1. cb80197 Disable GEMM/IGEMM micro-kernels with swizzle by Marat Dukhan · 5 years ago
  2. 4232323 Unify naming of functions in benchmark::utils:: by Marat Dukhan · 5 years ago
  3. 31a98d7 Remove warnings about inefficient padding parameters in Convolution by Marat Dukhan · 5 years ago
  4. 1756f9e Propagate GEMM/IGEMM SR argument to weights packing in Fully Connected operator by Marat Dukhan · 5 years ago
  5. e0df831 Remove trailing whitespace by Marat Dukhan · 5 years ago
  6. 07cb676 Refactor initialization of even/odd masks in parameters for SpCHW micro-kernels by Marat Dukhan · 5 years ago
  7. 838c8e3 Refactor initialization of masks in parameters for SpCHW micro-kernels by Marat Dukhan · 5 years ago
  8. caf8544 LD64/LD128 kernels remove all pushes (d8-d15) Remap d12-d15 to d16-d19 by Frank Barchard · 5 years ago
  9. fcfdc0e Automated g4 rollback of changelist 274728310. by Frank Barchard · 5 years ago
  10. 05ac8e3 VSCALE microkernel and SoftMax Three-Pass algorithm with Reloading by Marat Dukhan · 5 years ago
  11. 4a4a7fa Three-Pass Softargmax benchmark (recomputing version) by Marat Dukhan · 5 years ago
  12. 8e3c551 1x8 a53 kernel refactor based on a57. by Frank Barchard · 5 years ago
  13. baa9ead Update assembly Copyright notice to // comment by Frank Barchard · 5 years ago
  14. 9757953 Refactor and open-source Three-Pass Softmax micro-kernels by Marat Dukhan · 5 years ago
  15. 459c9fc 6x8 and a53 kernel comments. by Frank Barchard · 5 years ago
  16. 515c977 Refactor and open-source vectorized expminus function by Marat Dukhan · 5 years ago
  17. f6839e1 Refactor vectorized exp functions by Marat Dukhan · 5 years ago
  18. 2af471b Switch default intrinsics kernel to 6x8 by Frank Barchard · 5 years ago
  19. 9cdade3 Add prefetch instructions to 16x1, 16x2, 16x4 kernels. by Erich Elsen · 5 years ago
  20. 34dc2c0 Add gavgpool_spchw_scalar__x1 kernel. by Erich Elsen · 5 years ago
  21. ac4de80 Add chw 3x3s2p1_scalar kernels. by Erich Elsen · 5 years ago
  22. 0cc2c53 add 3x3p1_scalar kernel by Erich Elsen · 5 years ago
  23. a5ca10e Neon intrinsics clamping - Replace 2 LD1R with 1 LD2R by Frank Barchard · 5 years ago
  24. 6adff4e Vectorized implementations of expf function for AVX2 and AVX512F by Marat Dukhan · 5 years ago
  25. bd9e495 Remove 4x12 intrinsics kernels. by Frank Barchard · 5 years ago
  26. 7e95597 Pass XNN_ENABLE_ASSEMBLY for all tests and kernel benchmarks by Frank Barchard · 5 years ago
  27. 8fe54e4 Extra :xnnpack_operators_nhwc_f32 target with only F32 operators in NHWC layout by Marat Dukhan · 5 years ago
  28. 810171d Enable assembly by default. by Frank Barchard · 5 years ago
  29. 21be34f 1x8 A53 GEMM, GEMMINC and IGEMM microkernels. by Frank Barchard · 5 years ago
  30. db45b6a 1x8 neonfma IGEMM microkernel and 1x8 benchmarks. by Frank Barchard · 5 years ago
  31. 174706e Fix misleading comments for debug_build/optimized_build Bazel configs by Marat Dukhan · 5 years ago
  32. dbafc58 extend build flag --define=xnn_enable_assembly=true to GEMM and IGEMM benchmarks. by Frank Barchard · 5 years ago
  33. 4e0249a Add performance results on MobileNets & Pixel phones by Marat Dukhan · 5 years ago
  34. 466b523 Use GEMM/IGEMM micro-kernels with Swizzle on WAsm SIMD by Marat Dukhan · 5 years ago
