1, 5.3, 7.3, 7.5, 7.7, 9.7, 9.9, 10.1}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
// c.printIndexedBuffer();
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_2) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray b('f', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray exp('f', {M,N}, {-1.6, -0.7, 0.2, -0.8, 0.1, 1., -0., 0.9, 1.8, 0.8, 1.7, 2.6, 1.6, 2.5, 3.4}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_3) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {-1.9, -0.9, 0.1, 1.3, 0.3, -0.7, -0.7, 0.3, 1.3, 0.1, -0.9, -1.9, 0.5, 1.5, 2.5}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_4) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray b('f', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {0.1, 2.5, 4.9, 7.3, 9.7,0.3, 2.7, 5.1, 7.5, 9.9,0.5, 2.9, 5.3, 7.7, 10.1}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// NDArray* pA = a.permute({1,0});
|
|
|
|
|
// NDArray* pB = b.permute({1,0});
|
|
|
|
|
// NDArray* pC = c.permute({1,0});
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
// nd4j::MmulHelper::mmul(pB, pA, pC, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
// ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
|
|
|
|
|
// delete pA;
|
|
|
|
|
// delete pB;
|
|
|
|
|
// delete pC;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_5) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {-8.8, -4.3, 0.2, 8.6, 4.1, -0.4, -8.4, -3.9, 0.6, 8.2, 3.7, -0.8, -8.0, -3.5, 1.}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_6) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray b('f', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-1.6, -0.8, -0.0, 0.8, 1.6, -0.7, 0.1, 0.9, 1.7, 2.5, 0.2, 1.0, 1.8, 2.6, 3.4}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_7) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-1.9, 1.3, -0.7, 0.1, 0.5, -0.9, 0.3, 0.3, -0.9, 1.5, 0.1, -0.7, 1.3, -1.9, 2.5}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_8) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-8.8, 8.6, -8.4, 8.2, -8.0, -4.3, 4.1, -3.9, 3.7, -3.5, 0.2, -0.4, 0.6, -0.8, 1.}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_9) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-8.8, 8.6, -8.4, 8.2, -8.0, -4.3, 4.1, -3.9, 3.7, -3.5, 0.2, -0.4, 0.6, -0.8, 1.}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_10) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray b('f', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {0.1, 0.3, 0.5, 2.5, 2.7, 2.9, 4.9, 5.1, 5.3, 7.3, 7.5, 7.7, 9.7, 9.9, 10.1}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
// c.printIndexedBuffer();
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_11) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {-1.9, -0.9, 0.1, 1.3, 0.3, -0.7, -0.7, 0.3, 1.3, 0.1, -0.9, -1.9, 0.5, 1.5, 2.5}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_12) {
|
|
|
|
|
|
|
|
|
|
int devCnt = 0;
|
|
|
|
|
cudaGetDevice(&devCnt);
|
|
|
|
|
if(Environment::getInstance()->capabilities()[devCnt].first() < 5) return;
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 4;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 4;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.,2,3,4,5,6,7,8,9,2,3,2,1,0,4,7.}, nd4j::DataType::INT8);
|
|
|
|
|
NDArray b('f', {K,N}, {-2,-3,0,1,5,-6,7,-8,9,-1,2,-2,3,-4,5,-6.}, nd4j::DataType::INT8);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray exp('f', {M,N}, {-16., -22., -23., -25., 30., -12., -38., -70., 20., 16., 18., 18., 22., -8., -28., -52.}, nd4j::DataType::FLOAT32);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-08-28 17:27:08 +02:00
|
|
|
// c.printBuffer();
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_13) {
|
|
|
|
|
|
|
|
|
|
int devCnt = 0;
|
|
|
|
|
cudaGetDevice(&devCnt);
|
|
|
|
|
if(Environment::getInstance()->capabilities()[devCnt].first() < 5) return;
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.,2,3,4,5,6,7,8,9,10,11,12}, nd4j::DataType::INT8);
|
|
|
|
|
NDArray b('c', {K,N}, {-2,-3,0,1,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::INT8);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {-109., -122., -135., 111., 120., 129., -121., -134., -147., 129., 144., 159., -130., -140., -150.}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_14) {
|
|
|
|
|
|
|
|
|
|
int devCnt = 0;
|
|
|
|
|
cudaGetDevice(&devCnt);
|
|
|
|
|
if(Environment::getInstance()->capabilities()[devCnt].first() < 5) return;
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.,2,3,4,5,6,7,8,9,10,11,12}, nd4j::DataType::INT8);
|
|
|
|
|
NDArray b('c', {K,N}, {-2,-3,0,1,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::INT8);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray exp('c', {M,N}, {-45., 43., -49., 53., -50., -97., 79., -101., 113., -90., -149., 115., -153., 173., -130.}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_15) {
|
|
|
|
|
|
|
|
|
|
int devCnt = 0;
|
|
|
|
|
cudaGetDevice(&devCnt);
|
|
|
|
|
if(Environment::getInstance()->capabilities()[devCnt].first() < 5) return;
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray b('f', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {0.1, 0.3, 0.5, 2.5, 2.7, 2.9, 4.9, 5.1, 5.3, 7.3, 7.5, 7.7, 9.7, 9.9, 10.1}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
// c.printBuffer();
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 0.01));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_16) {
|
|
|
|
|
|
|
|
|
|
int devCnt = 0;
|
|
|
|
|
cudaGetDevice(&devCnt);
|
|
|
|
|
if(Environment::getInstance()->capabilities()[devCnt].first() < 5) return;
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {-1.9, -0.9, 0.1, 1.3, 0.3, -0.7, -0.7, 0.3, 1.3, 0.1, -0.9, -1.9, 0.5, 1.5, 2.5}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 0.01));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_17) {
|
|
|
|
|
|
|
|
|
|
int devCnt = 0;
|
|
|
|
|
cudaGetDevice(&devCnt);
|
|
|
|
|
if(Environment::getInstance()->capabilities()[devCnt].first() < 5) return;
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-8.8, 8.6, -8.4, 8.2, -8.0, -4.3, 4.1, -3.9, 3.7, -3.5, 0.2, -0.4, 0.6, -0.8, 1.}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 0.01));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_18) {
|
|
|
|
|
|
|
|
|
|
int devCnt = 0;
|
|
|
|
|
cudaGetDevice(&devCnt);
|
|
|
|
|
if(Environment::getInstance()->capabilities()[devCnt].first() < 5.3) return;
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray b('f', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::HALF);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {0.1, 0.3, 0.5, 2.5, 2.7, 2.9, 4.9, 5.1, 5.3, 7.3, 7.5, 7.7, 9.7, 9.9, 10.1}, nd4j::DataType::HALF);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 1e-1));
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_19) {
|
|
|
|
|
|
|
|
|
|
int devCnt = 0;
|
|
|
|
|
cudaGetDevice(&devCnt);
|
|
|
|
|
if(Environment::getInstance()->capabilities()[devCnt].first() < 5.3) return;
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::HALF);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {-1.9, -0.9, 0.1, 1.3, 0.3, -0.7, -0.7, 0.3, 1.3, 0.1, -0.9, -1.9, 0.5, 1.5, 2.5}, nd4j::DataType::HALF);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 1e-1));
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_20) {
|
|
|
|
|
|
|
|
|
|
int devCnt = 0;
|
|
|
|
|
cudaGetDevice(&devCnt);
|
|
|
|
|
if(Environment::getInstance()->capabilities()[devCnt].first() < 5.3) return;
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::HALF);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-8.8, 8.6, -8.4, 8.2, -8.0, -4.3, 4.1, -3.9, 3.7, -3.5, 0.2, -0.4, 0.6, -0.8, 1.}, nd4j::DataType::HALF);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 1e-1));
|
|
|
|
|
}
|
[WIP] multi-device support (#80)
* fix pad javadoc and @see links. (#72)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* [WIP] More fixes (#73)
* special tests for ConstantTadHelper/ConstantShapeHelper
Signed-off-by: raver119 <raver119@gmail.com>
* release methods for data buffers
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary TadPack C++/Java side (#74)
Signed-off-by: raver119 <raver119@gmail.com>
* Zoo model TF import test updates (#75)
* argLine fix, update compression_gru comment
* updated comment for xception
* undid but commented argLine change
* updated xlnet comment
* copyright headers
* - new NDArray methods like()/ulike() (#77)
- fix for depthwise_conv2d_bp + special test
Signed-off-by: raver119 <raver119@gmail.com>
* upsampling2d fix CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* DL4J trace logging (#79)
* MLN/CG trace logging for debugging
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tiny tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* strided_slice_bp shape fn leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff fixes and naming (#78)
* remove SDVariable inplace methods
* import methods
* npe fix in OpVal
* removed SameDiff inplace ops from tests
* Naming updates, moved to centralized methods in SameDiff, should use op_#:# for everything
* quick fixes
* javadoc
* SDVariable eval with placeholders
* use regex match
* better matching
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* fix javadoc. (#76)
* fix javadoc.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace most @see with @link s.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* 4 additional tests
Signed-off-by: raver119 <raver119@gmail.com>
* launch context reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* per-device LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* Various DL4J/ND4J fixes (#81)
* #7954 Force refresh of UI when switching tabs on overview page
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8017 Concurrent modification exception (synchronize) fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8033 Don't initialize updater in middle of writing memory crash dump
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8208 Fix shape checks for ND4J int[] creator methods
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6385 #7992 Keras import naming fixes + cleanup
