Gitiles
Code Review Sign In
review.mlplatform.org / ml / armnn / d2d22a6495eb3b2c29a84d146d667f1515940a41 / src / backends / cl / workloads
  1. c347b17 IVGCVSW-6889 Seg fault running ExeNet with --bf16-turbo-mode on fpga by Francis Murtagh · 1 year, 11 months ago
  2. ea660e1 IVGCVSW-6986 SLTS Failures due to Caching commits by Cathal Corbett · 2 years, 1 month ago
  3. 311cfa7 MLCE-825: Give reason when workload unsupported for Non Constant Weights/Bias by Francis Murtagh · 2 years, 1 month ago
  4. 8bd5360 IVGCVSW-6126 ConstTensorsAsInput: Conv2d - Backends by Cathal Corbett · 2 years, 2 months ago
  5. b4dd5cc IVGCVSW-6124 ConstTensorsAsInput: Conv2d - FrontEnd by Keith Davis · 2 years, 3 months ago
  6. 4452baf IVGCVSW-6260 ConstTensorsAsInput: Fully Connected Cl and Neon support. by Cathal Corbett · 2 years, 2 months ago
  7. 4b19d22 IVGCVSW-6940 ConstTensorsAsInput: DepthwiseConvolution2d - Complete ACL by Cathal Corbett · 2 years, 2 months ago
  8. 0302723 IVGCVSW-6936 Sqrt for CpuRef, CpuAcc and GpuAcc by Teresa Charlin · 2 years, 2 months ago
  9. 989e2f6 IVGCVSW-6861 Add GATHERNd CL workload by Teresa Charlin · 2 years, 2 months ago
  10. aac6112 IVGCVSW-6936 Add SQRT support to CL by Teresa Charlin · 2 years, 2 months ago
  11. 1299496 IVGCVSW-6806 Add Unidirectional Sequence Lstm support to Neon by Mike Kelly · 2 years, 2 months ago
  12. bab8fa9 IVGCVSW-6174 Add Cl Pooling3d Workload by Ryan OShea · 2 years, 4 months ago
  13. a3f4fba IVGCVSW-6732 Tests surrounded in '#if defined(ARMNNREF_ENABLED)' in android-nn-driver do not execute. by Cathal Corbett · 2 years, 3 months ago
  14. 2776183 IVGCVSW-6706 Move headers to profiling/client/include by Jim Flynn · 2 years, 3 months ago
  15. 4952a3e Revert "Revert "IVGCVSW-6267 Add support of Unidirectional Sequence Lstm fp32/fp16 to Cl"" by Cathal Corbett · 2 years, 4 months ago
  16. fd5bec4 Revert "Revert "IVGCVSW-6268 Add support of Unidirectional Sequence Lstm fp32/fp16 to Neon"" by Cathal Corbett · 2 years, 4 months ago
  17. 3826ab6 IVGCVSW-6700 Disable importing on ClConv2d when datalayout is NCHW by David Monahan · 2 years, 4 months ago
  18. f87b90e Revert "IVGCVSW-6268 Add support of Unidirectional Sequence Lstm fp32/fp16 to Neon" by Cathal Corbett · 2 years, 4 months ago
  19. 79cef69 Revert "IVGCVSW-6267 Add support of Unidirectional Sequence Lstm fp32/fp16 to Cl" by Cathal Corbett · 2 years, 4 months ago
  20. ad91717 IVGCVSW-6267 Add support of Unidirectional Sequence Lstm fp32/fp16 to Cl by Cathal Corbett · 2 years, 5 months ago
  21. b0baff7 IVGCVSW-6268 Add support of Unidirectional Sequence Lstm fp32/fp16 to Neon by Cathal Corbett · 2 years, 5 months ago
  22. c27d15c Add SupportsTensorHandleReplacement implementation to the ClConvert workloads by David Monahan · 2 years, 5 months ago
  23. 73c547d Refactor Forced Import by Finn Williams · 2 years, 5 months ago
  24. 5e7335b Add implementation of reconfigure function to Cl Convert workloads by Jim Flynn · 2 years, 5 months ago
  25. ec81999 IVGCVSW-6700 Add override functions to all typed Neon/CL workloads by David Monahan · 2 years, 5 months ago
  26. 67d6390 Handle optional biases better in Neon/Cl FullyConnected workloads by Matthew Bentham · 2 years, 5 months ago
  27. e2af6f4 IVGCVSW-6552 Add support of aligned host memory by Narumol Prangnawarat · 2 years, 5 months ago
  28. 588cbdf IVGCVSW-6685-6686 Modify workloads to extend Neon/Cl BaseWorkload by Teresa Charlin · 2 years, 5 months ago
  29. 98b0dcb IVGCVSW-6683-6684 Add ClBaseWorkload and NeonBaseWorkload by Teresa Charlin · 2 years, 6 months ago
  30. 0c47974 IVGCVSW-6626 Promote backend headers in backendCommon to armnn/backends by Colm Donelan · 2 years, 7 months ago
  31. 46c657d IVGCVSW-6519 Extend pad workload for GpuAcc to support mirror padding by Teresa Charlin · 2 years, 8 months ago