  35. f633c2c Fix Bazel symblinks in .gitignore by Marat Dukhan · 5 years ago
  36. 523448a Add .gitignore file by Marat Dukhan · 5 years ago
  37. 2dbdc2f CMake build configurations by Marat Dukhan · 5 years ago
  38. afbca9a Remove unused x21 and switch x20 to x8 to avoid push. by Frank Barchard · 5 years ago
  39. d620972 Group operators in public header by data type by Marat Dukhan · 5 years ago
  40. 5609a08 Document xnn_initialize and xnn_deinitialize functions by Marat Dukhan · 5 years ago
  41. cf056b2 Hide all emscripten-specific sources behind xnnpack_cc_library rule by Marat Dukhan · 5 years ago
  42. 0c57d2a Fix Bazel build for XNNPACK when using emscripten toolchain. by Daniel Smilkov · 5 years ago
  43. 1a729ec Internal change by Marat Dukhan · 5 years ago
  44. d343c22 Avoid cpuinfo dependency in Emscripten builds by Marat Dukhan · 5 years ago
  45. 1aaabb6 Remove unused field _np in GemmMicrokernelTester by Marat Dukhan · 5 years ago
  46. 885ca24 Support MacOS build with Bazel by Marat Dukhan · 5 years ago
  47. dd69f0b Rename XNN_CONVOLUTION_FLAG_DEPTHWISE to XNN_FLAG_DEPTHWISE_CONVOLUTION by Marat Dukhan · 5 years ago
  48. c8e00eb Disable logging in optimized builds, limit logging in fastbuild by Marat Dukhan · 5 years ago
  49. 12f1dea Increase static memory in Emscripten benchmarks to 128MB by Marat Dukhan · 5 years ago
  50. c068bb6 End-to-end benchmarks on MobileNet v1 and MobileNet v2 models by Marat Dukhan · 5 years ago
  51. 4efb351 Document availability of Fully Connected operator by Marat Dukhan · 5 years ago
  52. 1b0421b 1x12 and 1x8 assembly kernel cleanup by Frank Barchard · 5 years ago
  53. 4e45e66 Support Linux/AArch64 platform by Marat Dukhan · 5 years ago
  54. b8ab4cb Fix signed/unsigned mismatch warning in SpMM benchmarks by Marat Dukhan · 5 years ago
  55. c6edf92 Fix bug in Fully Connected F32 unit tests by Marat Dukhan · 5 years ago
  56. 9d056a4 Compatibility with TF.js WAsm build by Marat Dukhan · 5 years ago
  57. 3bcea2b Final touch before open-source release by Marat Dukhan · 5 years ago
  58. 08c4a43 Bazel BUILD file for XNNPACK by Marat Dukhan · 5 years ago
  59. 452662b Fix XNNPACK build on Mac by Marat Dukhan · 5 years ago
  60. f8c8046 Cleanup redundant #includes by Marat Dukhan · 5 years ago
  61. 341c321 Remove unused XNN_INTERNAL_EXTRA_BYTES constant by Marat Dukhan · 5 years ago
  62. df6985f Map Exynos-M[1-4] micro-architectures to equivalents in OSS cpuinfo by Marat Dukhan · 5 years ago
  63. 33f0c7a Guard Ruy and GemmLowp benchmarks by Marat Dukhan · 5 years ago
  64. d62f3cc Avoid using cpuinfo_get_max_cache_size() function by Marat Dukhan · 5 years ago
  65. 22f38e4 Refactor architecture identification macros by Marat Dukhan · 5 years ago
  66. 1dadbf7 Limit direct dependencies on cpuinfo by Marat Dukhan · 5 years ago
  67. 629a33e Fix incompatibilities with open-source Bazel-based build by Marat Dukhan · 5 years ago
  68. 4c2637d LD2R for loading clamp parameters by Frank Barchard · 5 years ago
  69. bb4c18b Report Freq in additional benchmarks by Frank Barchard · 5 years ago
  70. 80fc932 Unify comments style by Marat Dukhan · 5 years ago
  71. b455b12 Initial open-source release by XNNPACK Team · 5 years ago