raver119 3c4e959e21 [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>
2019-08-05 11:27:05 +10:00

125 lines
5.8 KiB
C++

/*******************************************************************************
* Copyright (c) 2015-2019 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
******************************************************************************/
// lstmBlock: Full LSTM layer in one op
// @author Alex Black
//
#include <op_boilerplate.h>
#if NOT_EXCLUDED(OP_lstmBlock)
#include <ops/declarable/CustomOperations.h>
#include<ops/declarable/helpers/lstmBlock.h>
namespace nd4j {
namespace ops {
//////////////////////////////////////////////////////////////////////////
CUSTOM_OP_IMPL(lstmBlock, 9, 7, false, 2, 2) {
auto maxTSLength = INPUT_VARIABLE(0);
auto x = INPUT_VARIABLE(1); // input [seqLen, bS, nIn] at time t
auto cLast = INPUT_VARIABLE(2); // previous cell state [bS, nOut], time t-1
auto yLast = INPUT_VARIABLE(3); // previous output [bS, nOut], time t-1
auto W = INPUT_VARIABLE(4); // Weights - concatenated (input-to-hidden, hidden-to-hidden weights) weights, [(nIn+nOut), 4*nOut]
auto Wci = INPUT_VARIABLE(5); // weights - cell peephole (t-1) connections to input modulation gate, [nOut]
auto Wcf = INPUT_VARIABLE(6); // weights - cell peephole (t-1) connections to forget gate, [nOut]
auto Wco = INPUT_VARIABLE(7); // weights - cell peephole (t) connections to output gate, [nOut]
auto b = INPUT_VARIABLE(8); // biases, [4*nOut]
auto i = OUTPUT_VARIABLE(0); // Output - input modulation gate activations [seqLen, bS, nOut]
auto c = OUTPUT_VARIABLE(1); // Activations, cell state (pre tanh) [seqLen, bs, nOut]
auto f = OUTPUT_VARIABLE(2); // Output - forget gate activations [seqLen, bs, nOut]
auto o = OUTPUT_VARIABLE(3); // Output - output gate activations [seqLen, bs, nOut]
auto z = OUTPUT_VARIABLE(4); // Output - input gate activations [seqLen, bs, nOut]
auto h = OUTPUT_VARIABLE(5); // Cell state, post tanh [seqLen, bs, nOut]
auto y = OUTPUT_VARIABLE(6); // current cell output [seqLen, bS, numProj], time t
const int peephole = INT_ARG(0); // if 1, provide peephole connections
const int dataFormat = INT_ARG(1); // 0=TNS=[seqLen,bS,nIn]; 1=NST=[bS,nIn,seqLen]; 2=NTS=[bS,seqLen,nIn]
const double forgetBias = T_ARG(0);
const double clippingCellValue = T_ARG(1); // clipping value for ct, if it is not equal to zero, then cell state is clipped
REQUIRE_TRUE(x->rankOf()==3, 0, "lstmBlock: Input array 1 (x) rank must be got input with rank %i", x->rankOf());
REQUIRE_TRUE(cLast->rankOf()==2 && yLast->rankOf()==2, 0, "lstmBlock: Input ranks must be 2 for inputs 2/3 (cLast, yLast) - got %i, %i", cLast->rankOf(), yLast->rankOf());
REQUIRE_TRUE(W->rankOf()==2, 0, "lstmBlock: Weights array rank must be 2");
REQUIRE_TRUE(b->rankOf()==1, 0, "lstmBlock: Biases must be rank 1");
REQUIRE_TRUE(i->rankOf()==3 && c->rankOf()==3 && f->rankOf()==3 && o->rankOf()==3 && z->rankOf()==3 && h->rankOf()==3 && y->rankOf()==3,
0, "lstmBlock: Output arrays must all be rank 3");
helpers::lstmBlockTimeLoop(maxTSLength, x, cLast, yLast, W, Wci, Wcf, Wco, b, i, c, f, o, z, h, y, {(double)peephole, forgetBias, clippingCellValue}, dataFormat);
return Status::OK();
}
DECLARE_TYPES(lstmBlock) {
getOpDescriptor()
->setAllowedInputTypes(nd4j::DataType::ANY)
->setAllowedOutputTypes({ALL_FLOATS});
}
DECLARE_SHAPE_FN(lstmBlock) {
auto x = inputShape->at(1);
auto cLast = inputShape->at(2);
auto yLast = inputShape->at(3);
auto W = inputShape->at(4);
auto b = inputShape->at(8);
REQUIRE_TRUE(shape::rank(x)==3, 0, "lstmBlock: Input array 1 (x) rank must be got input with rank %i", shape::rank(x));
REQUIRE_TRUE(shape::rank(cLast)==2 && shape::rank(yLast)==2, 0, "lstmBlock: Input ranks must be 2 for inputs 2/3 (cLast, yLast) - got %i, %i", shape::rank(cLast), shape::rank(yLast));
REQUIRE_TRUE(shape::rank(W)==2, 0, "lstmBlock: Weights array rank must be 2");
REQUIRE_TRUE(shape::rank(b)==1, 0, "lstmBlock: Biases must be rank 1");
const int dataFormat = INT_ARG(1); // 0=TNS=[seqLen,bS,size]; 1=NST=[bS,size,seqLen]; 2=NTS=[bS,seqLen,size]
int bs;
int t;
int nOut = cLast[2]; //rank, bs, nOut, ...]
Nd4jLong *s(nullptr);
ALLOCATE(s, block.getWorkspace(), shape::shapeInfoLength(3), Nd4jLong); // [time, bS, nOut]
s[0] = 3;
if(dataFormat == 0){
//[rank, seqLen, bs, nIn, ...]
s[1] = x[1]; //seqLen
s[2] = x[2]; //bS
s[3] = nOut;
} else if(dataFormat==1){
//[rank, bs, nIn, seqLen, ...]
s[1] = x[1]; //bS
s[2] = nOut;
s[3] = x[3]; //seqLen
} else {
//[rank, bs, seqLen, nIn, ...]
s[1] = x[1]; //bS
s[2] = x[2]; //seqLen
s[3] = nOut;
}
ShapeUtils::updateStridesAndType(s, x, 'c');
Nd4jLong *s1 = CONSTANT(s);
//7 outputs, all same shape/type
return SHAPELIST(s1, s1, s1, s1, s1, s1, s1);
}
}
}
#endif