| 1da8fed77c5c296afa18f754ec3616e7f02a4cfd |
|
12-Oct-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
Pass large model operand values in shared memory.
Because of a limitation in HIDL, large tensor values (e.g. weights)
need to pass in shared memory rather than as HIDL arguments. This
prevented large models from running on a driver.
Separated the handling of memory pools so that request and model
pools are not comingled.
Also improve logging so we see more details about the models when
logging.
Bug: 67603060
Test: Ran system tests and VTS tests.
Change-Id: I760e31275699f9306c4b21945935dc3a4ca68754
/frameworks/ml/nn/common/Utils.cpp
|
| 820215d28bed6c90f696cde0f282445d16da432e |
|
05-Oct-2017 |
Miao Wang <miaowang@google.com> |
Allow fine grain verbose logging control through system property.
- Existing DEBUG and INFO change to the new mechanism, existing ERROR and
WARNING unchanged.
- By default, all verbose logging are disabled.
- setprop debug.nn.vlog 1 enables all verbose logging.
- setprop debug.nn.vlog "tag1 tag2 ..." only enable the selected tags.
- Available tags:
all: same as 1.
model: enable logging with tag MODEL.
compilation: enable logging with tag COMPILATION.
execution: enable logging with tag EXECUTION.
cpuexe: enable logging with tag CPUEXE.
manager: enable logging with tag MANAGER.
driver: enable logging with tag DRIVER.
Bug: 63905942
Test: mm
Test: NeuralNetworksTests pass
Test: manually set property to allow individual module to logging
verbosely
Test: tested with debug.nn.partition default -> 0 -> 1 to make
sure getProp still works fine
Change-Id: Iaa0ffa62176dabcdc35058748597df720fd6e47e
/frameworks/ml/nn/common/Utils.cpp
|
| 69d24339cfca4979e4f3af884c455935a9909793 |
|
04-Oct-2017 |
David Gross <dgross@google.com> |
Merge changes I04c71d70,I58b763bc into oc-mr1-dev
* changes:
Make partitioning and execution of partitioned plan the default.
Manage inter-partition temporaries.
|
| a2a03635c8f215cb75be68ff1939bf4dec285ef8 |
|
03-Oct-2017 |
David Gross <dgross@google.com> |
Make partitioning and execution of partitioned plan the default.
Also, rename the debug.nn.partition.test property to
debug.nn.partition, and slightly change the interpretation of its
values:
2: the default: partitioned execution, with a fallback to
non-partitioned execution if there is a partitioning failure
3: a new value: partitioned execution, with NO fallback to
non-partitioned execution if there is a partitioning failure
Bug: 63905942
Test: mma (user)
ml/nn/runtime/tests (user)
(no new failures, logcat looks plausible,
debug.nn.partition 0 and 3 have no effect)
mma (userdebug)
ml/nn/runtime/tests (userdebug)
(with debug.nn.partition unspecified, 0, 1, 2, and 3;
no new failures, logcat looks plausible; also tried
manually introducing failures several places in the
partitioning process to ensure that simulation/fallback
behavior works properly for different values of
debug.nn.partition)
Change-Id: I04c71d7009aa0d1c971833a2af5816ff5830ecc9
/frameworks/ml/nn/common/Utils.cpp
|
| 96811e2b1347889a25bd9686f47ca3cbf061fb1b |
|
02-Oct-2017 |
David Gross <dgross@google.com> |
Manage inter-partition temporaries.
This means: Allocate a Memory object for each TEMPORARY in the original
model that is live across partition boundaries; and tell each
StepExecutor about the mapping from a submodel input or output to the
appropriate Memory object.
With these changes, we can now fully execute multiple-partition plans.
Limitations:
- Still under control of debug.nn.partition.test property.
- Cannot handle operands of unknown size, except for model (not
submodel) inputs and outputs.
- Execution is synchronous.
Also: Teach sizeOfData() to work on scalars.
Bug: 63905942
Test: mma (user)
mma (userdebug)
ml/nn/runtime/tests (userdebug)
(with debug.nn.partition.test 0, 1, and 2;
no new failures, logcat looks plausible,
confirmed that GeneratedTests.mobilenet
runs on multiple partitions)
Change-Id: I58b763bc68bf8fe2e0306610c775b854e9292f76
/frameworks/ml/nn/common/Utils.cpp
|
| 62cc2758c1c2d303861e209f26bddcf4d7564b73 |
|
28-Sep-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
Fix problem passing null optional operands.
Allow optional operands to be specified in the model as having no value.
Modify the HAL to allow passing missing operands. Change the validation
of most operations to verify that none of their operands are missing.
Bug: 63905942
Test: Compiled and ran runtime/test.
