Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / 77e93a2cd2f6b6de45b508f6a05e530fd0c9f156
  1. 77e93a2 Fix mismatch in block layout in mixed-layout Depth-To-Space operator by Marat Dukhan · 3 years, 7 months ago
  2. a5e242c QS8 LD32 GEMM microkernel for big cores with dotproduct by Frank Barchard · 3 years, 7 months ago
  3. 01c341b C8 MLA Neon GEMM/IGEMM microkernels count k down from kc. by Frank Barchard · 3 years, 7 months ago
  4. a414daa Enable Quantized C2 microkernel for Neon by Frank Barchard · 3 years, 7 months ago
  5. 36f95cf QS8 Neon IGEMM C16 microkernel with two 8 bit multiplies and vpadal to accumulate. by Frank Barchard · 3 years, 7 months ago
  6. 55d53a4 Fix bug in NHWC Convolution with depthwise kernels by Marat Dukhan · 3 years, 7 months ago
  7. 71c4d1a QS8 Neon GEMM C16 microkernel with two 8 bit multiplies and vpadal to accumulate. by Frank Barchard · 3 years, 7 months ago
  8. a6cba1d Add A55 microkernel to QS8 E2E benchmark. by Frank Barchard · 3 years, 7 months ago
  9. 6d138db Remove scalar C4 QS8 and QU8 gemm microkernels. by Frank Barchard · 3 years, 7 months ago
  10. a0fe11d QS8 C8 Neon remove remainder handling code and rewind the A pointers by kc by Frank Barchard · 3 years, 7 months ago
  11. 32389c6 QS8 e2e benchmark for C2 neon microkernels by Frank Barchard · 3 years, 7 months ago
  12. 6fa8078 QS8 C2 Neon igemm by Frank Barchard · 3 years, 7 months ago
  13. d79391d QS8 C8 Neon igemm by Frank Barchard · 3 years, 7 months ago
  14. aaafdc7 QS8 scalar gemm remove bias variables. by Frank Barchard · 3 years, 7 months ago
  15. fe14b85 Add space after casting by Frank Barchard · 3 years, 7 months ago
  16. 725a8e7 Wrap MR=1 end to end benchmarks with #if XNN_ENABLE_E2E_MR1 by Frank Barchard · 3 years, 8 months ago
  17. 10f9f05 Remove 0 from ranges where not needed by Frank Barchard · 3 years, 8 months ago
  18. 4baa2ac Process 32 pixels at a time in ARM64 SpMM microkernels by Marat Dukhan · 3 years, 8 months ago
  19. c8532ae Unroll KC loop to do MULL and then MLAL to 16 bit before lengthening to 32 bit. by Frank Barchard · 3 years, 8 months ago
  20. 4c032f3 E2E run benchmarks from fastest to slowest instruction set by Frank Barchard · 3 years, 8 months ago
  21. b8c9fa9 QS8 e2e benchmark add all x86 microkernels. by Frank Barchard · 3 years, 8 months ago
  22. 19f4748 QS8 e2e benchmark add all Web Assembly microkernels. by Frank Barchard · 3 years, 8 months ago
  23. 15c0036 QS8 e2e benchmark add all ARM microkernels. by Frank Barchard · 3 years, 8 months ago
  24. 2d6bcbb Reorder a few gemm1 initializations to match end to end order of gemm, igemm, gemm1, igemm1 by Jared Duke · 3 years, 8 months ago
  25. dc909cb qs8-gemm-e2e benchmark for comparing performance of quantized microkernels by Frank Barchard · 3 years, 8 months ago
  26. 9b7562b Reorder a few gemm1 initializations to match end to end order of gemm, igemm, gemm1, igemm1 by Frank Barchard · 3 years, 8 months ago
  27. 7e1f371 QS8 GEMM for neon reorder with MR inner loop so mull and mlal to avoid dependency on destination. by Frank Barchard · 3 years, 8 months ago
  28. 8247e21 C2 QS8 microkernel using mull then mlal with KC loop of 16 by Frank Barchard · 3 years, 8 months ago
  29. 5899012 QS8 Neon GEMM C8 microkernel with 8 bit multiply and vpadal to accumulate. by Frank Barchard · 3 years, 8 months ago
  30. a93765f Add MR=1 versions of QS8 gemm benchmarks by Frank Barchard · 3 years, 8 months ago
  31. 85b1e24 Merge pull request #1273 from powderluv:fix-compile by XNNPACK Team · 3 years, 8 months ago
