aboutsummaryrefslogtreecommitdiff
path: root/src/backends/cl/workloads
AgeCommit message (Collapse)Author
2019-08-05IVGCVSW-3342 Add CL backend support for Quantized_LSTM (16bit cell state)Ferran Balaguer
!android-nn-driver:1685 Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I17278562f72d4b77e22c3af25bf7199b9150a765
2019-08-01IVGCVSW-3539 Add CL support and tests for StackMatthew Jackson
* Added CL backend support for Stack * Added unit tests for Stack on the CL backend * Refactored unit tests to support generic data types Signed-off-by: Matthew Jackson <matthew.jackson@arm.com> Change-Id: I38ee3e9d8947ea98a3104c982698001e704d7d89
2019-07-26IVGCVSW-3554 Update workloads to pass Softmax Axis Parameter to BackendsFrancis Murtagh
* Add check in CL and Neon to ensure axis is 1 otherwise return unsupported. * Edit CreateWorkload test and JsonPrinter test to ensure axis of 1. Change-Id: I499b405532e26fefc2dd1c18b6dc6005813b5604 Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
2019-07-25IVGCVSW-3521 CpuAcc V1.2 pad FailuresMike Kelly
* Pad value for QASYMM8 is no longer stored in quantized form. Signed-off-by: Mike Kelly <mike.kelly@arm.com> Change-Id: I048e1d233353c0560ae03a7cc1ed5199295352bc
2019-07-22IVGCVSW-3548 Use BuildArmComputePadStrideInfo() in CL and NEON convolution ↵Aron Virginas-Tar
workloads * Refactoring: use existing utility function for creating arm_compute::PadStrideInfo objects in CL and NEON convolution workloads instead of duplicating code Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: Id5e5a0f264e20af99dabce8dd8c6b782dedb94e6
2019-07-16Remove unnecessary include from ClResizeWorkload.cppAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I5c8f6d08653646d99f839ceca11931e3be0467d8
2019-07-15IVGCVSW-3519 Refactor TransposeConvolution2dWorkload for CL backedNikhil Raj
Change-Id: I2c458499b05b16f71decd09e6b642ce3725623fc Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2019-07-12IVGCVSW-3296 Add CL backend support for ResizeNearestNeighbourAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I7f4c722141837939fd8904c52e75704a15c8a5e3
2019-07-11IVGCVSW-3298 Add CL backend support for dilated Convolution2dJan Eilers
* Update ClConvolution2dWorkload * Enable unit tests Change-Id: Id07bae220a35a0cadcacebe615f156622ae5f196 Signed-off-by: Jan Eilers <jan.eilers@arm.com>
2019-07-09IVGCVSW-3467 Add CL Backend support for Pad_v2 with Unit TestFinnWilliamsArm
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com> Change-Id: I4c51e49ef57065e9fb0038175e67290c59d5f396
2019-07-09IVGCVSW-3338 Add CL backend support for LSTM normalizationJan Eilers
* Enable calls to LSTM normalization unit tests on CL backend. * Update CL workload to set the layer normalization parameters. !android-nn-driver:1461 Change-Id: Ia5a29918961c391c1f1d8f331add377a38822ddd Signed-off-by: Francis Murtagh <francis.murtagh@arm.com> Signed-off-by: Jan Eilers <jan.eilers@arm.com>
2019-07-09IVGCVSW-3397 Join lstm parameter infos in a struct for isLstmSupportedJan Eilers
!android-nn-driver:1461 Change-Id: I9d8fe7adf13832ed0cbcfe98b2353c2f37011d22 Signed-off-by: Jan Eilers <jan.eilers@arm.com>
2019-07-05IVGCVSW-3353 Add CL support and tests for SpaceToDepthJames Conroy