  32. 2ea38c7 Bug Fix in CpuAcc and GpuAcc workload: Gather has 2 inputs by Teresa Charlin · 2 years, 8 months ago
  33. 9f6862d IVGCVSW-6440 Add profiling around CL workload configure calls by Kevin May · 2 years, 8 months ago
  34. 2e5d0b2 IVGCVSW-6469 Add MirrorPad FrontEnd and Ref Support by Matthew Sloyan · 2 years, 8 months ago
  35. 615ad6c IVGCVSW-6169 Add GpuAcc Conv3d Workload by Teresa Charlin · 2 years, 8 months ago
  36. 4692e11 IVGCVSW-6440 Print new Optimize and LoadedNetwork profiling points by Kevin May · 2 years, 9 months ago
  37. 1b2654f IVGCVSW-5985 Remove deprecated code by Jan Eilers · 2 years, 9 months ago
  38. 1222dbd IVGCVSW-3706 Add Channel Shuffle Workload to GpuAcc backend by Teresa Charlin · 2 years, 10 months ago
  39. 22f601b Fix incorrect string name for workload construct by Keith Davis · 2 years, 10 months ago
  40. bcd860a IVGCVSW-6249 Add ProfilingDetails Macros to all workloads in CL by Keith Davis · 2 years, 11 months ago
  41. 5a64f22 IVGCVSW-5980 Add Descriptor, TensorInfo and Convolution algorithm to JSON by Keith Davis · 2 years, 11 months ago
  42. 554fa09 IVGCVSW-5980 JSON profiling output by Keith Davis · 3 years ago
  43. 77c92e4 Fix compilation failure in CL Master nightly by Nikhil Raj · 3 years, 1 month ago
  44. 50de4fa IVGCVSW-6088 Add Sin and Log to ElementWiseUnary by Teresa Charlin · 3 years, 1 month ago
  45. 53ef795 IVGCVSW-5826 Change weights layout for depthwise to [1,H,W,I*M] by Jan Eilers · 3 years, 1 month ago
  46. 401c1c3 IVGCVSW-6072 NeonReduceWorkloadValidate not declared in IS_MULTI_AXES_REDUCE_SUPPORTED by Matthew Sloyan · 3 years, 1 month ago
  47. 5fc0fd6 MLCE-418 Reduce layer does not support multiple axes by Matthew Sloyan · 3 years, 2 months ago
  48. ae12306 Revert "MLCE-418 Reduce layer does not support multiple axes" by Matthew Sloyan · 3 years, 2 months ago
  49. d905dec MLCE-418 Reduce layer does not support multiple axes by Matthew Sloyan · 3 years, 2 months ago
  50. 1f58f03 IVGCVSW-5815 Generalise ConstCpuTensorHandle by James Conroy · 3 years, 2 months ago
  51. f40d6d4 IVGCVSW-5420 'Add CL support for CAST' by Sadik Armagan · 3 years, 2 months ago
  52. e11e63d IVGCVSW-5909 Fix CTS failure in GpuAcc DIV int32 by Teresa Charlin · 3 years, 2 months ago
  53. a274748 MLCE-347 'REDUCE_MIN, REDUCE_MAX, REDUCE_SUM Support' by Sadik Armagan · 3 years, 5 months ago
  54. c11ba46 IVGCVSW-4625 Add CL Rank Workload by David Monahan · 3 years, 7 months ago
  55. e944475 IVGCVSW-5482 'Add a ClCompileContext parameter to each ClWorkload Constructor' by Sadik Armagan · 3 years, 7 months ago
  56. fe3ec94 IVGCVSW-5092 Add CL Logical workload by James Conroy · 3 years, 8 months ago
  57. 33d2c78 IVGCVSW-5189 Fix error running EfficientNet-Lite on GpuAcc by Narumol Prangnawarat · 3 years, 8 months ago
  58. 0d4ed39 IVGCVSW-5328-5329 Fuse Activation Cleanup by Mike Kelly · 3 years, 8 months ago
  59. 07810fc IVGCVSW-5328-5329 Fuse Activation by Mike Kelly · 3 years, 8 months ago
  60. 24ac859 IVGCVSW-5334 Remove remaining boost::numeric_cast from armnn by Matthew Sloyan · 3 years, 9 months ago
  61. a2a512c COMPMID-3784 Fix 1 CTS MUL INT32 failure due to using SATURATE by Teresa Charlin · 3 years, 9 months ago
  62. be727be IVGCVSW-4973 Enable QLstm projection unit tests on CL by Teresa Charlin · 3 years, 9 months ago
  63. f3c2718 Update ACL pin to 840a72cc745c60eccbd26fe192b035ec68b2ee41 by Nikhil Raj · 3 years, 9 months ago
  64. 171214c IVGCVSW-5300 Remove some boost::numeric_cast from armnn/backends by Matthew Sloyan · 3 years, 10 months ago
  65. 04a7297 IVGCVSW-5157 'Pipe ModelOption through Network::LoadNetwork() to Workload factory' by Sadik Armagan · 3 years, 10 months ago