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8016 Upsampling3D - add NDHWC format support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Refactor NativeOps.h to export C functions
* Actually export functions from NativeOps.h
* Adapt the Java wrappers in ND4J generated with JavaCPP
* Create C wrappers for some of the C++ classes currently used by ND4J
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* remove duplicate code in createBufferDetached. (#83)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Keras model import - updater lr fix (#84)
* Keras model import - updater lr fix
Signed-off-by: eraly <susan.eraly@gmail.com>
* Keras model import - updater lr fix, cleanup
Signed-off-by: eraly <susan.eraly@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Fix functions of OpaqueVariablesSet
* thread-local buffers/affinity
Signed-off-by: raver119 <raver119@gmail.com>
* thread safety for LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* more of thread safety
Signed-off-by: raver119 <raver119@gmail.com>
* one more multi threaded test
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff Convolution Config validation, better output methods (#82)
* Conv Config validation & tests
Signed-off-by: Ryan Nett <rnett@skymind.io>
* stackOutputs utility method
Signed-off-by: Ryan Nett <rnett@skymind.io>
* use constructor for validation, support negative kernel sizes (infered from weights)
Signed-off-by: Ryan Nett <rnett@skymind.io>
* better output methods
Signed-off-by: Ryan Nett <rnett@skymind.io>
* move output to be with fit and evaluate
Signed-off-by: Ryan Nett <rnett@skymind.io>
* fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* more fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* refactor duplicate code from pad methods. (#86)
* refactor duplicate code from pad methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace switch with if.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes and improvements (#87)
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6488 ElementWiseVertex broadcast support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Constructors and broadcast supported it Transforms.max/min
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8054 ElementWiseVertex now supports broadcast inputs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8057 Nd4j.create overload dtype fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7551 ND4J Shape validation fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Numpy boolean import (#91)
* numpy bool type
Signed-off-by: raver119 <raver119@gmail.com>
* numpy bool java side
Signed-off-by: raver119 <raver119@gmail.com>
* remove create method with unused parameter. (#89)
* remove create method with unused parameter.
* removed more unused methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* removing more unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* last removal of unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* remove createSparse methods. (#92)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes (#90)
* Deprecate Old*Op instances
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8063 #8054 Broadcast exceptions + cleanup inplace ops
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Remove bad test condition
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7993 Fix shape function issue in crop_and_resize op
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* DL4J SameDiff lambda layer fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8029 Fix for pnorm backprop math
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8038 Fix Op profiler NaN/Inf triggering + add tests (#93)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* createUninitializedDetached refactoring. (#94)
* wip
* update interface, add null implementations.
* Breaking one test in a weird way.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* createUninitializedDetached refactored.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* cuda build fix for issues introduced by recent refactoring
Signed-off-by: raver119 <raver119@gmail.com>
* [WIP] More of CUDA (#95)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* Implementation of hashcode cuda helper. Working edition.
* Fixed parallel test input arangements.
* Fixed tests for hashcode op.
* Fixed shape calculation for image:crop_and_resize op and test.
* NativeOps tests. Initial test suite.
* Added tests for indexReduce methods.
* Added test on execBroadcast with NDArray as dimensions.
* Added test on execBroadcastBool with NDArray as dimensions.
* Added tests on execPairwiseTransform and execPairwiseTransofrmBool.
* Added tests for execReduce with scalar results.
* Added reduce tests for non-empty dims array.
* Added tests for reduce3.
* Added tests for execScalar.
* Added tests for execSummaryStats.
* - provide cpu/cuda code for batch_to_space
- testing it
Signed-off-by: Yurii <yurii@skymind.io>
* - remove old test for batch_to_space (had wrong format and numbers were not checked)
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed complilation errors with test.
* Added test for execTransformFloat.
* Added test for execTransformSame.
* Added test for execTransformBool.
* Added test for execTransformStrict.
* Added tests for execScalar/execScalarBool with TADs.
* Added test for flatten.
* - provide cpu/cuda code for space_to_Batch operaion
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for concat.
* comment unnecessary stuff in s_t_b
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for specialConcat.
* Added tests for memcpy/set routines.
* Fixed pullRow cuda test.
* Added pullRow test.
* Added average test.
* - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...)
Signed-off-by: Yurii <yurii@skymind.io>
* - debugging and fixing cuda tests in JavaInteropTests file
Signed-off-by: Yurii <yurii@skymind.io>
* - correct some tests
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for shuffle.
* Fixed ops declarations.
* Restored omp and added shuffle test.
* Added convertTypes test.
* Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps.
* Added sort tests.
* Added tests for execCustomOp.
* - further debuging and fixing tests terminated with crash
Signed-off-by: Yurii <yurii@skymind.io>
* Added tests for calculateOutputShapes.
* Addded Benchmarks test.
* Commented benchmark tests.
* change assertion
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for apply_sgd op. Added cpu helper for that op.
* Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps.
* Added test for assign broadcastable.
* Added tests for assign_bp op.
* Added tests for axpy op.
* - assign/execScalar/execTransformAny signature change
- minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed axpy op.
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* - fix tests for nativeOps::concat
Signed-off-by: Yurii <yurii@skymind.io>
* sequential transform/scalar
Signed-off-by: raver119 <raver119@gmail.com>
* allow nested parallelism
Signed-off-by: raver119 <raver119@gmail.com>
* assign_bp leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* block setRNG fix
Signed-off-by: raver119 <raver119@gmail.com>
* enable parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* enable nested parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* Added cuda implementation for row_count helper.
* Added implementation for tnse gains op helper.
* - take into account possible situations when input arrays are empty in reduce_ cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces.
* Added kernel for tsne/symmetrized op heleper.
* Implementation of tsne/symmetrized op cuda helper. Working edition.
* Eliminated waste printfs.
* Added test for broadcastgradientargs op.
* host-only fallback for empty reduce float
Signed-off-by: raver119 <raver119@gmail.com>
* - some tests fixes
Signed-off-by: Yurii <yurii@skymind.io>
* - correct the rest of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* - further correction of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for Cbow op. Also added cuda implementation for cbow helpers.
* - improve code of stack operation for scalar case
Signed-off-by: Yurii <yurii@skymind.io>
* - provide cuda kernel for gatherND operation
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of cbow helpers with cuda kernels.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* - further correction of cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implementatation of cbow op helper with cuda kernels. Working edition.
* Skip random testing for cudablas case.
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for ELU and ELU_BP ops.
* Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops.
* Added tests for neq_scalar.
* Added test for noop.
* - further work on clipbynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* - get rid of concat op call, use instead direct concat helper call
Signed-off-by: Yurii <yurii@skymind.io>
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for lrelu and lrelu_bp.
* Added tests for selu and selu_bp.
* Fixed lrelu derivative helpers.
* - some corrections in lstm
Signed-off-by: Yurii <yurii@skymind.io>
* operator * result shape fix
Signed-off-by: raver119 <raver119@gmail.com>
* - correct typo in lstmCell
Signed-off-by: Yurii <yurii@skymind.io>
* few tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA inverse broadcast bool fix
Signed-off-by: raver119 <raver119@gmail.com>
* disable MMAP test for CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* BooleanOp syncToDevice
Signed-off-by: raver119 <raver119@gmail.com>
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* additional data types for im2col/col2im
Signed-off-by: raver119 <raver119@gmail.com>
* Added test for firas_sparse op.
* one more RandomBuffer test excluded
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for flatten op.
* Added test for Floor op.
* bunch of tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* mmulDot tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Implemented floordiv_bp op and tests.
* Fixed scalar case with cuda implementation for bds.