  32. 6d490f7 Change isfinite() to std::isfinite() by Anush Elangovan · 3 years, 8 months ago
  33. 2202c81 Implement bilinear upsampling (CHW layout) for ARM architecture by Artsiom Ablavatski · 3 years, 8 months ago
  34. 2302ffd QS8 Neon GEMM microkernel with 8 bit multiply and vpadal to accumulate by Frank Barchard · 3 years, 8 months ago
  35. cadd422 Numerically sort microkernel filenames in BUILD files. by Frank Barchard · 3 years, 8 months ago
  36. ec0bf14 QS8 GEMM and IGEMM 3x8 3x16 and IGEMM 4x8 and 4x16 by Frank Barchard · 3 years, 8 months ago
  37. 4ecae2e QS8 Neon GEMM microkernel with 8 bit multiply by Frank Barchard · 3 years, 8 months ago
  38. b94e34b QS8 GEMM select 2x16 for Neon MLAL. by Frank Barchard · 3 years, 8 months ago
  39. cfbc849 Add 4x8 and 4x16 qs8 gemm microkernels by Frank Barchard · 3 years, 9 months ago
  40. db2475b Include <memory> for `std::addressof` after libc++ commit 7ad49aec125b3c1205b164331d0aa954d773f890. by XNNPACK Team · 3 years, 9 months ago
  41. abb547c Merge pull request #1257 from skyline75489:patch-3 by XNNPACK Team · 3 years, 9 months ago
  42. 5c29c64 Restore support for older armv7 devices by Chester Liu · 3 years, 9 months ago
  43. 25bab07 Improve architecture detection for Apple devices by Chester Liu · 3 years, 9 months ago
  44. c5704bf WebAssembly DWConv2D 3x3 stride 2 loadsplat by Frank Barchard · 3 years, 9 months ago
  45. e1ffe15 Merge pull request #1254 from malfet:enable-osx-cross-compilation by XNNPACK Team · 3 years, 9 months ago
  46. b126f9c Update cpuinfo checkout hash by Nikita Shulga · 3 years, 9 months ago
  47. 30dbea6 Add support for CMAKE_OSX_ARCHITECTURES by Nikita Shulga · 3 years, 9 months ago
  48. c6889b3 WebAssembly DWConv2D 5x5 stride 2 loadsplat by Frank Barchard · 3 years, 9 months ago
  49. e683659 Merge pull request #1252 from skyline75489:patch-1 by XNNPACK Team · 3 years, 9 months ago
  50. 4510c4a Exclude aarch32 & aarch64 ASM code accroding to XNNPACK_ENABLE_ASSEMBLY flag by Chester Liu · 3 years, 9 months ago
  51. 02bb429 WebAssembly DWConv2D 3x3p1 adapted from NEON by Frank Barchard · 3 years, 9 months ago
  52. b20dcd6 WASMSIMD dwconv2d 5x5p2 use loadsplat by Frank Barchard · 3 years, 9 months ago
  53. f7291fc Accuracy verification test for EXP evaluation stubs by Marat Dukhan · 3 years, 9 months ago
  54. 1a3db36 Fix CMake build by Marat Dukhan · 3 years, 9 months ago
  55. d28a5a2 Accuracy verification test for EXPMINUS evaluation stubs by Marat Dukhan · 3 years, 9 months ago
  56. c30f310 WASMSIMD dwconv2d chw 3x3p1 replace loadsplat with vector load and shuffle by Frank Barchard · 3 years, 9 months ago
  57. e332dd6 Fix bug in EXPM1MINUS and ELU implementation by Marat Dukhan · 3 years, 9 months ago
  58. f44f022 Accuracy verification test for EXPM1MINUS evaluation stubs by Marat Dukhan · 3 years, 10 months ago
  59. cf67ec6 Separate naming for accuracy evaluation benchmarks by Marat Dukhan · 3 years, 10 months ago
  60. 63ec750 Document support for Apple Silicon Macs by Marat Dukhan · 3 years, 10 months ago
  61. 51dd6eb Update Google Test dependency by Marat Dukhan · 3 years, 10 months ago
  62. dfe47b9 Use iOS microkernels for Apple Silicon Macs by Marat Dukhan · 3 years, 10 months ago
  63. 0fff1bd Update cpuinfo dependency by Marat Dukhan · 3 years, 10 months ago
  64. ced880d Add missing <memory> include in accuracy evaluation benchmarks by Marat Dukhan · 3 years, 10 months ago
  65. 4eddb9c Fix incompatibility with Apple Clang in Subgraph tester by Marat Dukhan · 3 years, 10 months ago
  66. 802fcae Additional SSE/SSE2 GEMM/IGEMM microkernels by Marat Dukhan · 3 years, 10 months ago
