* 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>
123 lines
4.9 KiB
Plaintext
123 lines
4.9 KiB
Plaintext
/*******************************************************************************
|
|
* 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
|
|
// @author Yurii Shyrma (iuriish@yahoo.com)
|
|
|
|
#ifndef PAIRWISE_CU
|
|
#define PAIRWISE_CU
|
|
|
|
|
|
#include "../pairwise_transform.h"
|
|
|
|
|
|
using namespace simdOps;
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
template <typename X, typename Y, typename Z, typename OpType>
|
|
__global__ static void pairwiseSimpleShaped(void* vx, Nd4jLong *xShapeInfo,
|
|
void *vy, Nd4jLong *yShapeInfo,
|
|
void *vz, Nd4jLong *zShapeInfo,
|
|
void *vextraParams) {
|
|
|
|
auto x = reinterpret_cast<X*>(vx);
|
|
auto y = reinterpret_cast<Y*>(vy);
|
|
auto z = reinterpret_cast<Z*>(vz);
|
|
auto extraParams = reinterpret_cast<Z*>(vextraParams);
|
|
|
|
int tid = blockIdx.x * blockDim.x + threadIdx.x;
|
|
|
|
__shared__ int xEws;
|
|
__shared__ int yEws;
|
|
__shared__ int zEws;
|
|
__shared__ char xOrder;
|
|
__shared__ char yOrder;
|
|
__shared__ char zOrder;
|
|
__shared__ Nd4jLong len;
|
|
|
|
if (threadIdx.x == 0) {
|
|
|
|
xEws = shape::elementWiseStride(xShapeInfo);
|
|
yEws = shape::elementWiseStride(yShapeInfo);
|
|
zEws = shape::elementWiseStride(zShapeInfo);
|
|
xOrder = shape::order(xShapeInfo);
|
|
yOrder = shape::order(yShapeInfo);
|
|
zOrder = shape::order(zShapeInfo);
|
|
len = shape::length(xShapeInfo);
|
|
}
|
|
__syncthreads();
|
|
|
|
|
|
if (xEws >= 1 && yEws >= 1 && zEws >= 1 && xOrder == yOrder && xOrder == zOrder) {
|
|
for (Nd4jLong i = tid; i < len; i += gridDim.x * blockDim.x) {
|
|
z[i * zEws] = OpType::op(x[i * xEws], y[i * yEws], extraParams);
|
|
}
|
|
}
|
|
else if (vx == vz) {
|
|
for (Nd4jLong i = tid; i < len; i += gridDim.x * blockDim.x) {
|
|
auto xOffset = shape::getIndexOffset(i, xShapeInfo, len);
|
|
auto yOffset = shape::getIndexOffset(i, yShapeInfo, len);
|
|
|
|
z[xOffset] = OpType::op(x[xOffset], y[yOffset], extraParams);
|
|
}
|
|
}
|
|
else {
|
|
for (Nd4jLong i = tid; i < len; i += gridDim.x * blockDim.x) {
|
|
auto xOffset = shape::getIndexOffset(i, xShapeInfo, len);
|
|
auto yOffset = shape::getIndexOffset(i, yShapeInfo, len);
|
|
auto zOffset = shape::getIndexOffset(i, zShapeInfo, len);
|
|
|
|
z[zOffset] = OpType::op(x[xOffset], y[yOffset], extraParams);
|
|
}
|
|
}
|
|
}
|
|
|
|
namespace functions {
|
|
namespace pairwise_transforms {
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
template<typename X, typename Y, typename Z>
|
|
template<typename OpType>
|
|
void __host__ PairWiseTransform<X,Y,Z>::intermediateShaped(dim3& launchDims, cudaStream_t *stream,
|
|
void *vx, Nd4jLong *xShapeInfo,
|
|
void *vy, Nd4jLong *yShapeInfo,
|
|
void *vz, Nd4jLong *zShapeInfo,
|
|
void *vextraParams){
|
|
|
|
pairwiseSimpleShaped<X, Y, Z, OpType><<<launchDims.x, launchDims.y, launchDims.z, *stream>>>(vx, xShapeInfo, vy, yShapeInfo, vz, zShapeInfo, vextraParams);
|
|
}
|
|
|
|
////////////////////////////////////////////////////////////////////////////////
|
|
template<typename X, typename Y, typename Z>
|
|
void __host__ PairWiseTransform<X,Y,Z>::executeCudaShaped(dim3& launchDims, cudaStream_t *stream, int opNum, void *vx, Nd4jLong *xShapeInfo, void *vy, Nd4jLong *yShapeInfo, void *vz, Nd4jLong *zShapeInfo, void *vextraParams) {
|
|
DISPATCH_BY_OPNUM_TTT(intermediateShaped, PARAMS(launchDims, stream, vx, xShapeInfo, vy, yShapeInfo, vz, zShapeInfo, vextraParams), PAIRWISE_TRANSFORM_OPS);
|
|
}
|
|
|
|
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_0);
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_1);
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_2);
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_3);
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_4);
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_5);
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_6);
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_7);
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_8);
|
|
BUILD_PAIRWISE_TEMPLATE(template class ND4J_EXPORT PairWiseTransform, , PAIRWISE_TYPES_9);
|
|
}
|
|
}
|
|
|
|
#endif // PAIRWISE_CU |