* - work on cuda kernel for clip_by_norm backprop op is completed
Signed-off-by: Yurii <yurii@skymind.io>
* Eliminate cbow crach.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminated abortion with batched nlp test.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed shared flag initializing.
* disabled bunch of cpu workspaces tests
Signed-off-by: raver119 <raver119@gmail.com>
* scalar operators fix: missing registerSpecialUse call
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed logdet for cuda and tests.
* - correct clipBynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed crop_and_resize shape datatype.
* - correct some mmul tests
Signed-off-by: Yurii <yurii@skymind.io>
* build fix
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI (#97)
Signed-off-by: raver119 <raver119@gmail.com>
* temporary stack fix
Signed-off-by: raver119 <raver119@gmail.com>
* round robin affinity test
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy CudaContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy ContextPool classes/methods
Signed-off-by: raver119 <raver119@gmail.com>
* one legacy test removed
Signed-off-by: raver119 <raver119@gmail.com>
* few more fields rearranged
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext++
Signed-off-by: raver119 <raver119@gmail.com>
* more of OpaqueLaunchContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext -> CudaContext
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handles
Signed-off-by: raver119 <raver119@gmail.com>
* typo
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver method
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handle propagated
Signed-off-by: raver119 <raver119@gmail.com>
* blas/solver handles
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* legacy concat implementations replaced with new CustomOp
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* concat now uses way more blocks
Signed-off-by: raver119 <raver119@gmail.com>
* print
Signed-off-by: raver119 <raver119@gmail.com>
* no more triple template mmul
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bitonic sort reorganized
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* type conversions moved to generic impl
Signed-off-by: raver119 <raver119@gmail.com>
* cpu data types pass
Signed-off-by: raver119 <raver119@gmail.com>
* non_max_suppression
Signed-off-by: raver119 <raver119@gmail.com>
* sortByValue fix
Signed-off-by: raver119 <raver119@gmail.com>
* ignore all mixed datatype tests for mmul
Signed-off-by: raver119 <raver119@gmail.com>
* special handling of OpProfiler exceptions
Signed-off-by: raver119 <raver119@gmail.com>
* - one failing concat test in cpp
- Nd4j.tile now uses op internally
Signed-off-by: raver119 <raver119@gmail.com>
* get back dtype exception for legacy arrays deserialization
Signed-off-by: raver119 <raver119@gmail.com>
2019-08-14 15:52:34 +02:00
|
|
|
/*
|
2019-06-06 14:21:15 +02:00
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_21) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.,2,3,4,5,6,7,8,9,10,11,12}, nd4j::DataType::INT8);
|
|
|
|
|
NDArray b('c', {K,N}, {-2,-3,0,1,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-45., 43., -49., 53., -50., -97., 79., -101., 113., -90., -149., 115., -153., 173., -130.}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_22) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.,2,3,4,5,6,7,8,9,10,11,12}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray b('c', {K,N}, {-2,-3,0,1,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-45., 43., -49., 53., -50., -97., 79., -101., 113., -90., -149., 115., -153., 173., -130.}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
|
|
|
|
// c.printBuffer();
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_23) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-8.8, 8.6, -8.4, 8.2, -8.0, -4.3, 4.1, -3.9, 3.7, -3.5, 0.2, -0.4, 0.6, -0.8, 1.}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 0.01));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_24) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-8.8, 8.6, -8.4, 8.2, -8.0, -4.3, 4.1, -3.9, 3.7, -3.5, 0.2, -0.4, 0.6, -0.8, 1.}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 0.01));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_25) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray b('c', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::HALF);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-8.8, 8.6, -8.4, 8.2, -8.0, -4.3, 4.1, -3.9, 3.7, -3.5, 0.2, -0.4, 0.6, -0.8, 1.}, nd4j::DataType::HALF);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 0.01));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_26) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
// 3x4 * 4x5 = 3x5
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray a('c', {M,K}, {1.,2,3,4,5,6,7,8,9,10,11,12}, nd4j::DataType::INT64);
|
|
|
|
|
NDArray b('c', {K,N}, {-2,-3,0,1,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray c('c', {M,N}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M,N}, {-45., 43., -49., 53., -50., -97., 79., -101., 113., -90., -149., 115., -153., 173., -130.}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
|
|
|
|
// c.printBuffer();
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_27) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('f', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::HALF);
|
|
|
|
|
NDArray b('f', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {0.1, 0.3, 0.5, 2.5, 2.7, 2.9, 4.9, 5.1, 5.3, 7.3, 7.5, 7.7, 9.7, 9.9, 10.1}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
// c.printBuffer();
|
|
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp, 0.01));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxM_28) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
|
|
|
|
const Nd4jLong K = 4;
|
|
|
|
|
const Nd4jLong N = 5;
|
|
|
|
|
|
|
|
|
|
NDArray a('c', {M,K}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray b('f', {K,N}, {1,-2,3,-4,5,-6,7,-8,9,-10,11,-12,13,-14,15,-16,17,-18,19,-20}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray c('f', {M,N}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M,N}, {-1.6, -0.7, 0.2, -0.8, 0.1, 1., -0., 0.9, 1.8, 0.8, 1.7, 2.6, 1.6, 2.5, 3.4}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &b, &c, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
ASSERT_TRUE(c.equalsTo(&exp));
|
|
|
|
|
}
|
[WIP] multi-device support (#80)
* fix pad javadoc and @see links. (#72)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* [WIP] More fixes (#73)
* special tests for ConstantTadHelper/ConstantShapeHelper
Signed-off-by: raver119 <raver119@gmail.com>
* release methods for data buffers
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary TadPack C++/Java side (#74)
Signed-off-by: raver119 <raver119@gmail.com>
* Zoo model TF import test updates (#75)
* argLine fix, update compression_gru comment
* updated comment for xception
* undid but commented argLine change
* updated xlnet comment
* copyright headers
* - new NDArray methods like()/ulike() (#77)
- fix for depthwise_conv2d_bp + special test
Signed-off-by: raver119 <raver119@gmail.com>
* upsampling2d fix CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* DL4J trace logging (#79)
* MLN/CG trace logging for debugging
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tiny tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* strided_slice_bp shape fn leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff fixes and naming (#78)
* remove SDVariable inplace methods
* import methods
* npe fix in OpVal
* removed SameDiff inplace ops from tests
* Naming updates, moved to centralized methods in SameDiff, should use op_#:# for everything
* quick fixes
* javadoc
* SDVariable eval with placeholders
* use regex match
* better matching
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* fix javadoc. (#76)
* fix javadoc.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace most @see with @link s.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* 4 additional tests
Signed-off-by: raver119 <raver119@gmail.com>
* launch context reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* per-device LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* Various DL4J/ND4J fixes (#81)
* #7954 Force refresh of UI when switching tabs on overview page
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8017 Concurrent modification exception (synchronize) fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8033 Don't initialize updater in middle of writing memory crash dump
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8208 Fix shape checks for ND4J int[] creator methods
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6385 #7992 Keras import naming fixes + cleanup
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8016 Upsampling3D - add NDHWC format support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Refactor NativeOps.h to export C functions
* Actually export functions from NativeOps.h
* Adapt the Java wrappers in ND4J generated with JavaCPP
* Create C wrappers for some of the C++ classes currently used by ND4J
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* remove duplicate code in createBufferDetached. (#83)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Keras model import - updater lr fix (#84)
* Keras model import - updater lr fix
Signed-off-by: eraly <susan.eraly@gmail.com>
* Keras model import - updater lr fix, cleanup
Signed-off-by: eraly <susan.eraly@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Fix functions of OpaqueVariablesSet
* thread-local buffers/affinity
Signed-off-by: raver119 <raver119@gmail.com>
* thread safety for LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* more of thread safety
Signed-off-by: raver119 <raver119@gmail.com>
* one more multi threaded test
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff Convolution Config validation, better output methods (#82)
* Conv Config validation & tests
Signed-off-by: Ryan Nett <rnett@skymind.io>
* stackOutputs utility method
Signed-off-by: Ryan Nett <rnett@skymind.io>
* use constructor for validation, support negative kernel sizes (infered from weights)
Signed-off-by: Ryan Nett <rnett@skymind.io>
* better output methods
Signed-off-by: Ryan Nett <rnett@skymind.io>
* move output to be with fit and evaluate
Signed-off-by: Ryan Nett <rnett@skymind.io>
* fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* more fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* refactor duplicate code from pad methods. (#86)
* refactor duplicate code from pad methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace switch with if.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes and improvements (#87)
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6488 ElementWiseVertex broadcast support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Constructors and broadcast supported it Transforms.max/min
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8054 ElementWiseVertex now supports broadcast inputs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8057 Nd4j.create overload dtype fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7551 ND4J Shape validation fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Numpy boolean import (#91)
* numpy bool type
Signed-off-by: raver119 <raver119@gmail.com>
* numpy bool java side
Signed-off-by: raver119 <raver119@gmail.com>
* remove create method with unused parameter. (#89)
* remove create method with unused parameter.