  67. 412e2f4 Rename WASMSIMD dwconv2d functions to splat or loadsplat by Frank Barchard · 3 years, 10 months ago
  68. 3de5dfa Remove PSIMD dependency by Marat Dukhan · 3 years, 10 months ago
  69. 094e692 Support sparse rewriting for clusters with ELU operator by Marat Dukhan · 3 years, 10 months ago
  70. c1aa297 Inroduce `timeout` parameter into `xnnpack_unit_test` by Artsiom Ablavatski · 3 years, 10 months ago
  71. b36582b Enable sparse inference by default by Marat Dukhan · 3 years, 10 months ago
  72. cfbed0a Disable sparse graph rewriting on x86 with AVX+ by Marat Dukhan · 3 years, 10 months ago
  73. c10585f Minor refactoring of SubgraphTester by Marat Dukhan · 3 years, 10 months ago
  74. 54b2d54 Disable sparse graph rewriting for clusters with <= 2/3 zeroes by Marat Dukhan · 3 years, 10 months ago
  75. 6f7d4a2 Remove unused input_width_tile from dwconv2d_chw_parameters by Marat Dukhan · 3 years, 10 months ago
  76. 4ddfab4 Optimize CHW microkernel selection for pre-NEON AArch32 by Marat Dukhan · 3 years, 10 months ago
  77. c763488 CONV2D HWC2CHW microkernel for ARM NEON by Marat Dukhan · 3 years, 10 months ago
  78. 3e91338 Initialize pointers to NEON CHW microkernels by Marat Dukhan · 3 years, 10 months ago
  79. c8bbe70 Benchmarks for NEON versions of DWCONV2D CHW microkernels by Marat Dukhan · 3 years, 10 months ago
  80. 3b32261 Simplify constant expressions in WAsm SIMD DWConv CHW by Frank Barchard · 3 years, 10 months ago
  81. 0725b8d Rename WebAssembly SIMD source files and functions with x86 or arm suffix after wasmsimd by Frank Barchard · 3 years, 10 months ago
  82. 5d7ca1a Remove duplicate WASMSIMD dwconv2d 5x5s2 tests by Frank Barchard · 3 years, 10 months ago
  83. c12dcda Fix typo in sparse rewriting by Marat Dukhan · 3 years, 10 months ago
  84. 7332e83 Add Runtime flag to indicate sparse inference preference by Marat Dukhan · 3 years, 10 months ago
  85. 1631e3e Refactor SpMM benchmarks by Marat Dukhan · 3 years, 10 months ago
  86. 3a30521 Refactor accuracy evaluation benchmarks by Marat Dukhan · 3 years, 10 months ago
  87. 5b86c43 NEON versions of non-blocked F32 SpMM microkernels by Marat Dukhan · 3 years, 10 months ago
  88. 2fa7a0c Build and test non-blocked NEONFMA SpMM microkernels on AArch32 by Marat Dukhan · 3 years, 10 months ago
  89. f56b4bb Fix classification of Depth-to-Space operator in Sparse rewriting by Marat Dukhan · 3 years, 10 months ago
  90. 102e9ea Revert "Remove PSIMD dependency" by Marat Dukhan · 3 years, 10 months ago
  91. c11e654 Document Alibaba HALO and Samsung ONE as XNNPACK users by Marat Dukhan · 3 years, 10 months ago
  92. cee4e95 Remove PSIMD dependency by Marat Dukhan · 3 years, 10 months ago
  93. 6eaa152 Update pthreadpool dependency by Marat Dukhan · 3 years, 10 months ago
  94. 892310c Simplify parallelization in elementwise binary and Padding operators by Marat Dukhan · 3 years, 10 months ago
  95. e7223ee WASMSIMD dwconv2d 5x5s2 tests and benchmark by Frank Barchard · 3 years, 10 months ago
  96. 4e89587 Guard microbenchmarks against running microkernels on incompatible CPUs by Marat Dukhan · 3 years, 10 months ago
  97. d713e8a Refactor microbenchmarks by Marat Dukhan · 3 years, 10 months ago
  98. ff0624e Add WebAssembly dwconv2d_chw_3x3s2p1 benchmark by Frank Barchard · 3 years, 10 months ago
  99. b88d011 WebAssembly SIMD DWConv2D 3x3 stride-2 adapted from NEON by Frank Barchard · 3 years, 10 months ago
  100. 729f07b WebAssembly SIMD DWConv2D 5x5 stride 2 adapted from NEON by Frank Barchard · 3 years, 10 months ago