Age | Commit message (Collapse) | Author |
|
* Fix filelist issue with CPU MatMul
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Iaeaae6467df23b36e48fe6aa707d61c28515ad16
|
|
* Change fp16 GeMM heuristic for Arm® Mali™-G77
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I7b39b20f9d428750e05333e5a8f4aec49353c5f9
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I94a95c84241e6beac63e4d4fc91c1d42a6ed2a5f
|
|
* 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: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Idcad2be6cf1748583a00ec21ef4446604a34c519
|
|
* Add quantized CL MatMul kernels for Lhs NT/T, Rhs NT
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I7f8c457ebee2e36674f59c687641d2ee74803012
|
|
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I9ded47fece6f19a302a0d017f6561c32b9c54daa
|
|
* Changed build so that electing to build the unit tests also builds
ExecuteNetwork and the other test applications.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I76cb6552a4f6dcee173de3dd05d43207e699a751
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: If764a8fac1a2aac0ef3b2418b56f4f87d61fd9d8
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I2a71d1d1024deccbcfdba44c2d77c7bb721b1ab4
|
|
* Fixed broken steps in BuildGuideAndroidNDK.md
* Fixed broken links in BuildGuideAndroidNDK.md
* Removed unneeded steps from BuildGuideAndroidNDK.md
* Added instructions for building the tflite parser and delegate for
android
* Fixed errors in CMakeLists.txt that made it impossible to build without
Neon or Ref.
* Added build_android_ndk_guide.sh, a shell script that contains the same
steps as BuildGuideAndroidNDK.md
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: Ie0479d3a2e4a776e7de88017b222d35a48c1fe10
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I43c0aff1b1e0ebbf37c1e8e878283d77d4975954
|
|
* Add cropping support to NEBatchToSpace
Change-Id: I021f288cec3549423f30192a5d26673772df4b34
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibf7bf5eac91bf89101b1f20449edbbc542f3f679
|
|
* Fix BatchToSpaceFixture
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I40a7dabf25b96de7d31e4060390795035445d187
|
|
* Add Texture Pipe Support for Matmul Lhs T/NT Rhs T kernels
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I473677e39c7da38477fcce8a26fec0339a674a36
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Id5e5cb47c492f955584f7f0b76c2cc4706efd6bf
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ib00025e77387327ab591e4fbd1cf0fa3f35b80e4
|
|
* Fixed clang-cl linker errors
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I6ac578887f9955cd0103cae061390cffa3482810
|
|
* 9006: Fix num_threads_hint() on macos
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I202fc1c10e7dc78964835b6dff1578e6129148ac
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ie53a4a0acc9f612948f12637c28256eb701bde4d
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I01c73aa11676f200744db5a96ad589f41581ddc6
|
|
* Fix performance regression when stride equal to kernel size
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I64dd433bc1e1f2137675612f4744b02c00341f3f
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ic20665daff9d184bf29da110f267c8dfa755e292
|
|
* 8911: Add broadcast batched matmul validation cases
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I030aca89dee6431b94ac53c93d76aabaacc5b069
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia783db31d553e2a70067fde6efbaba6644490980
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I8cf59fab3b4a06de69a3825f92b42464c0d552ce
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ice8000c47664faf967809d3ac4dd79ceafafa03d
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I75ff1d006d27d53898e6749a18f52359c043ec3a
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I6cd834ffaba9c7d598ba5c86df3d1e8bc9c86418
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: If47571cfc531cca81e983daaf7c13a7f608e9365
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ia9b59fd3482c5a12d7f6a369b1bdf91f06596a66
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Id32a970b0fe7a6af3b8d5e17a6f380b5e09341db
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I54ec99383e723cd1323c1cce8cef6ed4fbde9f46
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I6338fe09067a90ef2f52f252b3d5cf2c8810f3ff
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I9bc849ec3375c74647b637758e38fdb1870832b7
|
|
* Modify get_tensorflow.sh to point to the 2.10 Tensorflow tag.
* Modify FindTfLite.cmake to handle the break up of libruy.a
* Modify armnn_delegate.cpp to add registration_external field.
* Prevent the serializer/deserializer from using a system installed
version of flatc.
Signed-off-by: Colm Donelan <colm.donelan@arm.com>
Change-Id: I688f33f387924ba29bf400f60e56f73b2329fdc1
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I07fc2fc524452ff3631abe8aafd5993cb23a2258
|
|
* Add scons option to generate Map files.
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Ic1485f4f544ae1139e2475b95bc6d4f0d4791f02
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I6c712d6b817f87f3d3a996e11e81208e9449da9f
|
|
* Update GEMM reshaped rhs only heuristic
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I3b7489c1133ed8ae03dbc7c1e30b1979d604f4ba
|
|
* Fix overflow in NEActivationLayer for FP16 type
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I0f2e1609b8a46b69a9d83a4fa2cb6cf22af8c8d3
|
|
* Add FP32 Neon™ swish activation
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I606855096d90aa16aef9282e5860d41e3dc64d7f
|
|
* Add test for ClGemmLowpMatrixMultiplyCore to test a batched matrix multiplication
with variable input tensors
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Id1531ff661de6a01c861737111924e4c23e814fb
|
|
* Add test case for disable Winograd on fp16 if fast-math = false
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: Id4543f566a095c5822aa0f7df5ad9af4c4bd739e
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I3f0637b4b2911c9cf314b3459ff84e959e467073
|
|
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I61096136abba9c8c6b9c4c7c5ade4156cb49c8c0
|
|
* Allow user-specified directory name for the ACL
repo (other than 'clframework') with the '-n'
option.
* Fix indentation.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: Iadec158bd9469fbc0d0875b085a5702e4a89ae83
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I45d26029c90f80afb79bc1e6a4360a263f61df95
|
|
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
Change-Id: I12f2993d6e7476f9d9cb4590de9ac40bc6dd6449
|