Age | Commit message (Collapse) | Author |
|
* Added new ARMNN_STUB_PROFILING and ARMNN_DISABLE_DYNAMIC_BACKEND
defines to replace BUILD_BARE_METAL and BUILD_EXECUTE_NETWORK_STATIC
* Add new CMake variables to disable sample apps and dynamic backends
* Improve BUILD_SHARED_LIBS CMake variable
* Add new archive output location to various libraries so that the
static libraries appear in the same location as the shared libraries
* Fixes for bare metal build
* Add ARMNN_DISABLE_FILE_SYSTEM defines to missing locations
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: I1db9a8f483e7134bd261294b35240cf21b150d45
|
|
* Added CEIL and other missing operators to TfLiteParser and
TfLite Delegate documentation.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ic30a3367a13d3b64aca2f7a8d8cc5b16616a0bcc
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Ibdded86713368ecfdf31c4118dfe8a3404d1e3b8
|
|
* Call dedicated MatMul kernel in ACL
* Add int8 tests
* Add int8 to documentation
* Force tensors to be dynamic (nonConst) as per request of ACL
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I7b7ac20deec8637dc46ca990d339d92c4587cbe4
|
|
* Call dedicated MatMul kernel in ACL
* Add int8 tests
* Add int8 to documentation
* Force tensors to be dynamic (nonConst) as per request of ACL
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I992ae9aae1174214607bf29305f21cdeaf3fdc1b
|
|
output size
* Added fix to Classic and Opaque Delegate which now matches
the TfLiteParser.
* Removed uses of single parameter IsValid function in classic
Convolution visit functions.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I5be91ec25c11354a9b8472d0a429e71e02df6f9c
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Iadba213e78f4c7eed7d1eea2206dcd1d977446b5
|
|
* If the dimension Size[n] in a Slice is -1 then it should be treated as
"InputShape[n] - Begin[n]" but the Delegate simply cast the Size to
uint and treated it as 4294967295.
* Added the layer name that includes the node index to the Slice to aid
debugging.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I45fa88b24982c3c97f48d0dc05cf7d9bb6db4074
|
|
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Signed-off-by: Ryan OShea <ryan.oshea3@arm.com>
Change-Id: Ie02021ac56a512598760e4c6d05ef1a80f4aec8d
|
|
* Intermediate tensors aren't accessible through the new
Opaque interface yet, so we have to cast to TfLiteNode for now.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ifd91131e5d5ff6cc057b80729fea9afa68ed240b
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib0d7835355e82d94b66b27a25b56b788c4606ae8
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Iaf3242b4d06bd043fe25a00722da6cb6406d013b
|
|
Classic and Opaque Delegate
* Implemented unsupported operators in Classic Delegate.
* Added unit tests.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ib39eeea53c114b15943e8dc2e796ce64c40cb3a5
|
|
* Added implementation for Split / SplitV in Opaque Delegate
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I1ad2925aece7d4e0567e63ecb768348152a70a7a
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I402a4c74610b5dc8a3ca6e22218b58fbe59474ed
|
|
# Fix im2col for fast-maths mode with padding.
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I6140f5435b81598d29a30f1f6747fd59e2304101
|
|
* Aligns both sh script and md file
* Change default branch to main as 'latest' release will change every 3 month
* Clones github repos instead of mlplatform repos
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I4bed6c4c231b5f3bab0abf92b0febf825ddb4ce7
|
|
* flag should be flag_tflite_classic_delegate instead
of flag_tflite_delegate
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I4c1f6406d88ee91c032f8edcf1196f2e8e8bcb92
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib3aaba6d2bbe52978fc3e8873c78e4c2989131ed
|
|
* Fix export_to_cl_image issue in the fp16 GeMM implementation
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I07440e48243abb599a0bd9e6d96d8c3291e87e91
|
|
* The source and destination size checks in CopyTensorContentsGeneric are
handled by asserts instead of exceptions.
* Adding unit tests.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: Ia00c07158afde6768002dc6059067fd08e47fcff
|
|
* Moved CreateOutputTensorShape function to common DelegateUtils.hpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I3d8a9834ecd6b7cda170cce958677a0dde62824a
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I5d8b9e38b50ee56e03c8421e4ddb9a02eade5d47
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Iaf3f1b5e4e41d0d946a21504c6d44e47d83273e0
|
|
* Change alignment in Shape.hpp
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibc21cf5c56a1ba2daa7507a5d5c2b7311756f17f
|
|
* Added 2 opaque delegate operators and associated test cases
* Removed IsDynamicTensor check from BatchMatMul as covered by IsValid.
