Age | Commit message (Collapse) | Author |
|
IVGCVSW-4203 Add Neon EXP Workload
* Added CL EXP operator workload
* Added EXP test suite
* Enabled EXP tests on ACL and Ref
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I793d31af1b2e3fe86b0bec6d9e5de503c5dab970
|
|
Change-Id: I4b4d8ae419dfb8470e8937e75cd3bab85f03b935
Signed-off-by: Pavel Macenauer <pavel.macenauer@nxp.com>
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I3e934142487b92897eb487099a22d032f80e8e07
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I3ac729efba4945868710e2a233646f9634470967
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib8e9074fcd3cc30a092c3e928cb5bc3f2304f7ed
|
|
Change-Id: Ieccb26190d80e570ddef8d7c22e824eda1b92d7f
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Added unit tests
* Updated Documentation
Signed-off-by: Darshan Patel <darsh.jp@gmail.com>
Change-Id: Iadb5c76139d74d755d7f4be4b023b4417efe1e92
|
|
skipped in CpuRef
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I1c870ac258e8c3805a95b259cb40731f8e81541e
|
|
Change-Id: I75cca9804a67f629cddc83671397a84640e9bf0e
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Id908e0bcbefd3284da51cdbe8ec0c2181b9b553e
|
|
* Add TPIP used by Arm NN
* Add SqueezeNet to CaffeSupport.md
* Add ResNet v2 50 to TensorFlowSupport.md
* Update tested networks in TensorFlowLiteSupported.md
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I15927ea600a3dfffee082933d32f235f3940730e
|
|
* Updated Documentation
* Created unit test file
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Change-Id: Ic8384b5ed21ac53f918860be8a98c0ac7477d0e1
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Ifb0295ee4516ca6cbd4364ade418b707fb39b354
|
|
reduce traffic
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Ia55c52c12fe3d30eb47bc42c932a33c620dc9197
|
|
Change-Id: I58a4c0c6ce5fb806ac317b625663c2e3cbf689c8
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
Added Dockerfile to build ArmNN under an x86_64 system to target an Arm64 system.
Signed-off-by: Jegathesan Shanmugam <nullbyte.in@gmail.com>
Change-Id: I244bab37cc5fe7b38a22d4b530d42e593f223d79
|
|
Added Docker file to build an Android NDK container to build ARMNN.
Signed-off-by: Jegathesan Shanmugam <nullbyte.in@gmail.com>
Change-Id: I0f15dd21ae295894b168213c6522bb4d20051f76
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
|
|
* With semantic versioning ARMNN_VERSION is changed from 20200500 to 21.0.0
causing this function to return "Armnn .0..0" instead of "Armnn 20.1"
* Remove the use of substrings and instead use the Major/Minor macros to
give the expected output format: "Armnn 21.0" compared to last release's
"Armnn 20.02"
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: Id255ff154f59e922434f72a68563ccc6126e187a
|
|
* Add Transpose to SerializerSupport.md
* Remove ResizeBilinear as it is deprecated layer
* Add EXP and SPLIT_V to TensorFlowLiteSupport.md
* Add transpose to TensorFlowSupport.md
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: I05b0411b61c1b74b27b4669e81fa8ce521bb4190
|
|
In common cases this reduces the cmake arguments needed
for Compute Library from:
"cmake -DARMCOMPUTENEON=1 -DARMCOMPUTECL=1 -DARMCOMPUTE_ROOT=../ComputeLibrary -DARMCOMPUTE_BUILD_DIR=ARMCOMPUTE_BUILD_DIR=../ComputeLibrary/build -DSHARED_BOOST=1 ../armnn/"
to:
"cmake -DARMCOMPUTENEON=1 -DARMCOMPUTECL=1 -DARMCOMPUTE_ROOT=../ComputeLibrary -DSHARED_BOOST=1 ../armnn/"
Signed-off-by: Matthew Bentham <matthew.bentham@arm.com>
Change-Id: I992f4ef428f10dc92ca9457fe8981ae3af93f538
|
|
* Number of elements is output size for projection bias on QLSTM
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I9d32cfb187bbe0c6ef809a7a89da907fbac83380
|
|
* 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>
|
|
Change-Id: I70f78ae111b76569c8f00a331527380903f85896
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: Ice37e693f4598a6b3c38bd38d89f1d35cdaa8a18
Signed-off-by: Pavel Macenauer <pavel.macenauer@nxp.com>
|
|
* QLstm EndToEndTest added for Ref, NEON
and CL.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Icd2c878541f6304d726202a93d71ff3d79f6f054
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I380862816cbc7ec509ff01791e77297b859f21ac
|
|
* Adds QLstm CL workload
* Added Layer and CreateWorkload tests
Signed-off-by: Ryan OShea <Ryan.OShea2@arm.com>
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I32335e528467bfd619edb249d2971705ac2a6163
|
|
* Adds QLstm workload.
* Adds CreateWorkload and Layer tests.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I585eb2691395ee4ccd45b5a853660f90fc5cc821
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I34d7d3ccfb21ff882df23dfcc961f3335256229f
|
|
* Bump major version to 21
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Change-Id: I35237dfa3683d962871bad6b0353f6910d7c3e3b
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I3563209dcb3db1b40cf2db3855adc631b5e323be
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I5fafae1e3d64056d2f717b2e74f675182e7c12d6
|
|
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
|
|
Signed-off-by: Nina Drozd <nina.drozd@arm.com>
Change-Id: I04d82dd3a9759c660fdb908433becda915a3f5b5
|
|
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Iedfcf0ef487bd7836b1bc4ba8a0e4337dc4da391
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I2443dc8bc19239e954fff353a64d0b9d07623c6c
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I5dee006d5532cc85b86997a4cd0877afbf043122
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I8ba8dabba73b4682bc64c6719cf79f68383363b9
|
|
* Add FAQ entry about ArmNN and ComputeLibrary mismatch
* Add documentation reference to README that dynamically referrs to
gh branch on GitHub.
* Update ONNXSupport.mb to fix broken links.
Signed-off-by: Colm Donelan <Colm.Donelan@arm.com>
Change-Id: I6390d87443c57cc43e27ea0a27f830f8fc25244d
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Iad18bd7f845a06438b3f4ce80a6f27e959d6912e
|
|
* Adds serialization/deserilization for QLstm.
* 3 unit tests: basic, layer norm and advanced.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I97d825e06b0d4a1257713cdd71ff06afa10d4380
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I834ef1ec7c2c7b5ece1c6d1cf3cfe5d856cde349
|
|
ProfilingService::IsCounterRegistered
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I3d207a74a147f1ca2ddae43c65c65ca7cdbe2368
|
|
* change neon softmax axis to be int
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I7a9486c11494ed4993abd683a50d6b4483f283e1
|
|
* Change ComputeSoftmaxAclAxis to work with int and uint axis
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibbfa9ec7e2f0416e6885673212a767419c871cca
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: Id7fbb7a39d2e9c7085636df44d4c8603a60cd4bf
|
|
Signed-off-by: Finn Williams <Finn.Williams@arm.com>
Change-Id: I7957ee41fd700ee502cc14aa313a60664d4caec9
|