* removed more unused methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* removing more unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* last removal of unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* remove createSparse methods. (#92)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes (#90)
* Deprecate Old*Op instances
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8063 #8054 Broadcast exceptions + cleanup inplace ops
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Remove bad test condition
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7993 Fix shape function issue in crop_and_resize op
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* DL4J SameDiff lambda layer fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8029 Fix for pnorm backprop math
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8038 Fix Op profiler NaN/Inf triggering + add tests (#93)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* createUninitializedDetached refactoring. (#94)
* wip
* update interface, add null implementations.
* Breaking one test in a weird way.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* createUninitializedDetached refactored.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* cuda build fix for issues introduced by recent refactoring
Signed-off-by: raver119 <raver119@gmail.com>
* [WIP] More of CUDA (#95)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* Implementation of hashcode cuda helper. Working edition.
* Fixed parallel test input arangements.
* Fixed tests for hashcode op.
* Fixed shape calculation for image:crop_and_resize op and test.
* NativeOps tests. Initial test suite.
* Added tests for indexReduce methods.
* Added test on execBroadcast with NDArray as dimensions.
* Added test on execBroadcastBool with NDArray as dimensions.
* Added tests on execPairwiseTransform and execPairwiseTransofrmBool.
* Added tests for execReduce with scalar results.
* Added reduce tests for non-empty dims array.
* Added tests for reduce3.
* Added tests for execScalar.
* Added tests for execSummaryStats.
* - provide cpu/cuda code for batch_to_space
- testing it
Signed-off-by: Yurii <yurii@skymind.io>
* - remove old test for batch_to_space (had wrong format and numbers were not checked)
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed complilation errors with test.
* Added test for execTransformFloat.
* Added test for execTransformSame.
* Added test for execTransformBool.
* Added test for execTransformStrict.
* Added tests for execScalar/execScalarBool with TADs.
* Added test for flatten.
* - provide cpu/cuda code for space_to_Batch operaion
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for concat.
* comment unnecessary stuff in s_t_b
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for specialConcat.
* Added tests for memcpy/set routines.
* Fixed pullRow cuda test.
* Added pullRow test.
* Added average test.
* - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...)
Signed-off-by: Yurii <yurii@skymind.io>
* - debugging and fixing cuda tests in JavaInteropTests file
Signed-off-by: Yurii <yurii@skymind.io>
* - correct some tests
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for shuffle.
* Fixed ops declarations.
* Restored omp and added shuffle test.
* Added convertTypes test.
* Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps.
* Added sort tests.
* Added tests for execCustomOp.
* - further debuging and fixing tests terminated with crash
Signed-off-by: Yurii <yurii@skymind.io>
* Added tests for calculateOutputShapes.
* Addded Benchmarks test.
* Commented benchmark tests.
* change assertion
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for apply_sgd op. Added cpu helper for that op.
* Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps.
* Added test for assign broadcastable.
* Added tests for assign_bp op.
* Added tests for axpy op.
* - assign/execScalar/execTransformAny signature change
- minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed axpy op.
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* - fix tests for nativeOps::concat
Signed-off-by: Yurii <yurii@skymind.io>
* sequential transform/scalar
Signed-off-by: raver119 <raver119@gmail.com>
* allow nested parallelism
Signed-off-by: raver119 <raver119@gmail.com>
* assign_bp leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* block setRNG fix
Signed-off-by: raver119 <raver119@gmail.com>
* enable parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* enable nested parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* Added cuda implementation for row_count helper.
* Added implementation for tnse gains op helper.
* - take into account possible situations when input arrays are empty in reduce_ cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces.
* Added kernel for tsne/symmetrized op heleper.
* Implementation of tsne/symmetrized op cuda helper. Working edition.
* Eliminated waste printfs.
* Added test for broadcastgradientargs op.
* host-only fallback for empty reduce float
Signed-off-by: raver119 <raver119@gmail.com>
* - some tests fixes
Signed-off-by: Yurii <yurii@skymind.io>
* - correct the rest of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* - further correction of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for Cbow op. Also added cuda implementation for cbow helpers.
* - improve code of stack operation for scalar case
Signed-off-by: Yurii <yurii@skymind.io>
* - provide cuda kernel for gatherND operation
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of cbow helpers with cuda kernels.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* - further correction of cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implementatation of cbow op helper with cuda kernels. Working edition.
* Skip random testing for cudablas case.
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for ELU and ELU_BP ops.
* Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops.
* Added tests for neq_scalar.
* Added test for noop.
* - further work on clipbynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* - get rid of concat op call, use instead direct concat helper call
Signed-off-by: Yurii <yurii@skymind.io>
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for lrelu and lrelu_bp.
* Added tests for selu and selu_bp.
* Fixed lrelu derivative helpers.
* - some corrections in lstm
Signed-off-by: Yurii <yurii@skymind.io>
* operator * result shape fix
Signed-off-by: raver119 <raver119@gmail.com>
* - correct typo in lstmCell
Signed-off-by: Yurii <yurii@skymind.io>
* few tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA inverse broadcast bool fix
Signed-off-by: raver119 <raver119@gmail.com>
* disable MMAP test for CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* BooleanOp syncToDevice
Signed-off-by: raver119 <raver119@gmail.com>
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* additional data types for im2col/col2im
Signed-off-by: raver119 <raver119@gmail.com>
* Added test for firas_sparse op.
* one more RandomBuffer test excluded
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for flatten op.
* Added test for Floor op.
* bunch of tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* mmulDot tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Implemented floordiv_bp op and tests.
* Fixed scalar case with cuda implementation for bds.
* - work on cuda kernel for clip_by_norm backprop op is completed
Signed-off-by: Yurii <yurii@skymind.io>
* Eliminate cbow crach.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminated abortion with batched nlp test.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed shared flag initializing.
* disabled bunch of cpu workspaces tests
Signed-off-by: raver119 <raver119@gmail.com>
* scalar operators fix: missing registerSpecialUse call
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed logdet for cuda and tests.
* - correct clipBynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed crop_and_resize shape datatype.