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com>
Change-Id: If7c58cb23ae5c5b8a9451dddfd7b6dfcbf248d4c
|
|
DepthToSpace and Tranpose for opaque delegate
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ie0c608f94a76956e9be75f555824cef865cab395
|
|
Dequantize operator
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I318cb25f526dfe0f7aa6afcf77971afd8d437209
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I25415793497f0ee08d880539e265b133875a20f7
|
|
* Fix filelist issue with CPU MatMul
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Iaeaae6467df23b36e48fe6aa707d61c28515ad16
|
|
NECast can use conversion instructions where they are available
so this should in general be faster.
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I3f259e17b280a4f4c36f363965ffbc8ee8c4c29f
|
|
* Added visit functions for ElementwiseBinary Ops
* Moved MultiLayerFacade.hpp to common directory and updated both delegates to use it
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: I84b8bd74d15a194895e63da47c29be994531a889
|
|
Lstm, Pooling2d and Pooling3d operators for Opaque Delegate
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ic9af1c50589285ab359661699d32a889cd267cd9
|
|
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com>
Change-Id: Id4b02b951ed81c69171f6af2d0d327175c6e5d3c
|
|
opaque delegate
* Add check for TF version so tests work with opaque and classic
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I3a6699150afabfc6200e1cd4d264a1f7c65c5f60
|
|
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I501a3e01932d44eca796e93a9383378dafc758c5
|
|
LogicalBinary operators for opaque delegate
* Report the operator as part of the layer name for:
- LogicalBinary,
- ElementwiseUnary
- Comparison
- Activation
* Fixing indentation in Gather.hpp
* Removing not needed includes in Gather, GatherNd and Comparison
* Correct end of namespace comment in Comparison
* Correct log from TfLiteArmnnDelegate to TfLiteArmnnOpaqueDelegate
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ia0d497709309e912d31eb4b6db0fef9e79b7a3af
|
|
* Change fp16 GeMM heuristic for Arm® Mali™-G77
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I7b39b20f9d428750e05333e5a8f4aec49353c5f9
|
|
and Prelu operators for Opaque Delegate
* Added missing headers to opaque/CMakeLists.txt (Control and Comparison)
* Cleaned up Control.hpp headers.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I442edb9c467b515b130fbaf02879f0802006255f
|
|
* Updating TF to the 2.12 SHA Arm NN will be using
* Turn Off JNI build
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib75e16687ac3a2dd4a77ed68f97bf14fdd86eec0
|
|
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: Id2b6a4f70b1cb50e5f7f7ab4e30487b3816c9ad4
|
|
* Added Opaque ArgMinMax and associated test cases
Signed-off-by: John Mcloughlin <john.mcloughlin@arm.com>
Change-Id: I098b94cc35707370a0bbc7456bfdd48bb47432f0
|
|
Opaque Delegate
Signed-off-by: Kevin May <kevin.may@arm.com>
Change-Id: I38304abce1a417bb69aced2a5b38e976ea0cbbc0
|
|
* If the output shape is given in Transpose convolution, use it to calculate the padding
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I0bf3dee94c2ce606ed67fb385018b220188c3017
|
|
!android-nn-driver:9431
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
Change-Id: I58143445b5c5cf2aafd0838156c9543adce21e6a
|
|
in Opaque Delegate
* Removed input slot check from Connect function as number of TFLite
and Arm NN inputs can differ.
* Moved SetupConcatViewOrigin function to DelegateUtils.hpp
* Simplified validation checks in VistConvolution functions as IsValid
and IsDynamic were already being called.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I858dbe4b643f9d350d9c38ea255ce5effbda4612
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I94a95c84241e6beac63e4d4fc91c1d42a6ed2a5f
|
|
* Added VisitConvolution2d and VisitDepthwiseConv2d functions
to Convolution2d.hpp.
* Enabled Convolution2d and DepthwiseConv2d tests.
* Moved TransposeConvolution2d tests to separate file.
* Added Opaque Delegate shared functions.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: Ica10c9469fc830f512edad1ad79884f90ae511d0
|
|
* Implement CL kernel for a native batched matmul Quantized - LHS transposed, RHS transposed
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I00d1499033f7b6279d489c26c17200860daaf299
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I637fb48e5ae0e2bc90c2900b5b35860e0fbcfb25
|