Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / eff8d95991205e874091576e2d225f63246dd0bb / src
  1. eff8d95 COMPMID-1316 Using 8 bit dot product instruction in CLDepthWiseConvolution with QASYMM8 by Giorgio Arena · 6 years ago
  2. 74b671b COMPMID-1188: Remove FP16 capabilities check form NEReshapeLayer. by Georgios Pinitas · 6 years ago
  3. ef776a8 COMPMID-1386: Add FC convert weights on NEON by Georgios Pinitas · 6 years ago
  4. a855af1 COMPMID-1401 Implement NEFullyConnectedLayer for QASYMM8 by Giorgio Arena · 6 years ago
  5. 5a3ee4f COMPMID-1347: Simplified CPUInfo enum by Anthony Barbier · 6 years ago
  6. eaefd00 COMPMID-1419: Make NEGEMMAssemblyDispatch dynamically typed instead of templated by Anthony Barbier · 6 years ago
  7. c8e84b5 COMPMID-1405: Create our own gemm_native kernel / function. by Anthony Barbier · 6 years ago
  8. 3efb375 COMPMID-1347: Fixed fallback CPUInfo populate function and added latest CPUs by Anthony Barbier · 6 years ago
  9. 96fc1d6 COMPMID-1394: Fixed OCLGrind failures ColorConvert by Pablo Tello · 6 years ago
  10. 7d66a8e COMPMID-1386: Add support for converting weights for CL. by Georgios Pinitas · 6 years ago
  11. ae54e02 COMPMID-1364: Add support for NHWC in NEDepthConcatenateLayer by Georgios Pinitas · 6 years ago
  12. b0b3717 COMPMID-1417: (Nightly) OCLGrind failures in winograd_output_transform_nhwc by Georgios Pinitas · 6 years ago
  13. dbbe4a3 COMPMID-1412; (Nightly) OCLGrind failures in input_transform CL NHWC by Georgios Pinitas · 6 years ago
  14. e155337 COMPMID-1357: Stop passing around raw pointers in NEWinogradConvolution by Anthony Barbier · 6 years ago
  15. 578225e COMPMID-1357: Port NEWinogradConvolution to use NEGEMMAssemblyDispatch by Anthony Barbier · 6 years ago
  16. d02eb45 COMPMID-1411 (Nightly) CLWinograd 5x5 mismatches by Giorgio Arena · 6 years ago
  17. e29acf1 COMPMID-1365: Add support for NHWC in CLDepthConcatenateLayer by Georgios Pinitas · 6 years ago
  18. 76259ca COMPMID-1385: Fixed QASYMM8 mismatches by Pablo Tello · 6 years ago
  19. 42447c1 COMPMID-1188: Fixes LSTM IO dimension requirements. by Georgios Pinitas · 6 years ago
  20. 6f109bd COMPMID-1409: Disable BN + Act fusion in the graph if activation is not supported by Georgios Pinitas · 6 years ago
  21. 7b607dc COMPMID-1400: Add command line option to specify the tuner's config file by Anthony Barbier · 6 years ago
  22. 3d31946 COMPMID-807: NHWC support in CLDirectConvolution. by Pablo Tello · 6 years ago
  23. 92d2081 COMPMID-1271 Avoid memory leak in list of gemm methods by Anthony Barbier · 6 years ago
  24. 6200fa4 COMPMID-1288 Optimizing CLGEMMLowp using 8 bit dot product instruction by Giorgio Arena · 6 years ago
  25. ea55f91 COMPMID-1373 Enable tests for CLWinogradConvolutionLayer for NHWC by Giorgio Arena · 6 years ago
  26. 5376c4c COMPMID-1399: In ITensor::copy_from, line_size contains twice num_channels by Anthony Barbier · 6 years ago
  27. 67fd4e8 COMPMID-1381: Fix nightly build failure on armv7 by Anthony Barbier · 6 years ago
  28. 5b52fe3 COMPMID-1390: OCLGrind and benchmark tests fail for QASYMM8 by Georgios Pinitas · 6 years ago
  29. 71d9b57 COMPMID-1381: Cleaned up the AssemblyHelper interface by Anthony Barbier · 6 years ago
  30. d1794eb COMPMID-1226 Extend CLMeanStdDev to support FP32 / FP16 by Michalis Spyrou · 6 years ago
  31. 7777b1a COMPMID-1388: Change default CLTuner to the one for the detected GPU by Georgios Pinitas · 6 years ago
  32. 7784c83 COMPMID-1167: Validation for NEDepthwiseConvolutionLayer by Abe Mbise · 6 years ago
  33. b03f7c5 COMPMID-1188 : Rename TNOX to Mali-G76 by Georgios Pinitas · 6 years ago