* - correct some mmul tests
Signed-off-by: Yurii <yurii@skymind.io>
* build fix
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI (#97)
Signed-off-by: raver119 <raver119@gmail.com>
* temporary stack fix
Signed-off-by: raver119 <raver119@gmail.com>
* round robin affinity test
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy CudaContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy ContextPool classes/methods
Signed-off-by: raver119 <raver119@gmail.com>
* one legacy test removed
Signed-off-by: raver119 <raver119@gmail.com>
* few more fields rearranged
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext++
Signed-off-by: raver119 <raver119@gmail.com>
* more of OpaqueLaunchContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext -> CudaContext
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handles
Signed-off-by: raver119 <raver119@gmail.com>
* typo
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver method
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handle propagated
Signed-off-by: raver119 <raver119@gmail.com>
* blas/solver handles
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* legacy concat implementations replaced with new CustomOp
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* concat now uses way more blocks
Signed-off-by: raver119 <raver119@gmail.com>
* print
Signed-off-by: raver119 <raver119@gmail.com>
* no more triple template mmul
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bitonic sort reorganized
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* type conversions moved to generic impl
Signed-off-by: raver119 <raver119@gmail.com>
* cpu data types pass
Signed-off-by: raver119 <raver119@gmail.com>
* non_max_suppression
Signed-off-by: raver119 <raver119@gmail.com>
* sortByValue fix
Signed-off-by: raver119 <raver119@gmail.com>
* ignore all mixed datatype tests for mmul
Signed-off-by: raver119 <raver119@gmail.com>
* special handling of OpProfiler exceptions
Signed-off-by: raver119 <raver119@gmail.com>
* - one failing concat test in cpp
- Nd4j.tile now uses op internally
Signed-off-by: raver119 <raver119@gmail.com>
* get back dtype exception for legacy arrays deserialization
Signed-off-by: raver119 <raver119@gmail.com>
2019-08-14 15:52:34 +02:00
|
|
|
*/
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_1) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x('f', {N}, {1,-2,3,-4}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M}, {0.1, 0.3, 0.5}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_2) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x('f', {N}, {1,-2,3,-4}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M}, {-1.6, -0.7, 0.2}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_3) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x('c', {N}, {1,-2,3,-4}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M}, {-1.6, -0.7, 0.2}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_4) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x('c', {N}, {1,-2,3,-4}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray y('c', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M}, {-1.6, -0.7, 0.2}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_5) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x('c', {N}, {1,-2,3,-4}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray y('c', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
NDArray exp('c', {M}, {0.1, 0.3, 0.5}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_6) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray temp('f', {M,N,5}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray x = temp(6, {0,2});
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {5.5, 5.1, 4.7}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_7) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {M,N,5}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray x = temp(6, {0,2});
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {5.1, 3.3, 1.5}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-08-02 19:01:03 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_8) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {N,M,5}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x = temp(4, {1,2});
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {6.2, 4.5, 1.7}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_9) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray x = temp(3, {0,1});
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {1.5, 1.8, 1.5}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_10) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray x = temp(2, {0,1});
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {-0.3, 0.3, 0.9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_11) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('c', {5,N,M}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray x = temp(13, {0,2});
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {-12.1, -10.9, -9.7}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_12) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('c', {5,N,M}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray x = temp(10, {0,2});
|
|
|
|
|
NDArray y('c', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('c', {M}, {3.3, 3.3, 3.3}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-08-02 19:01:03 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_13) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray x = temp(2, {0,1}, true);
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {-0.3, 0.3, 0.9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_14) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('c', {5,N,M}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray x = temp(10, {0,2}, true);
|
|
|
|
|
NDArray y('c', {M}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('c', {M}, {3.3, 3.3, 3.3}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-08-02 19:01:03 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
2019-06-06 14:21:15 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_15) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x = temp(2, {0,1});
|
|
|
|
|
NDArray y = temp(17, {0,2});
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {-0.3, 0.3, 0.9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_16) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray temp1('c', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x = temp(2, {0,1});
|
|
|
|
|
NDArray y = temp1(17, {0,2});
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('c', {M}, {-0.3, 0.3, 0.9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_17) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x = temp(2, {0,1});
|
|
|
|
|
NDArray y = temp(17, {0,2}, true);
|
|
|
|
|
// y.printShapeInfo();
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {1,M,1}, {-0.3, 0.3, 0.9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_18) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::DOUBLE);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray temp1('c', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x = temp(2, {0,1},true);
|
|
|
|
|
NDArray y = temp1(17, {0,2},true);
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('c', {1,M,1}, {-0.3, 0.3, 0.9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
[WIP] multi-device support (#80)
* fix pad javadoc and @see links. (#72)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* [WIP] More fixes (#73)
* special tests for ConstantTadHelper/ConstantShapeHelper
Signed-off-by: raver119 <raver119@gmail.com>
* release methods for data buffers
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary TadPack C++/Java side (#74)
Signed-off-by: raver119 <raver119@gmail.com>
* Zoo model TF import test updates (#75)
* argLine fix, update compression_gru comment
* updated comment for xception
* undid but commented argLine change
* updated xlnet comment
* copyright headers
* - new NDArray methods like()/ulike() (#77)
- fix for depthwise_conv2d_bp + special test
Signed-off-by: raver119 <raver119@gmail.com>
* upsampling2d fix CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* DL4J trace logging (#79)
* MLN/CG trace logging for debugging
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tiny tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* strided_slice_bp shape fn leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff fixes and naming (#78)
* remove SDVariable inplace methods
* import methods
* npe fix in OpVal
* removed SameDiff inplace ops from tests
* Naming updates, moved to centralized methods in SameDiff, should use op_#:# for everything
* quick fixes
* javadoc
* SDVariable eval with placeholders
* use regex match
* better matching
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* fix javadoc. (#76)
* fix javadoc.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace most @see with @link s.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* 4 additional tests
Signed-off-by: raver119 <raver119@gmail.com>
* launch context reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* per-device LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* Various DL4J/ND4J fixes (#81)
* #7954 Force refresh of UI when switching tabs on overview page
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8017 Concurrent modification exception (synchronize) fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8033 Don't initialize updater in middle of writing memory crash dump
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8208 Fix shape checks for ND4J int[] creator methods
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6385 #7992 Keras import naming fixes + cleanup
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8016 Upsampling3D - add NDHWC format support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Refactor NativeOps.h to export C functions
* Actually export functions from NativeOps.h
* Adapt the Java wrappers in ND4J generated with JavaCPP
* Create C wrappers for some of the C++ classes currently used by ND4J
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* remove duplicate code in createBufferDetached. (#83)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Keras model import - updater lr fix (#84)
* Keras model import - updater lr fix
Signed-off-by: eraly <susan.eraly@gmail.com>
* Keras model import - updater lr fix, cleanup
Signed-off-by: eraly <susan.eraly@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Fix functions of OpaqueVariablesSet
* thread-local buffers/affinity
Signed-off-by: raver119 <raver119@gmail.com>
* thread safety for LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* more of thread safety
Signed-off-by: raver119 <raver119@gmail.com>
* one more multi threaded test
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff Convolution Config validation, better output methods (#82)
* Conv Config validation & tests
Signed-off-by: Ryan Nett <rnett@skymind.io>
* stackOutputs utility method
Signed-off-by: Ryan Nett <rnett@skymind.io>
* use constructor for validation, support negative kernel sizes (infered from weights)
Signed-off-by: Ryan Nett <rnett@skymind.io>
* better output methods
Signed-off-by: Ryan Nett <rnett@skymind.io>
* move output to be with fit and evaluate
Signed-off-by: Ryan Nett <rnett@skymind.io>
* fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* more fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* refactor duplicate code from pad methods. (#86)
* refactor duplicate code from pad methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace switch with if.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes and improvements (#87)
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6488 ElementWiseVertex broadcast support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Constructors and broadcast supported it Transforms.max/min
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8054 ElementWiseVertex now supports broadcast inputs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8057 Nd4j.create overload dtype fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7551 ND4J Shape validation fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Numpy boolean import (#91)
* numpy bool type
Signed-off-by: raver119 <raver119@gmail.com>
* numpy bool java side
Signed-off-by: raver119 <raver119@gmail.com>
* remove create method with unused parameter. (#89)
* remove create method with unused parameter.
* removed more unused methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* removing more unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* last removal of unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* remove createSparse methods. (#92)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes (#90)
* Deprecate Old*Op instances
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8063 #8054 Broadcast exceptions + cleanup inplace ops
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Remove bad test condition
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7993 Fix shape function issue in crop_and_resize op
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* DL4J SameDiff lambda layer fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8029 Fix for pnorm backprop math
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8038 Fix Op profiler NaN/Inf triggering + add tests (#93)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* createUninitializedDetached refactoring. (#94)
* wip
* update interface, add null implementations.
* Breaking one test in a weird way.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* createUninitializedDetached refactored.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* cuda build fix for issues introduced by recent refactoring
Signed-off-by: raver119 <raver119@gmail.com>
* [WIP] More of CUDA (#95)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* Implementation of hashcode cuda helper. Working edition.
* Fixed parallel test input arangements.
* Fixed tests for hashcode op.
* Fixed shape calculation for image:crop_and_resize op and test.
* NativeOps tests. Initial test suite.
* Added tests for indexReduce methods.
* Added test on execBroadcast with NDArray as dimensions.
* Added test on execBroadcastBool with NDArray as dimensions.
* Added tests on execPairwiseTransform and execPairwiseTransofrmBool.
* Added tests for execReduce with scalar results.
* Added reduce tests for non-empty dims array.
* Added tests for reduce3.
* Added tests for execScalar.
* Added tests for execSummaryStats.
* - provide cpu/cuda code for batch_to_space
- testing it
Signed-off-by: Yurii <yurii@skymind.io>
* - remove old test for batch_to_space (had wrong format and numbers were not checked)
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed complilation errors with test.
* Added test for execTransformFloat.
* Added test for execTransformSame.
* Added test for execTransformBool.
* Added test for execTransformStrict.
* Added tests for execScalar/execScalarBool with TADs.
* Added test for flatten.
* - provide cpu/cuda code for space_to_Batch operaion
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for concat.
* comment unnecessary stuff in s_t_b
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for specialConcat.
* Added tests for memcpy/set routines.
* Fixed pullRow cuda test.
* Added pullRow test.
* Added average test.
* - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...)
Signed-off-by: Yurii <yurii@skymind.io>
* - debugging and fixing cuda tests in JavaInteropTests file
Signed-off-by: Yurii <yurii@skymind.io>
* - correct some tests
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for shuffle.