Change-Id: I378bc51847a8fb30cb2d36c9bf707ebadc79289b
/frameworks/ml/nn/common/Utils.cpp
|
| 25f0f2dcd7049cd9f8a60133697dff114bbbf00e |
|
28-Sep-2017 |
Miao Wang <miaowang@google.com> |
Allow ADD and MUL taking quantized input.
- Implement the quant8 path for ADD and MUL.
- Add tests for quant8 ADD and MUL, both normal and broadcast version.
- Add validation for quantization parameters, forcing scale >= 0 and
zeroPoint in range [0, 255] for QUANT8_ASYMM type operands.
Bug: 63905942
Test: mm
Test: NeuralNetworksTest pass
Change-Id: Ib643217737af9624a079369e0aea792025223fbb
/frameworks/ml/nn/common/Utils.cpp
|
| e127e49e67b53c96eb79f6a9c58f956ad4761227 |
|
28-Sep-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
Moved validation to the specific classes.
It's hard to keep track of what's validated when the validations
are found in two files (NeuralNetworks.cpp + one of the other).
Move all the validations except for the initial nullptr check
to the specific file.
Moved some code from Memory.h into the .cpp file.
Adjusted some type size for setInput/Output/*
Adding new validations will be in the future CLs to make
review easier.
Bug: 63905942
Test: Ran local and VTS tests.
Change-Id: I2c448c9b0d3f2e878278f24eafce5720590403f3
/frameworks/ml/nn/common/Utils.cpp
|
| 0b9453e41a544f9c780eaa15ad65136ad4662ccb |
|
23-Sep-2017 |
David Gross <dgross@google.com> |
More debugging tools for graph partitioning.
1) Under property debug.nn.partition.test, run partitioning
algorithm fropm CompilationBuilder::finish(). We don't
use the results -- this is to produce log output and to
verify that we don't crash.
2) Add a little more LOG(DEBUG) output.
Bug: 63905942
Test: mm (userdebug and user)
Change-Id: I8f0f4477cb9a564dcd55536677687c7914a9b86e
/frameworks/ml/nn/common/Utils.cpp
|
| 7d6ac906f000f3afe418e92c0a4ae36b2ea1143e |
|
23-Sep-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
Remove operationTuple.
Removed operationTuple from Model in the HAL, as the data type was
redundant information.
Removed supportedOperationTuples from Capabilities, as real drivers need
more complex restrictions than this provided. For the OC-MR1, we'll just
rely on getSupportedNodes.
Also removed the unused cachesCompilation.
Bug: 63905942
Test: Compiled and ran tests, incl. vts.
Change-Id: I84433d1e0e5211ac2f77317f3752171d85a5ab04
/frameworks/ml/nn/common/Utils.cpp
|
| 91e8417c4c395e3922d12abfd956b93b71121976 |
|
14-Sep-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
Partition the requests to run on multiple devices.
Partition the request so that subgraphs can run on the best device.
Also respects the capabilities of a device so that we don't try
to run a device incapable to run a graph.
Bug: 63905942
Test: Compiled and ran unit tests. We'll want more advance tests.
Change-Id: I8662fa719661e5b68c47cd75703edb5937fc8f0a
/frameworks/ml/nn/common/Utils.cpp
|
| 5e7827e7bdc7ee6b6fc9b1989070c98fa10e9797 |
|
13-Sep-2017 |
David Gross <dgross@google.com> |
Move OEM codes out of NeuralNetworks.h to new file NeuralNetworksOEM.h.
Also remove FAKE_QUANT operation.
Bug: 63905942
Test: nn/runtime/tests, vts
Change-Id: Ia9262ec727f93dfe1b0ccade4ed76347c55ba163
/frameworks/ml/nn/common/Utils.cpp
|
| 5f916fc9a7ae95f172492bdfe5344c37beff3a6f |
|
12-Sep-2017 |
Michael Butler <butlermichael@google.com> |
Neuralnetworks HAL cleanup -- frameworks/ml/nn
Does three primary cleanups:
1) Removes unused OperandTypes, creates OEM types
2) Creates explicit ErrorStatus; functions return status
3) IDevice::initialize renamed to getCapabilities,
IDevice::getSupportedSubgraph renamed to getSupportedOperations
It makes the corresponding changes to the runtime.
Bug: 63905942
Test: mm, frameworks/ml/nn/runtime/test
Change-Id: I1545373dfa30780aaf9b61b3938be536cf122e74
/frameworks/ml/nn/common/Utils.cpp
|
| a4e2ee81d015b5e26897d18b18dd50044faba62f |
|
10-Sep-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
Refactor how arguments are tracked.
Use an explicit description of the lifetime of an operand
rather than relying on poolIndex to do the job.
