Age | Commit message (Collapse) | Author |
|
reduce traffic
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Ia55c52c12fe3d30eb47bc42c932a33c620dc9197
|
|
* Implemented CLTuning flow for ExecuteNetwork tests
* Added --tuning-path to specify tuning file to use/create
* Added --tuning-level to specify tuning level to use as well as enable extra tuning run to generate the tuning file
* Fixed issue where TuningLevel was being parsed incorrectly
* Added measurements for initialization, network parsing, network optimization, tuning, and shutdown
* Added flag to control number of iterations inference is run for
Signed-off-by: alered01 <Alex.Redshaw@arm.com>
Change-Id: Ic739ff26e136e32aff9f0995217c1c3207008ca4
|
|
* Use exact floating point constants for min/max values
* Rename test case so it doesn't collide with a function name
Change-Id: Icf03cfd8fedd505d02cd7f0a150502557939b903
Signed-off-by: Robert Hughes <robert.hughes@arm.com>
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I3563209dcb3db1b40cf2db3855adc631b5e323be
|
|
UNREGISTERED_BACKENDS
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I3600dd15f97ccd4ab745deb87d06ba978e2a0b11
|
|
* Cast to correct datatype for Winsock API
* Replace non-standard u_int32_t
* Add missing link dependency of timelineDecoder on armnn
* Don't try to link pthread if the platform doesn't have it
* Use abstracted Socket type rather than int
* Link to WinSock DLL on windows
Change-Id: I9ace4af50257ce1e3da92fb4c452f36775dac973
Signed-off-by: Robert Hughes <robert.hughes@arm.com>
|
|
* Adds missing nullptr checks for peephole bias for
QLstm.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Ib04c8352141977cc7ea11a4859f1b11d46472722
|
|
* Introduce a constant definition of the size of a POSIX thread ID.
* Update all code to use the new constant definition.
* Update all unit tests to use the new constant definition.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: I836ab1a77ed13f774e66fd7b425923c24b9a6dab
|
|
* Adds ref implemenation for new HAL 1.3
operator, QLstm.
* Adds Layer and CreateWorkload unit tests.
* Adds WorkloadData validate for QLstm.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I8a721f07ff06105e6495a1a0561b9503aa8146dc
|
|
* Refactor Neon Softmax workload to accept supported data types
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I54aa72d5cbb862cafcc1eabe48f6a00d61050cd7
|
|
In order to improve the maintability of the LayerType enum,
it is easier to use the X macro technique https://en.wikipedia.org/wiki/X_Macro
Thanks to that, the pre-processor can generate some code based on the
list provided by the LIST_OF_LAYER_TYPE macro
Signed-off-by: Laurent Carlier <laurent.carlier@arm.com>
Change-Id: I3a6049abfb1e964fe0bf32aa4e26bec4e29a77de
|
|
* Removed split, classification, trim, string, join, contains
* Added StringUtils.hpp to replace the removed Boost String functionality
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I8aa938dc3942cb65c512cccb2c069da66aa24668
|
|
* as replacement for boost::polymorphic_pointer_downcast
* added PolymorphicPointerDowncast
* added related unit test
* added description to PolymorphicDowncast
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I47e94344c1c21941865549a5632cfb7cad804d35
|
|
* Move the call to EnableProfiling() into ConnectionAcknowledgedHandler
* Fix an issue with MockGatord forcing some command handlers to be quiet
* Add some small unrelated improvements and typo fixes to the
periodic counter command handlers
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I9e6066b78d1f782cfaf27c11571c0ec5cb5d126f
|
|
* exchange boost::polymorphic_downcast with armnn::PolymorphicDowncast
* remove unnecessary includes of boost::polymorphic_downcast
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ie603fb82860fe05fee547dc78073230cc62b2e1f
|
|
* Change boost assert to armnn assert
* Change include file to armnn assert
* Fix ARMNN_ASSERT_MSG issue with multiple conditions
* Change BOOST_ASSERT to BOOST_TEST where appropriate
* Remove unused include statements
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I5d0fa3a37b7c1c921216de68f0073aa34702c9ff
|
|
* Add Activate/Deactivate command handlers
* Add IReportStructure, INotifyBackends single function interfaces
* Add overrided mechanism to report structure in Runtime.cpp
* Add overrided mechanism to notify backends in ProfilingService.cpp
* Add optional IReportStructure argument to ProfilingService constructor
for use in ActivateTimelineReportingCommandHandler
* Refactoring and tidying up indentation
* Removal of unused code in ProfilingUtils.cpp and ProfilingService.cpp
* Added GatordMock end to end test
* Fixed an issue with SendCounterPacket sending duplicate packets
* Fixed an issue with DirectoryCaptureCommandHandler handling of Optional
Signed-off-by: Keith Davis <keith.davis@arm.com>
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I5ef1b74171459bfc649861dedf99921d22c9e63f
|
|
HAL 1.1/1.2 to account for negative slices
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ia98101b07b826359fb621b801fcbc811d7ec6f6a
|
|
* Add NeonConvertBf16ToFp32Workload
* Add NeonConvertFp32ToBf16Workload
* Add BFloat16 type support to NeonConstantWorkload and NeonTensorHandle
* Add ConvertBf16ToFp32Weight when ConvertBf16ToFp32Layer is added
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Id5b44a203add5e0c98c1ca4e2162115741b56644
|
|
* CellToInputWeights were not handeled correctly
* Changed CellToInputWeights from Cifg to peephole parameter
* Modified exiting unit tests