* Added CL backend support for SpaceToDepth. * Enabled unit tests for SpaceToDepth on CL. * Renamed unit tests to make them type-agnostic. * Added QSymm16/S16 support to ClTensorHandle. Signed-off-by: James Conroy <james.conroy@arm.com> Change-Id: I417d82946142ed619c447428bf0b0c4a2116c004
2019-07-05IVGCVSW-3401 Update ACL pin to latest masterJames Conroy
* Updated ACL pin to latest master. * Minor changes to Softmax Neon/CL uint8 workloads to reflect refactoring in ACL. !android-nn-driver:1476 Change-Id: I1c5005ddbcccdb41d8cb09d3fa61cf3ce0e9ffdb Signed-off-by: James Conroy <james.conroy@arm.com>
2019-07-05IVGCVSW-3293 Add CL backend support for PReLUNikhil Raj
Change-Id: I1bb187db89bb3eb883b8f0aca4c3439d82b56583 Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
2019-06-28IVGCVSW-3162 Support CL workload for TransposeConv2DAron Virginas-Tar
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I3b021c0828d30298d99ddb211c9aae17fe3636f0
2019-06-27IVGCVSW-3287 Add L2Normalization epsilon CL workload supportFerran Balaguer
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: Ifb7d50ed43cd66e219b17369130f9091d4a668e7
2019-06-26Update the CL pin to the latest masterFerran Balaguer
* Update SoftMaxUint8Workload for CL and NEON to deal with quantization parameters as vectors. * Change Sigmoid Activation function QAsymm8 tests to use scale=1.f/256.f and offset=0 as quatization output parameters. !android-nn-driver:1417 Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: Ief91f10193fbbbad0c0124ece41f0bf4e0dcd992
2019-06-04Update the CL pin to the latest masterMatteo Martincigh
* Updated the pinned CL revision * Changed the type for axis in L2Norm workloads !clframework:d7dd15c445397ab879439de6659859db09f4b752 !android-nn-driver:1268 Change-Id: Ib568869ae8259c4c7d62fc8b434c74a7f8242988 Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
2019-05-31IVGCVSW-3147 Add CL Dequantization workloadJim Flynn
Change-Id: I9baf6af3d98a26005a31075cd9c4e1f40938789b Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-31IVGCVSW-3186 Add ClQuantizeWorkloadSadik Armagan
* Added ClQuantizeWorkload to enable quantization on CL backend Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Id49d5ec29514f6f853c2500a34b1a12444c49168
2019-05-28IVGCVSW-3119 Rename MergerLayer to ConcatLayerJim Flynn
!android-nn-driver:1210 Change-Id: I940b3b9e421c92bfd55ae996f7bc54ac077f2604 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-23IVGCVSW-2771 Fix SubTensor error in vgg16 ExecuteNetwork CLNarumol Prangnawarat
* Add check if Sub-tensors cannot be used, call ACL function * Add ClSplitterWorkload functions * Modify IsSplitterSupported to call ACL validate function if sub-tensor cannot be used * Also check if quantization parameters match when using sub-tensors Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com> Change-Id: I5dfd0e422b7d485dd4421a664add83d870bec5d6
2019-05-20IVGCVSW-3117 Rename ClMergerWorkload to ClConcatWorkloadJim Flynn
Change-Id: Ie0394336a772afa7b075eb562ac5191c8b3ec9f3 Signed-off-by: Jim Flynn <jim.flynn@arm.com>
2019-05-13MLCE-101: Adding dilation support in conv and dconvPablo Tello
Added support for dilation in DepthwiseConvolution2d in the Neon and CL backends. Change-Id: Ie1522b498c07f80d6efcf9dc79e926c8cfa06ca5 Signed-off-by: Pablo Tello <pablo.tello@arm.com>
2019-04-16IVGCVSW-2957 MergerLayer subtensor optimization now backend agnosticDerek Lamberti