* Fixed ops declarations.
* Restored omp and added shuffle test.
* Added convertTypes test.
* Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps.
* Added sort tests.
* Added tests for execCustomOp.
* - further debuging and fixing tests terminated with crash
Signed-off-by: Yurii <yurii@skymind.io>
* Added tests for calculateOutputShapes.
* Addded Benchmarks test.
* Commented benchmark tests.
* change assertion
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for apply_sgd op. Added cpu helper for that op.
* Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps.
* Added test for assign broadcastable.
* Added tests for assign_bp op.
* Added tests for axpy op.
* - assign/execScalar/execTransformAny signature change
- minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed axpy op.
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* - fix tests for nativeOps::concat
Signed-off-by: Yurii <yurii@skymind.io>
* sequential transform/scalar
Signed-off-by: raver119 <raver119@gmail.com>
* allow nested parallelism
Signed-off-by: raver119 <raver119@gmail.com>
* assign_bp leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* block setRNG fix
Signed-off-by: raver119 <raver119@gmail.com>
* enable parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* enable nested parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* Added cuda implementation for row_count helper.
* Added implementation for tnse gains op helper.
* - take into account possible situations when input arrays are empty in reduce_ cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces.
* Added kernel for tsne/symmetrized op heleper.
* Implementation of tsne/symmetrized op cuda helper. Working edition.
* Eliminated waste printfs.
* Added test for broadcastgradientargs op.
* host-only fallback for empty reduce float
Signed-off-by: raver119 <raver119@gmail.com>
* - some tests fixes
Signed-off-by: Yurii <yurii@skymind.io>
* - correct the rest of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* - further correction of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for Cbow op. Also added cuda implementation for cbow helpers.
* - improve code of stack operation for scalar case
Signed-off-by: Yurii <yurii@skymind.io>
* - provide cuda kernel for gatherND operation
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of cbow helpers with cuda kernels.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* - further correction of cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implementatation of cbow op helper with cuda kernels. Working edition.
* Skip random testing for cudablas case.
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for ELU and ELU_BP ops.
* Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops.
* Added tests for neq_scalar.
* Added test for noop.
* - further work on clipbynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* - get rid of concat op call, use instead direct concat helper call
Signed-off-by: Yurii <yurii@skymind.io>
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for lrelu and lrelu_bp.
* Added tests for selu and selu_bp.
* Fixed lrelu derivative helpers.
* - some corrections in lstm
Signed-off-by: Yurii <yurii@skymind.io>
* operator * result shape fix
Signed-off-by: raver119 <raver119@gmail.com>
* - correct typo in lstmCell
Signed-off-by: Yurii <yurii@skymind.io>
* few tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA inverse broadcast bool fix
Signed-off-by: raver119 <raver119@gmail.com>
* disable MMAP test for CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* BooleanOp syncToDevice
Signed-off-by: raver119 <raver119@gmail.com>
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* additional data types for im2col/col2im
Signed-off-by: raver119 <raver119@gmail.com>
* Added test for firas_sparse op.
* one more RandomBuffer test excluded
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for flatten op.
* Added test for Floor op.
* bunch of tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* mmulDot tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Implemented floordiv_bp op and tests.
* Fixed scalar case with cuda implementation for bds.
* - work on cuda kernel for clip_by_norm backprop op is completed
Signed-off-by: Yurii <yurii@skymind.io>
* Eliminate cbow crach.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminated abortion with batched nlp test.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed shared flag initializing.
* disabled bunch of cpu workspaces tests
Signed-off-by: raver119 <raver119@gmail.com>
* scalar operators fix: missing registerSpecialUse call
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed logdet for cuda and tests.
* - correct clipBynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed crop_and_resize shape datatype.
* - correct some mmul tests
Signed-off-by: Yurii <yurii@skymind.io>
* build fix
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI (#97)
Signed-off-by: raver119 <raver119@gmail.com>
* temporary stack fix
Signed-off-by: raver119 <raver119@gmail.com>
* round robin affinity test
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy CudaContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy ContextPool classes/methods
Signed-off-by: raver119 <raver119@gmail.com>
* one legacy test removed
Signed-off-by: raver119 <raver119@gmail.com>
* few more fields rearranged
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext++
Signed-off-by: raver119 <raver119@gmail.com>
* more of OpaqueLaunchContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext -> CudaContext
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handles
Signed-off-by: raver119 <raver119@gmail.com>
* typo
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver method
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handle propagated
Signed-off-by: raver119 <raver119@gmail.com>
* blas/solver handles
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* legacy concat implementations replaced with new CustomOp
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* concat now uses way more blocks
Signed-off-by: raver119 <raver119@gmail.com>
* print
Signed-off-by: raver119 <raver119@gmail.com>
* no more triple template mmul
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bitonic sort reorganized
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* type conversions moved to generic impl
Signed-off-by: raver119 <raver119@gmail.com>
* cpu data types pass
Signed-off-by: raver119 <raver119@gmail.com>
* non_max_suppression
Signed-off-by: raver119 <raver119@gmail.com>
* sortByValue fix
Signed-off-by: raver119 <raver119@gmail.com>
* ignore all mixed datatype tests for mmul
Signed-off-by: raver119 <raver119@gmail.com>
* special handling of OpProfiler exceptions
Signed-off-by: raver119 <raver119@gmail.com>
* - one failing concat test in cpp
- Nd4j.tile now uses op internally
Signed-off-by: raver119 <raver119@gmail.com>
* get back dtype exception for legacy arrays deserialization
Signed-off-by: raver119 <raver119@gmail.com>
2019-08-14 15:52:34 +02:00
|
|
|
/*
|
2019-06-06 14:21:15 +02:00
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_19) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray x('f', {N}, {1,-2,3,-4}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
NDArray exp('f', {M}, {0.1, 0.3, 0.5}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_20) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray x('f', {N}, {1,-2,3,-4}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray exp('f', {M}, {-1.6, -0.7, 0.2}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_21) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray x('c', {N}, {1,-2,3,-4}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray y('c', {M}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray exp('c', {M}, {-1.6, -0.7, 0.2}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_22) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray temp('f', {M,N,5}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x = temp(6, {0,2});
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::FLOAT32);
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {5.5, 5.1, 4.7}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_23) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray x = temp(3, {0,1});
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {1.5, 1.8, 1.5}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_24) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray temp('f', {M,N,5}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x = temp(6, {0,2},true);
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::FLOAT32);
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {5.5, 5.1, 4.7}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_25) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('f', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray x = temp(3, {0,1}, true);
|
|
|
|
|
NDArray y('f', {M}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {1.5, 1.8, 1.5}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_26) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray temp1('c', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray x = temp(2, {0,1});
|
|
|
|
|
NDArray y = temp1(17, {0,2});
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('c', {M}, {-0.3, 0.3, 0.9}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_27) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {N,M}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
a.permutei({1,0});
|
|
|
|
|
NDArray temp('f', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray temp1('c', {5,M,N}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray x = temp(2, {0,1},true);
|
|
|
|
|
NDArray y = temp1(17, {0,2},true);
|
2019-08-02 19:01:03 +02:00
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('c', {1,M,1}, {-0.3, 0.3, 0.9}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulMxV_28) {
|
|
|
|
|
|
|
|
|
|
const Nd4jLong M = 3;
|
2019-08-02 19:01:03 +02:00
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray a('c', {M,N}, {1.2,1.1,1.0,0.9,0.8,0.7,0.5,0.4,0.3,0.2,0.1,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray temp('f', {M,N,5}, {16,2,-6,7,2,-2,4,-7,6,4,4,6,-3,1,3,9,1,4,9,10,-10,-3,-8,7,-7,-7,6,9,7,-6,8,7,-3,-3,4,-2,5,-3,-3,4,6,-5,-1,7,-5,4,-10,-1,8,0,-7,4,-10,-7,-8,-9,2,9,7,9}, nd4j::DataType::DOUBLE);
|
|
|
|
|
NDArray x = temp(6, {0,2});