  34. 12be7ab COMPMID-1310: Create graph validation executables. by Georgios Pinitas · 6 years ago
  35. e39334c COMPMID-1271: New system for GEMM heuristics by David Mansell · 6 years ago
  36. e8bd2c7 COMPMID-1384: graph_mobilenet fails for NHWC on OpenCL by Georgios Pinitas · 6 years ago
  37. ed32f43 COMPMID-1383: OCLGrind failure in CLDepthwiseConvolution 3x3 stride 1 NHWC by Georgios Pinitas · 6 years ago
  38. cdb43bd COMPMID-1246: Fixed typo in MidgardTuner.h filename by Anthony Barbier · 6 years ago
  39. ff12a76 COMPMID-1387: Removed unnecessary extended_atomics extension for clMeanStdDevKernel by Anthony Barbier · 6 years ago
  40. 42a3172 COMPMID-1124 : Fixes in CLLSTM layer by Georgios Pinitas · 6 years ago
  41. d28b751 COMPMID-1340 - Implementing Winograd Convolution Layer 1x5/5x1 on OpenCL NHWC by Gian Marco Iodice · 6 years ago
  42. 3a3b431 COMPMID-1378: Graph: bias in FullyConnectedLayer should always have data type S32 by Michele Di Giorgio · 6 years ago
  43. d304e80 COMPMID-1349: Add support for QASYMM8 LOGISTIC activation in CLActivationLayer by Michele Di Giorgio · 6 years ago
  44. d93991e COMPMID-1380: Pre-work for SVE support. by David Mansell · 6 years ago
  45. 149fdf3 COMPMID-1337 Implementing Winograd Convolution Layer 1x3 and 3x1 kernels on OpenCL NHWC by Giorgio Arena · 6 years ago
  46. 876be2a COMPMID-1339 - Implementing Winograd Convolution Layer 1x5 and 5x1 kernels on OpenCL NCHW by Gian Marco Iodice · 6 years ago
  47. 09daf4d COMPMID-1246 Change CLLSTM in order to match android tests by Michalis Spyrou · 6 years ago
  48. 2fab0c2 COMPMID-1246 Fix CLDeconvolution arguments when calculating by Michalis Spyrou · 6 years ago
  49. f4cb81b COMPMID-970 : Remove QS8 / QS16 support by Vidhya Sudhan Loganathan · 6 years ago
  50. 060c4b7 COMPMID-1374: Fix constraints on AArch32 SGEMM. by David Mansell · 6 years ago
  51. 584252d COMPMID-1355: OpenMP compilation is broken. by Georgios Pinitas · 6 years ago
  52. 5f70773 COMPMID-1369: Revert accidental formatting of RSH's repo by Anthony Barbier · 6 years ago
  53. 7485d5a COMPMID-970 : Remove QS8 / QS16 support by Vidhya Sudhan Loganathan · 6 years ago
  54. de01468 COMPMID-1363: Handle null bias pointer in DirectConvolutionOutputStageKernel by Anthony Barbier · 6 years ago
  55. dce7bef COMPMID-1323: Added proper messages in graph NodeValidators. by Georgios Pinitas · 6 years ago
  56. 17d6d3c COMPMID-1352: Disable support for 4D softmax layer. by Georgios Pinitas · 6 years ago
  57. b7a2023 COMPMID-1358: Debug FB's graph example on Android. by Georgios Pinitas · 6 years ago
  58. a50e5e0 COMPMID-1338 Split winograd.cl by Giorgio Arena · 6 years ago
  59. 9e454f3 COMPMID-1350: (Nightly) Fix GEMMConvolutionLayer FP32/FP16 CL failing by Georgios Pinitas · 6 years ago
  60. 00b93f5 COMPMID-1325 Add data layout suffix to the config_id on OpenCL kernels by Giorgio Arena · 6 years ago
  61. d051e97 COMPMID-811 Add NHWC data format support for CL depthwise convolution by Giorgio Arena · 6 years ago
  62. f1c2bf0 COMPMID-1201 - Implementing Winograd Convolution Layer 1x3 and 3x1 kernels on OpenCL by Gian Marco Iodice · 6 years ago
  63. 4622ac1 COMPMID-1336: Add CLArithmeticAddition support for QASYMM8 by Michele Di Giorgio · 6 years ago
  64. f3139dd COMPMID-1334 (Nightly) Fix std::bad_alloc error in 32-bit NEON runs by Giorgio Arena · 6 years ago
  65. d89940e COMPMID-1345: Switched from using mutexes to atomics in the CPP Scheduler by Anthony Barbier · 6 years ago
  66. 19ea419 COMPMID-809: Add NHWC data format on CLGEMMConvolutionLayer. by Georgios Pinitas · 6 years ago
  67. bb71fe5 COMPMID-1253: Nightly: Fix Canny Edge NEON failing by Michele Di Giorgio · 6 years ago