* Added unit test to cover new configuration
* Added more descriptive error messages
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ied5dc1253d3df1fd1a79b887a58603d0a9c8f396
|
|
Convolution2d and FullyConnected layers
* Add InsertConvertFp32ToBf16LayersBefore
* Add ConvertWeight to ConvertFp32NetworkToBf16Impl for Conv2d and FullyConnected
* Allow different input and output when input is BF16 and output is FP32
Conv2d and FullyConnected layers
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ic8f92ff28edcae08a72a3114a28f50c4619f919b
|
|
* The std::thread::id is included in some timeline packages of the
profiler. But the size of thread::id is platform dependent. That's why
some tests expected a wrong package size
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: I4794ebbdda2d75ed5be7112f6a3bf2e5f14f221b
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I35e0a891cd69f2c130b8886460089c441d8e666d
|
|
* Add ReduceFp32ToBf16 to OptimizerOptions
* Add ConvertFp32NetworkToBf16
* Add utility functions to insert conversion layers
* Add constant conversion BF16 <-> FP32
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Iaff77e20c721400b052cb37eb9ef6fe16d7abaff
|
|
* Added new layer QLstm (Android R HAL 1.3)
* Made necessary updates to APIs
* Added unit tests
* This layer is functionally equivalent to the
original unquantized LSTM layer with some
additonal quantization features added. Due
to this, original LstmParams are used for
this layer.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I5b7f2d2fb6e17e81573b41a31bc55f49ae79608f
|
|
the Backends CI job
* Enable the GetProfilingService() function to BackendProfilingTests and ProfilingTestUtils
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I32e3625db0f465883f2ec27fb7c2fad4e91b6306
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I9099a4f840fb747336f77d20a0868b64e801a310
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I174f83c9a454b5499f817baf0bddcd4a49cac523
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I84ab68c048675a39a67045430b2dde571b45e479
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I345c39a10a4693a500aa1687d9a5cee76da791c3
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ida6d7e1d2c9abe0618f8b711bab9d62c011090d6
|
|
* Improved error reporting by using VisitorThrowingPolicy in
DynamicQuantizationVisitor.
Change-Id: I8a7d0975d448e6c2b6efb5f315ac255eec29f7a2
Signed-off-by: Pablo Tello <pablo.tello@arm.com>
|
|
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I7f6932f0d21b5678ab9822b0fc69f589bbbb07e5
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I85b6967469dc1fddbbc875b34ba107480b78089a
|
|
!referencetests:229377
Signed-off-by: Jan Eilers <jan.eilers@arm.com>
Change-Id: Ia9b360b4a057fe7bbce5b268092627c09a0dba82
|
|
* Add ConvertFloat32ToBFloat16
* Add ConvertBFloat16ToFloat32
* Add BFloat16Encoder
* Add BFloat16Decoder
* Unit tests
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I198888384c923aba28cfbed09a02edc6f8194b3e
|
|
* Changed TimelinePacket encoding so that there is only one header for
multiple timeline swtrace messages
* Refactored function names to have more suitable description
* Refactored CodeStyle to coincide with ArmNN coding standards
* Refactored profiling test names to be descriptive
* Refactored ErrorCode name to TimelineStatus
* Updated existing unit tests
Signed-off-by: Keith Davis <keith.davis@arm.com>
Change-Id: I83bd4bb9e7393617bca97eba96a6e1388916e5b0
|
|
Change-Id: I3e64bca4a1709ac199513676579cf3c9a3090f26
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: I958dd719162337eb5c7e71f4ac49dd5784564b1a
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ie2e9e617b9210d79a26e7ba58ecc874d1202e599
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ie2fcf06d0bae9e2ef958e60ab9e8b121fdc7b590
|
|
* Changed some existing Permutation specific optimizations to also support Transpose
* Added MoveTransposeUp optimization
* Added TransposeAsReshape optimization
* Added tests for Transpose optimizations
* Added missing layer tests for Transpose
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I20d099b284861402ae94aaa5dbf34907327a485f
|
|
Change-Id: I6ddcffe792e39b17fcdb8af7f13f4a689ef8019d
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
EnableProfiling and adding error checking to the Runtime
Invocation
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I65b8bb16c6f1c7d668de31238ce0408a48974997
|
|
* Add a new Activiation type of HardSwish.
* Add CpuRef support and tests.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: I68c3840aa45b7a27d5e416a5d50fe8f99f003ce8
|
|
* Added TransposeLayer
* Added CL, Neon and Ref Workloads
* Added Transpose utilities
* Added Serializer and Deserializer support
* Added Quantizer support
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I04c755ba7cb5b1edf72b3c9f3c0314878032e3c7
|
|
* Added CpuRef implementation
* Added Unit Tests
* Added Quantizer Test
* Enabled Tests for Neon and CL backends on fp32 only
* Added to Serializer
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Ic23e1797dbc9352b40678c389d7fe2b836b582ea
|
|
* Sync up the Android build files with the CMakeLists.txt
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: I1675b0937fed7c74833e46af6d077ced57cf5bed
|
|
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I9ff918e7f9fe340e65f8dd1b1c47754c8b41de1f
|
|
* Added Quantization Scheme for QAsymmS8
* Added Unit Tests for QAsymmS8
* Renamed QAsymm8 calls to QAsymmU8
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: I897b4e018ba1d808cc3f8c113f2be2dbad49c8db
|