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray y('f', {M}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
2019-06-06 14:21:15 +02:00
|
|
|
NDArray exp('f', {M}, {5.1, 3.3, 1.5}, nd4j::DataType::FLOAT32);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&a, &x, &y, 1., 0.);
|
|
|
|
|
ASSERT_TRUE(y.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulDot_1) {
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray x('c', {N}, {1, 2, 3, 4}, nd4j::DataType::INT32);
|
|
|
|
|
NDArray y('f', {N}, {0.1, 0.2, 0.3, 0.4}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray z(nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
|
NDArray exp('c', {}, {3}, nd4j::DataType::DOUBLE);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&x, &y, &z);
|
|
|
|
|
ASSERT_TRUE(z.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulDot_2) {
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray x('c', {1,1,N}, {1,2, 3, 4}, nd4j::DataType::INT32);
|
|
|
|
|
NDArray y('f', {1,1,N,1,1,1}, {0.1, 0.2, 0.3, 0.4}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray z(nd4j::DataType::DOUBLE);
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
|
NDArray exp('c', {}, {3}, nd4j::DataType::DOUBLE);
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&x, &y, &z);
|
|
|
|
|
ASSERT_TRUE(z.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulDot_3) {
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray xBig('c', {4,2}, {1, 0, 2, 0, 3, 0, 4, 0}, nd4j::DataType::INT32);
|
|
|
|
|
NDArray yBig('c', {4,3}, {0.1, 0, 0, 0.2, 0, 0, 0.3, 0, 0, 0.4, 0,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray x = xBig(0, {1}, true);
|
|
|
|
|
NDArray y = yBig(0, {1}, true);
|
|
|
|
|
NDArray z(nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray exp('c', {}, {3}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&x, &y, &z);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(z.equalsTo(&exp));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
//////////////////////////////////////////////////////////////////////////
|
|
|
|
|
TEST_F(CudaBasicsTests2, mmulDot_4) {
|
2019-08-02 19:01:03 +02:00
|
|
|
|
|
|
|
|
const Nd4jLong N = 4;
|
2019-06-06 14:21:15 +02:00
|
|
|
|
|
|
|
|
NDArray xBig('f', {4,2}, {1, 2, 3, 4, 0, 0, 0, 0}, nd4j::DataType::INT32);
|
|
|
|
|
NDArray yBig('c', {4,3}, {0.1, 0, 0, 0.2, 0, 0, 0.3, 0, 0, 0.4, 0,0}, nd4j::DataType::FLOAT32);
|
|
|
|
|
NDArray x = xBig(0, {1}, true);
|
|
|
|
|
NDArray y = yBig(0, {1});
|
|
|
|
|
NDArray z(nd4j::DataType::DOUBLE);
|
|
|
|
|
|
2019-08-02 19:01:03 +02:00
|
|
|
NDArray exp('c', {}, {3}, nd4j::DataType::DOUBLE);
|
|
|
|
|
|
|
|
|
|
nd4j::MmulHelper::mmul(&x, &y, &z);
|
2019-06-06 14:21:15 +02:00
|
|
|
ASSERT_TRUE(z.equalsTo(&exp));
|
[WIP] multi-device support (#80)
* fix pad javadoc and @see links. (#72)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* [WIP] More fixes (#73)
* special tests for ConstantTadHelper/ConstantShapeHelper
Signed-off-by: raver119 <raver119@gmail.com>
* release methods for data buffers
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary buffer Java side
Signed-off-by: raver119 <raver119@gmail.com>
* delete temporary TadPack C++/Java side (#74)
Signed-off-by: raver119 <raver119@gmail.com>
* Zoo model TF import test updates (#75)
* argLine fix, update compression_gru comment
* updated comment for xception
* undid but commented argLine change
* updated xlnet comment
* copyright headers
* - new NDArray methods like()/ulike() (#77)
- fix for depthwise_conv2d_bp + special test
Signed-off-by: raver119 <raver119@gmail.com>
* upsampling2d fix CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* DL4J trace logging (#79)
* MLN/CG trace logging for debugging
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Tiny tweak
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* strided_slice_bp shape fn leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff fixes and naming (#78)
* remove SDVariable inplace methods
* import methods
* npe fix in OpVal
* removed SameDiff inplace ops from tests
* Naming updates, moved to centralized methods in SameDiff, should use op_#:# for everything
* quick fixes
* javadoc
* SDVariable eval with placeholders
* use regex match
* better matching
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* fix javadoc. (#76)
* fix javadoc.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace most @see with @link s.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* 4 additional tests
Signed-off-by: raver119 <raver119@gmail.com>
* launch context reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext reorganization
Signed-off-by: raver119 <raver119@gmail.com>
* per-device LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* Various DL4J/ND4J fixes (#81)
* #7954 Force refresh of UI when switching tabs on overview page
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8017 Concurrent modification exception (synchronize) fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8033 Don't initialize updater in middle of writing memory crash dump
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8208 Fix shape checks for ND4J int[] creator methods
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6385 #7992 Keras import naming fixes + cleanup
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8016 Upsampling3D - add NDHWC format support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Refactor NativeOps.h to export C functions
* Actually export functions from NativeOps.h
* Adapt the Java wrappers in ND4J generated with JavaCPP
* Create C wrappers for some of the C++ classes currently used by ND4J
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* remove duplicate code in createBufferDetached. (#83)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Keras model import - updater lr fix (#84)
* Keras model import - updater lr fix
Signed-off-by: eraly <susan.eraly@gmail.com>
* Keras model import - updater lr fix, cleanup
Signed-off-by: eraly <susan.eraly@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* ContextBuffers as separate entity
Signed-off-by: raver119 <raver119@gmail.com>
* Fix functions of OpaqueVariablesSet
* thread-local buffers/affinity
Signed-off-by: raver119 <raver119@gmail.com>
* thread safety for LaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* more of thread safety
Signed-off-by: raver119 <raver119@gmail.com>
* one more multi threaded test
Signed-off-by: raver119 <raver119@gmail.com>
* SameDiff Convolution Config validation, better output methods (#82)
* Conv Config validation & tests
Signed-off-by: Ryan Nett <rnett@skymind.io>
* stackOutputs utility method
Signed-off-by: Ryan Nett <rnett@skymind.io>
* use constructor for validation, support negative kernel sizes (infered from weights)
Signed-off-by: Ryan Nett <rnett@skymind.io>
* better output methods
Signed-off-by: Ryan Nett <rnett@skymind.io>
* move output to be with fit and evaluate
Signed-off-by: Ryan Nett <rnett@skymind.io>
* fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* more fixes
Signed-off-by: Ryan Nett <rnett@skymind.io>
* refactor duplicate code from pad methods. (#86)
* refactor duplicate code from pad methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* replace switch with if.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes and improvements (#87)
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Reshape and reallocate - small fixes
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #6488 ElementWiseVertex broadcast support
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Constructors and broadcast supported it Transforms.max/min
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8054 ElementWiseVertex now supports broadcast inputs
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8057 Nd4j.create overload dtype fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7551 ND4J Shape validation fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* [WIP] Numpy boolean import (#91)
* numpy bool type
Signed-off-by: raver119 <raver119@gmail.com>
* numpy bool java side
Signed-off-by: raver119 <raver119@gmail.com>
* remove create method with unused parameter. (#89)
* remove create method with unused parameter.
* removed more unused methods.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* removing more unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* last removal of unused code.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* remove createSparse methods. (#92)
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* Various ND4J/DL4J fixes (#90)
* Deprecate Old*Op instances
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8063 #8054 Broadcast exceptions + cleanup inplace ops
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Small fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* Remove bad test condition
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #7993 Fix shape function issue in crop_and_resize op
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* DL4J SameDiff lambda layer fix
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8029 Fix for pnorm backprop math
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* #8038 Fix Op profiler NaN/Inf triggering + add tests (#93)
Signed-off-by: AlexDBlack <blacka101@gmail.com>
* createUninitializedDetached refactoring. (#94)
* wip
* update interface, add null implementations.
* Breaking one test in a weird way.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* createUninitializedDetached refactored.
Signed-off-by: Robert Altena <Rob@Ra-ai.com>
* cuda build fix for issues introduced by recent refactoring
Signed-off-by: raver119 <raver119@gmail.com>
* [WIP] More of CUDA (#95)
* initial commit
Signed-off-by: raver119 <raver119@gmail.com>
* Implementation of hashcode cuda helper. Working edition.
* Fixed parallel test input arangements.
* Fixed tests for hashcode op.
* Fixed shape calculation for image:crop_and_resize op and test.
* NativeOps tests. Initial test suite.
* Added tests for indexReduce methods.
* Added test on execBroadcast with NDArray as dimensions.
* Added test on execBroadcastBool with NDArray as dimensions.
* Added tests on execPairwiseTransform and execPairwiseTransofrmBool.
* Added tests for execReduce with scalar results.
* Added reduce tests for non-empty dims array.
* Added tests for reduce3.
* Added tests for execScalar.