+ Update clframework pin + Cl and Neon Merger workloads updated to use MemoryLayout agnostic API + Workloads only use sub-tensor optimization if ALL input tensors are sub-tensors + Refactor LayerSupportCommon code to be a bit more succinct Change-Id: Ib61ad4ccbd767e924dff07e61022e0cda4069828 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-04-10IVGCVSW-2947 Remove boost dependency from include/TypesUtils.hppAron Virginas-Tar
!android-nn-driver:968 Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com> Change-Id: I03ccb4842b060a9893567542bfcadc180bbc7311
2019-03-15IVGCVSW-2354 Caffe SqueezeNet through armnn Cl and NeonNarumol Prangnawarat
* Compute Softmax Acl axis for Cl and Neon * Add unittests for Softmax in 3D and 4D * Correct input and output layer names in CaffeSqueezeNet inference test Change-Id: I2d369d9a2db19c40f2af3341039dd33f0c5637b1 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-02-26IVGCVSW-2756 Fix bug in ClSpaceToBatchNdWorkloadNattapat Chaimanowong
*Padding was not in format expected by Cl Change-Id: Id0de3fd2b306e31d555e2d67bc4406e5302dcd3b Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
2019-02-21IVGCVSW-2424 Add LOGISTIC Operator Support (CL)Finn Williams
* Added Logistic tests in ClLayerTests * Removed check for QuantisedAsymm8 in CLActivationWorkload Change-Id: I6950e18109504d8426b727cb6b7d19898c899024 Signed-off-by: Finn Williams <finn.williams@arm.com>
2019-01-29IVGCVSW-2443 Add Cl support for Greater operatorNattapat Chaimanowong
Change-Id: I7eb3b2e712dbaa5c13f6cf3a1da63df4d2bd4de5
2019-01-14MLCE-86 Reversing the pad list in the ClPadValidate function similarly to ↵Éanna Ó Catháin
whats done in the constructor. Change-Id: I9488cebd63767c0c51d9ee6333d5aaf0e4a85847
2019-01-09IVGCVSW-2438 Add Minimum operator support (CL)saoste01
* Added CL unit tests Change-Id: Ia4af49b133774141384a177f5b042e65764bf682
2019-01-04MLCE-77 Depthwise Convolution with depth multiplier > 1 doesn't workMatteo Martincigh
* Unified ArmNN's weight format to [ M, I, H, W ] for the depthwise convolution * Added conversion utilities to permute/reshape the weights as appropriate when using CL and Neon backends * Updated the reference implementation of the convolution * Updated the relevant unit tests accordingly !android-nn-driver:459 Change-Id: I07d0818efa9d1ca1e5dad82983aac1fe78eadb18
2019-01-02MLCE-82 Add Neon Mean support and unit testsMatthew Bentham
Factor out new BuildArmComputeReductionCoordinates function from CL backend into ArmComputeTensorUtils. Update NEON LayerSupport and WorkloadFactory objects Change-Id: Icc975ec699199bffafbdb207323df509d35e1e04
2018-12-20IVGCVSW-2164 Added ACL implementation of SpaceToBatchNd operation to ArmNNSadik Armagan
!android-nn-driver:428 Change-Id: I42e59ad96d2c80f46b085182855d34b710a74dfe
2018-12-20IVGCVSW-2211 Maximum operator support (CL)keidav01
* Added CLMaximumWorkload implementation * Added CL unit tests Change-Id: I922c83fe25d17be21a5d0f4e861038463cb09789
2018-12-18IVGCVSW-2131 Implementation of StridedSlice operationkeidav01
* Added ACl Implementation to ArmNN * Added helper function for setting CL Strided Slice arguments Change-Id: Ie10d387fdb054027ea9b8782743d270bb72949c1
2018-12-10IVGCVSW-2354 Remove dimension validation from softmaxMohamed Nour Abouelseoud
Change-Id: I0d69a72df9e348cbeca690926485c050499d1051