Bug: 63905942
Test: Ran unit tests and test.py
Change-Id: I8ce007c439ccc99b1e04cce412ba6c93453c7a02
/frameworks/ml/nn/common/Utils.cpp
|
| 55cef2193279a646292fdeb355399627dd8990c8 |
|
09-Sep-2017 |
Miao Wang <miaowang@google.com> |
Explicitly add "_2D" to applicable ops, and add fused activation
function enum.
- Add the fused activation enum to explicitly set the expectation that
only the included ones are supported for fused ops.
- Add "_2D" to CONV, DEPTHWISE_CONV, AVG_POOL, MAX_POOL, and L2_POOL,
since they are only supposed to do 2D computation.
- Updated the tests and the stack to plumbing the changes through.
Bug: 63905942
Test: mm
Test: NeuralNetworksTests pass for both CPU path and sample hidl driver.
Change-Id: I60aeabab1d193d26d938c0d1d3ffdd519740d222
/frameworks/ml/nn/common/Utils.cpp
|
| c1ab6fc5e953a61811e9f25d2afff06bfa571f0e |
|
01-Sep-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
Cleanup the constants in NeuralNetworks.h
- Alphabetize the operations.
- Move the constants that count operation and types
out of the public header file.
- Remove N_GRAM operation.
- Add TENSOR_INT32.
- Add static assert verifications.
- Add documentation.
Test: Compiled and ran the tests.
Bug: 63905942
Change-Id: Ifafdcb3fd00efabd2b1972b035cc5d43f7dbec51
/frameworks/ml/nn/common/Utils.cpp
|
| a67d8a0e28baef2fab57a2a3255461869abed74d |
|
30-Aug-2017 |
Miao Wang <miaowang@google.com> |
Add OEM_OPERATION enum.
Bug: 63905942
Test: mm
Test: All unit tests passing on sailfish
Change-Id: I391ca039620be6525d95ad581acdb6e11d091af2
/frameworks/ml/nn/common/Utils.cpp
|
| 15b59e721efe1a75b0e8cde8bd44bbb532446e13 |
|
12-Aug-2017 |
Yang Ni <yangni@google.com> |
Implement EMBEDDING_LOOKUP and HASHTABLE_LOOKUP
Bug: 63905942
Adapted previous TF Lite implementation and unit tests for NN API on
CPU.
Test: adb shell /data/nativetest64/embedding_lookup_test/embedding_lookup_test
Test: adb shell /data/nativetest64/hashtable_lookup_test/hashtable_lookup_test
Change-Id: I6e4a9d8c5d0d47e66e3fa771967da3526d19ac4b
/frameworks/ml/nn/common/Utils.cpp
|
| 8b99bb1d98a42b67ba1c00e12c7abb3708cf7c05 |
|
21-Aug-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
Add full support for Memory pools.
Weights can now be passed via memory pools.
Test: Compiled and ran the unit test.
Bug: 63905942
Change-Id: I997a10f6102dcae7c6876c96a4f6f913eaf54c74
/frameworks/ml/nn/common/Utils.cpp
|
| 27e9be3904b034e422ee9b6ab70b35ea994d2b39 |
|
03-Aug-2017 |
Miao Wang <miaowang@google.com> |
Initial implementation of the following quantized ops.
- CONV_QUANT8
- DEPTHWISE_CONV_QUANT8
- AVERAGE_POOL_QUANT8
- MAX_POOL_QUANT8
- LOGISTIC_QUANT8
Additionally, added functions to plumb through quantization
parameters.
Bug: 63905942
Test: mm
Test: end-to-end MobileNet quantized test pass
Change-Id: Ib2753c68bf2c51467ae1c158b45541bcfdf10789
/frameworks/ml/nn/common/Utils.cpp
|
| 707dbd2d55f5dacf78ffb3ad7c8b3f37c2e9d758 |
|
25-Jul-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
Pass the model as an HIDL component.
Major rework where instead of serializing the model and
passing it in a shared memory, we pass it via HIDL.
The runtime/test code does two run, one goes through the
default CPU path, the other through any available driver.
Note: The code in hardware/../sample was written by Michael Buttler.
Bug: 63905942
Test: Runs both the CPU path and through the sample driver.
Change-Id: Ie3ee975d33056ba299895b13193f4698a690dd04
/frameworks/ml/nn/common/Utils.cpp
|
| 96775128e3bcfdc5be51b62edc50309c83861fe8 |
|
12-Jul-2017 |
Jean-Luc Brouillet <jeanluc@google.com> |
First implementation of the Neural Networks API.
This first version can run a simple query on the CPU either
via the fallback path or through a simulated driver.
This code has many deficiencies: single threaded, not all
validation are done, not going through HIDL, and not
enough unit tests. Expect more changes!
Test: Compiled and ran the unit tests
Change-Id: I9f6a485a2e7207aeb5f91a2904dcb4b7fd8a6f65
/frameworks/ml/nn/common/Utils.cpp
|