* Added tests for execSummaryStats.
* - provide cpu/cuda code for batch_to_space
- testing it
Signed-off-by: Yurii <yurii@skymind.io>
* - remove old test for batch_to_space (had wrong format and numbers were not checked)
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed complilation errors with test.
* Added test for execTransformFloat.
* Added test for execTransformSame.
* Added test for execTransformBool.
* Added test for execTransformStrict.
* Added tests for execScalar/execScalarBool with TADs.
* Added test for flatten.
* - provide cpu/cuda code for space_to_Batch operaion
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for concat.
* comment unnecessary stuff in s_t_b
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for specialConcat.
* Added tests for memcpy/set routines.
* Fixed pullRow cuda test.
* Added pullRow test.
* Added average test.
* - correct typo in NDArray::applyPairwiseTransform(nd4j::pairwise::BoolOps op...)
Signed-off-by: Yurii <yurii@skymind.io>
* - debugging and fixing cuda tests in JavaInteropTests file
Signed-off-by: Yurii <yurii@skymind.io>
* - correct some tests
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for shuffle.
* Fixed ops declarations.
* Restored omp and added shuffle test.
* Added convertTypes test.
* Added tests for execRandom. Eliminated usage of RandomBuffer with NativeOps.
* Added sort tests.
* Added tests for execCustomOp.
* - further debuging and fixing tests terminated with crash
Signed-off-by: Yurii <yurii@skymind.io>
* Added tests for calculateOutputShapes.
* Addded Benchmarks test.
* Commented benchmark tests.
* change assertion
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for apply_sgd op. Added cpu helper for that op.
* Implement cuda helper for aplly_sgd op. Fixed tests for NativeOps.
* Added test for assign broadcastable.
* Added tests for assign_bp op.
* Added tests for axpy op.
* - assign/execScalar/execTransformAny signature change
- minor test fix
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed axpy op.
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* - fix tests for nativeOps::concat
Signed-off-by: Yurii <yurii@skymind.io>
* sequential transform/scalar
Signed-off-by: raver119 <raver119@gmail.com>
* allow nested parallelism
Signed-off-by: raver119 <raver119@gmail.com>
* assign_bp leak fix
Signed-off-by: raver119 <raver119@gmail.com>
* block setRNG fix
Signed-off-by: raver119 <raver119@gmail.com>
* enable parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* enable nested parallelism by default
Signed-off-by: raver119 <raver119@gmail.com>
* Added cuda implementation for row_count helper.
* Added implementation for tnse gains op helper.
* - take into account possible situations when input arrays are empty in reduce_ cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implemented tsne/edge_forces op cuda-based helper. Parallelized cpu-based helper for edge_forces.
* Added kernel for tsne/symmetrized op heleper.
* Implementation of tsne/symmetrized op cuda helper. Working edition.
* Eliminated waste printfs.
* Added test for broadcastgradientargs op.
* host-only fallback for empty reduce float
Signed-off-by: raver119 <raver119@gmail.com>
* - some tests fixes
Signed-off-by: Yurii <yurii@skymind.io>
* - correct the rest of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* - further correction of reduce_ stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Added test for Cbow op. Also added cuda implementation for cbow helpers.
* - improve code of stack operation for scalar case
Signed-off-by: Yurii <yurii@skymind.io>
* - provide cuda kernel for gatherND operation
Signed-off-by: Yurii <yurii@skymind.io>
* Implementation of cbow helpers with cuda kernels.
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* minor tests tweaks
Signed-off-by: raver119 <raver119@gmail.com>
* - further correction of cuda stuff
Signed-off-by: Yurii <yurii@skymind.io>
* Implementatation of cbow op helper with cuda kernels. Working edition.
* Skip random testing for cudablas case.
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for ELU and ELU_BP ops.
* Added tests for eq_scalar, gt_scalar, gte_scalar and lte_scalar ops.
* Added tests for neq_scalar.
* Added test for noop.
* - further work on clipbynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* - get rid of concat op call, use instead direct concat helper call
Signed-off-by: Yurii <yurii@skymind.io>
* lstmBlockCell context fix
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for lrelu and lrelu_bp.
* Added tests for selu and selu_bp.
* Fixed lrelu derivative helpers.
* - some corrections in lstm
Signed-off-by: Yurii <yurii@skymind.io>
* operator * result shape fix
Signed-off-by: raver119 <raver119@gmail.com>
* - correct typo in lstmCell
Signed-off-by: Yurii <yurii@skymind.io>
* few tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* CUDA inverse broadcast bool fix
Signed-off-by: raver119 <raver119@gmail.com>
* disable MMAP test for CUDA
Signed-off-by: raver119 <raver119@gmail.com>
* BooleanOp syncToDevice
Signed-off-by: raver119 <raver119@gmail.com>
* meh
Signed-off-by: raver119 <raver119@gmail.com>
* additional data types for im2col/col2im
Signed-off-by: raver119 <raver119@gmail.com>
* Added test for firas_sparse op.
* one more RandomBuffer test excluded
Signed-off-by: raver119 <raver119@gmail.com>
* Added tests for flatten op.
* Added test for Floor op.
* bunch of tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* mmulDot tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Implemented floordiv_bp op and tests.
* Fixed scalar case with cuda implementation for bds.
* - work on cuda kernel for clip_by_norm backprop op is completed
Signed-off-by: Yurii <yurii@skymind.io>
* Eliminate cbow crach.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Eliminated abortion with batched nlp test.
* more tests fixed
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed shared flag initializing.
* disabled bunch of cpu workspaces tests
Signed-off-by: raver119 <raver119@gmail.com>
* scalar operators fix: missing registerSpecialUse call
Signed-off-by: raver119 <raver119@gmail.com>
* Fixed logdet for cuda and tests.
* - correct clipBynorm_bp
Signed-off-by: Yurii <yurii@skymind.io>
* Fixed crop_and_resize shape datatype.
* - correct some mmul tests
Signed-off-by: Yurii <yurii@skymind.io>
* build fix
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI
Signed-off-by: raver119 <raver119@gmail.com>
* exclude two methods for JNI (#97)
Signed-off-by: raver119 <raver119@gmail.com>
* temporary stack fix
Signed-off-by: raver119 <raver119@gmail.com>
* round robin affinity test
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy CudaContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* get rid of legacy ContextPool classes/methods
Signed-off-by: raver119 <raver119@gmail.com>
* one legacy test removed
Signed-off-by: raver119 <raver119@gmail.com>
* few more fields rearranged
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext
Signed-off-by: raver119 <raver119@gmail.com>
* OpaqueLaunchContext++
Signed-off-by: raver119 <raver119@gmail.com>
* more of OpaqueLaunchContext methods
Signed-off-by: raver119 <raver119@gmail.com>
* LaunchContext -> CudaContext
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* AffinityManger changes
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handles
Signed-off-by: raver119 <raver119@gmail.com>
* typo
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver method
Signed-off-by: raver119 <raver119@gmail.com>
* cusolver handle propagated
Signed-off-by: raver119 <raver119@gmail.com>
* blas/solver handles
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* legacy concat implementations replaced with new CustomOp
Signed-off-by: raver119 <raver119@gmail.com>
* one more test
Signed-off-by: raver119 <raver119@gmail.com>
* concat now uses way more blocks
Signed-off-by: raver119 <raver119@gmail.com>
* print
Signed-off-by: raver119 <raver119@gmail.com>
* no more triple template mmul
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of kernels have dtypes reconsidered
Signed-off-by: raver119 <raver119@gmail.com>
* bitonic sort reorganized
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* bunch of cpu stuff removed from cuda scope
Signed-off-by: raver119 <raver119@gmail.com>
* type conversions moved to generic impl
Signed-off-by: raver119 <raver119@gmail.com>
* cpu data types pass
Signed-off-by: raver119 <raver119@gmail.com>
* non_max_suppression
Signed-off-by: raver119 <raver119@gmail.com>
* sortByValue fix
Signed-off-by: raver119 <raver119@gmail.com>
* ignore all mixed datatype tests for mmul
Signed-off-by: raver119 <raver119@gmail.com>
* special handling of OpProfiler exceptions
Signed-off-by: raver119 <raver119@gmail.com>
* - one failing concat test in cpp
- Nd4j.tile now uses op internally
Signed-off-by: raver119 <raver119@gmail.com>
* get back dtype exception for legacy arrays deserialization
Signed-off-by: raver119 <raver119@gmail.com>
2019-08-14 15:52:34 +02:00
|
|
|
}
|
|
|
|
|
*/
|