2018-11-28IVGCVSW-1199: BATCH_TO_SPACE_ND integrate Arm Compute CLMike Kelly
Change-Id: Ic772acf481caed6e8a6b99f68a63dfc2a34c24dc
2018-11-19IVGCVSW-2169 Remove DataLayoutIndexed from public APIMatthew Bentham
Change-Id: If8d8087d9d365e467d3ca9bf9c40d7219cb75cfd
2018-11-19IVGCVSW-2043 - Merger using ACL for innermost concat axisNikhil Raj
* Add ClMergerWorkload and NeonMergerWorkload to call ACL for innermost concat axis * Modify layer support to call ClMergerWorkloadValidate and NeonMergerWorkloadValidate when concat axis is inner most * Add m_ConcatAxis to MergerDescriptor * Modify MergerQueueDescriptor::Validate to check sub tensor only when using subtensor !android-nn-driver:166 Change-Id: I56676b43964c8d6d726387b41b3cc34a512c0f0a
2018-11-16IVGCVSW-2017: CLWorkload to use L2NormalizationFrancisMurtagh
* Changed ClL2Normalisation from using CLNormalizationLayer to use CLL2NormalizeLayer to normalise along the channel axis in either NCHW or NHWC format. Change-Id: I399cbee408a277d1ef8c6c85ebcbd86d6c3e407b
2018-11-16IVGCVSW-2092 Port LSTMCell::Eval to ArmNNMatteo Martincigh
* Ported Google's LSTM implementation to RefLstmFloat32Workload * Fixed the code throughout because of an error in the docs around the scratch buffer size * Updated IsLstmSupported * Added the unit tests !android-nn-driver:127 Change-Id: I5577b7e39ca52df1a7f102a9b437df6aa99520b6
2018-11-05IVGCVSW-2113: Update ClDepthWiseConvolutionWOrkload to suit NCHW/NHWC ↵saoste01
DataLayout (3*3 Optimization) Change-Id: Icfc137201c52e2c856076b7795572cc4ba75cc95
2018-11-02IVGCVSW-1946: Remove armnn/src from the include pathsAron Virginas-Tar
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
2018-10-25IVGCVSW-2049 + IVGCVSW-2051 Create the CL Mean Float workload and addMatteo Martincigh
the unit tests * Created the ClFloatWorkload class * Added ClMeanValidate validation function * Added helper function to convert the reduction axes from the ArmNN format to ACL's * Added workload tests * Added some unit tests * These changes need the CL pin to be pointing at least to revision 88d871028eeae57f9e4536d0329110eccb5e2890 (COMPMID-1574 Implement ReduceMean in OpenCL) !android-nn-driver:155033 Change-Id: I694fd36be0458c90e158172afde045fcc88c32ae
2018-10-22IVGCVSW-1955: Unify backend exceptions (wrap cl::Error)Aron Virginas-Tar
* Added wrapper function around arm_compute::IFunction::run() that catches cl::Error and wraps it into an armnn::RuntimeException * Added MakeWorkload template inside ClWorkloadFactory that catches cl::Error and wraps it into an armnn::RuntimeException * Replaced cl::Error with armnn::RuntimeException in catch statements inside LoadedNetwork Change-Id: I2340f41ae02b8db1d7ef5157824a50e7410854e3
2018-10-22IVGCVSW-2061: Add ARMNN_SCOPED_PROFILING_EVENT_CL inside ↵Aron Virginas-Tar
ClLstmFloatWorkload::Execute() Change-Id: Ia3f895474b54e73711feb9795e7d47cbd61f13a3
2018-10-22IVGCVSW-2024: Support NHWC for Pooling2D CpuRefJames Conroy
* Adds implementation to plumb DataLayout parameter for Pooling2D on CpuRef. * Adds unit tests to execute Pooling2D on CpuRef using NHWC data layout. * Refactors original tests to use DataLayoutIndexed and removes duplicate code. Change-Id: Ife7e0861a886cf58a2042e5be20e5b27af4528c9
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-30 04:00:51 +0000