  66. 045f6be IVGCVSW-5156 Introduce ModelOptions to OptimizedNetwork by Sadik Armagan · 3 years, 10 months ago
  67. e386676 Update ACL pin to ec4dee8c68a3d0f6d63db184bfb2f4589429778e by Teresa Charlin · 3 years, 10 months ago
  68. 7ac3ca6 IVGCVSW-5167 Use a generic axis in CL/Neon LogSoftmax and Softmax workload by Teresa Charlin · 4 years ago
  69. 57512af Update ACL pin 42e57362933b7fa04f9a86297fa75ed38c5e3c97 by Teresa Charlin · 4 years ago
  70. 8398edc IVGCVSW-3896 Add CL LOG_SOFTMAX Workload by Teresa Charlin · 4 years ago
  71. 552ee4d Update ACL pin to aa95ddc2abb7cef0b2edd03f7c4c9d9c6b9d7cf4 by Teresa Charlin · 4 years ago
  72. 9b14bfc IVGCVSW-5005 Fix Deprecated Functions in CL/NEON Resize Workload by David Monahan · 4 years ago
  73. 5266473 IVGCVSW-4903 Connect axis parameter in Gather from android to ACL. by Teresa Charlin · 4 years ago
  74. 66aecb0 IVGCVSW-4621 Add CL FILL Workload by Sadik Armagan · 4 years ago
  75. 749294b remove BOM from files by Laurent Carlier · 4 years, 1 month ago
  76. 9ad2e5b IVGCVSW-3844 Add CL GATHER Workload by Teresa Charlin · 4 years, 3 months ago
  77. 4a0c9b9 IVGCVSW-4888 Update Resize Front end for new parameters by David Monahan · 4 years, 1 month ago
  78. 9fabf43 IVGCVSW-4200 Add CL EXP Workload IVGCVSW-4203 Add Neon EXP Workload by Sadik Armagan · 4 years, 1 month ago
  79. 2323af4 IVGCVSW-4450 Add CL Enhanced Quantized LSTM Workload by Ryan OShea · 4 years, 2 months ago
  80. 56b465d IVGCVSW-4831 Fix Packet header includes in backends by Finn Williams · 4 years, 2 months ago
  81. c1f6b09 IVGCVSW-4753 Refactor CL Softmax workload generalizing for different datatype by Teresa Charlin · 4 years, 2 months ago
  82. 0886ac4 MLCE-190: Neon and CL Constant Workloads do not support newer DataTypes by Mike Kelly · 4 years, 2 months ago
  83. 3c9e045 IVGCVSW-4483 Removes boost::polymorphic_pointer_downcast by Jan Eilers · 4 years, 3 months ago
  84. bb446e5 IVGCVSW-4483 Remove boost::polymorphic_downcast by Jan Eilers · 4 years, 3 months ago
  85. ac2770a IVGCVSW-4485 Remove Boost assert by Narumol Prangnawarat · 4 years, 3 months ago
  86. 2b030d9 IVGCVSW-4603 Support comparison operators in CL by Teresa Charlin · 4 years, 3 months ago
  87. ac47210 IVGCVSW-3813 Add Unary Elementwise Operation 'NEG' support to the android-nn-driver by Sadik Armagan · 4 years, 3 months ago
  88. b60dd24 IVGCVSW-4565 TENSOR_BOOL8 data type not supported in AndroidNN Driver by Sadik Armagan · 4 years, 4 months ago
  89. c9ea45a IVGCVSW-4375 Add support for Transpose by Mike Kelly · 4 years, 4 months ago
  90. a856501 IVGCVSW-4420 Failing Unit Test Cl: Quantize layer by Keith Davis · 4 years, 5 months ago
  91. 9b3e738 Clean up header inclusion in CL workloads. by Matthew Bentham · 4 years, 5 months ago
  92. 820eb14 MLCE-139: add capability to align corners for bilinear resize by Sang-Hoon Park · 4 years, 6 months ago
  93. a023c40 IVGCVSW-4262 Use ACL Permute and Reshape Validate function in Neon and CL by Kevin May · 4 years, 7 months ago
  94. d466a54 IVGCVSW-4370 Deprecate DataType::QuantizedSymm8PerAxis by Derek Lamberti · 4 years, 5 months ago
  95. 39ef3e5 Remove use of ArmNN.hpp where it is unnecessary. by Matthew Bentham · 4 years, 5 months ago
  96. f90c56d Rename quantized data types to remove ambiguity for signed/unsigned payloads by Derek Lamberti · 4 years, 6 months ago
  97. e56fb45 IVGCVSW-4295 Disable mixed precision in ClPooling2dWorkload by janeil01 · 4 years, 7 months ago
  98. e011d20 IVGCVSW-4209 Create a public API for the ArmNN Utils by Matteo Martincigh · 4 years, 7 months ago
  99. 9820d30 MLCE-115 Remove redundant error checking in CL backend by Matthew Bentham · 4 years, 7 months ago
  100. 899f64f IVGCVSW-3859 Per-channel QSymm8 support of Convolution2d in Cl by Keith Davis · 4 years, 7 months ago