  68. d3a78ab COMPMID-1283: (GitHub issue) after convolution output data is zero by Georgios Pinitas · 6 years ago
  69. be39f12 COMPMID-1204 Add NHWC data format support to Winograd input transform 4x4_5x5 by Giorgio Arena · 6 years ago
  70. 17b1230 COMPMID-1293: Handle aligned allocations by Georgios Pinitas · 6 years ago
  71. 09b1912 COMPMID-1294: (Nightly) Fix Im2Col mismatches by Georgios Pinitas · 6 years ago
  72. cfac9a1 COMPMID-1307: Mismatches in CLGEMMConvolutionLayer F16 by Georgios Pinitas · 6 years ago
  73. 80d65d8 COMPMID-1204 Add NHWC data format support to Winograd filter transform 4x4_5x5 by Giorgio Arena · 6 years ago
  74. 7210fe8 COMPMID-1204 Add NHWC data format support to Winograd output transform 4x4_5x5 by Giorgio Arena · 6 years ago
  75. fa23f11 COMPMID-1246 CLDepthwiseConvolution QASYMM8 NHWC kernel cleanup by Giorgio Arena · 6 years ago
  76. 7282d56 COMPMID-1287: Extending NEWinogradLayer test suite by Pablo Tello · 6 years ago
  77. 542e92d COMPMID-1067 NEON RNN FP32 / FP16 by Michalis Spyrou · 6 years ago
  78. 7221933 COMPMID-1145: (API) Introduce prepare() stage (NEON/CL/GLES) by Georgios Pinitas · 6 years ago
  79. c42f28d COMPMID-1048 Add NHWC data format support to Winograd input transform 4x4_3x3 by Giorgio Arena · 6 years ago
  80. 376c85f COMPMID-1180: Add support for bucket multi-threading (Part2) by Anthony Barbier · 6 years ago
  81. 8e74f44 COMPMID-911: Allow GEMM to work with 3D tensors by Isabella Gottardi · 6 years ago
  82. 0a88792 COMPMID-1222 Implementing CLArithmeticDivision - FP32 / FP16 by Michalis Spyrou · 6 years ago
  83. 7df2786 COMPMID-1162: Enable NHWC data layout support for NEWinogradConvolutionLayer - part1 by Pablo Tello · 6 years ago
  84. c084f0d COMPMID-1269: (Nightly) Fix CL/Winograd/OutputTransform mismatches by Georgios Pinitas · 6 years ago
  85. 14bd2cf COMPMID-1246: (OCLgrind) Fix casting from __global pointer by Michele Di Giorgio · 6 years ago
  86. 4a626a7 COMPMID-801: NHWC support in CLIm2Col. by Pablo Tello · 6 years ago
  87. e083771 COMPMID-1160 Turn Graph hints into heuristics by Giorgio Arena · 6 years ago
  88. 5cb3773 COMPMID-1278: Make intermediate tensors resizable in CLSoftmaxLayer::validate() by Michele Di Giorgio · 6 years ago
  89. d4b2c9f COMPMID-1270: Allow having weights with 1 IFM and multiple OFMs in CLDepthwiseConvolution3x3NCHW by Michele Di Giorgio · 6 years ago
  90. aaab602 COMPMID-1156: Allow memory reusage when trying to reallocate a smaller CLTensor by Michele Di Giorgio · 6 years ago
  91. dcb5b28 COMPMID-1048 Add NHWC data format support to Winograd filter transform 4x4_3x3 by Giorgio Arena · 6 years ago
  92. 17812ba COMPMID-817: Tuner: Port kernels to new design. by Georgios Pinitas · 6 years ago
  93. 1db7beb COMPMID-1256: Memory corruption in NEGEMM by Georgios Pinitas · 6 years ago
  94. 70ba7d6 COMPMID-1257: Allow retaining weights in CLDeconvolutionLayer by Michele Di Giorgio · 6 years ago
  95. 3695f9a COMPMID-1048 Add NHWC data format support to Winograd output transform 4x4_3x3 by Giorgio Arena · 6 years ago
  96. b62280a COMPMID-1244: Allow retaining weights in CLGEMMConvolutionLayer and CLFullyConnectedLayer by Michele Di Giorgio · 6 years ago
  97. da2491f COMPMID-1151: Templatize FunctionFactories. by Georgios Pinitas · 6 years ago
  98. d2d5f75 COMPMID-1199: Fixed mismatches in CLColorConvert. by Pablo Tello · 6 years ago
  99. 343722b COMPMID-1143 - Excessive padding in CLReductionOperationKernel when configuring window by Michalis Spyrou · 6 years ago
  100. e03342e COMPMID-799 - Use new OpenCL 8-bit dot product instruction by Michalis Spyrou · 6 years ago