Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / 1c5871166d8697b9c6388e8a4857a754b6e9bb5d / src
  1. 1c58711 Add MINMAX suffix to filenames of GEMM/IGEMM/PPMM/DWCONV micro-kernels by Marat Dukhan · 4 years, 4 months ago
  2. eb09a6b Rename F32/U8 output params to minmax params by Marat Dukhan · 4 years, 4 months ago
  3. a51cf48 Unify layout of min/max parameters by Marat Dukhan · 4 years, 4 months ago
  4. 1841b1a Avoid signbit in scalar PReLU micro-kernel by Marat Dukhan · 4 years, 4 months ago
  5. 05702cf Dynamically choose micro-kernel depending on active core by Marat Dukhan · 4 years, 4 months ago
  6. d21fdcb Fix FP16 SpMM incompatibility with gcc by Marat Dukhan · 4 years, 4 months ago
  7. 0d1052c iOS 6x8 microkernel based on Cortex-A75 but with X18 avoided. by Frank Barchard · 4 years, 4 months ago
  8. 4195af5 Avoid push d8, d9 for xnn_f32_dwconv_ukernel_up4x9__aarch64_neonfma_cortex_a55. by Frank Barchard · 4 years, 4 months ago
  9. 6f8c966 Use x13 instead of x18. by Frank Barchard · 4 years, 4 months ago
  10. 1c8bc0c Fix bug in Average Pooling operator by Marat Dukhan · 4 years, 5 months ago
  11. c58bd34 Fix bug in dilated max pooling with padding by Marat Dukhan · 4 years, 5 months ago
  12. 5868d80 Automatically switch to GAVGPOOL micro-kernels in Average Pooling operator by Marat Dukhan · 4 years, 5 months ago
  13. b187835 Polyfill _cvtu32_mask16 for Apple Clang 10.x by Marat Dukhan · 4 years, 5 months ago
  14. 057e796 For IOS disable assembly, falling back on intrinsics. by Frank Barchard · 4 years, 5 months ago
  15. 8fb9055 4x8 GEMM and IGEMM microkernels for Cortex A55. 7.8% faster for e2e mobile net v2. by Frank Barchard · 4 years, 5 months ago
  16. b3801eb Micro-kernel selection for newly detected microarchitectures by Marat Dukhan · 4 years, 5 months ago
  17. 36053aa 4x8 AARCH32 GEMM/IGEMM avoid r2 push/pop. by Frank Barchard · 4 years, 5 months ago
  18. b7dd29e 4x8 GEMM and IGEMM microkernels for AARCH32 Cortex A55. 11.5% faster end to end: by Frank Barchard · 4 years, 5 months ago
  19. d6a5463 Refactor Average Pooling setup by Marat Dukhan · 4 years, 5 months ago
  20. d9e92eb Fix AVX and AVX512F PReLU microkernels by Marat Dukhan · 4 years, 5 months ago
  21. 90eca0a AVX and AVX512F versions of PReLU micro-kernel by Marat Dukhan · 4 years, 5 months ago
  22. f32ae34 Unify the value of $ABC variable across all templates by Marat Dukhan · 4 years, 5 months ago
  23. 5c5fa96 Auto-generate CLAMP micro-kernels by Marat Dukhan · 4 years, 5 months ago
  24. a63a6fc Refactor GAVGPOOL micro-kernels by Marat Dukhan · 4 years, 5 months ago
  25. 660fd19 Rename BILINEAR microkernels into IBILINEAR by Marat Dukhan · 4 years, 5 months ago
  26. 64debce Cortex-A55 cpu detect and select 6x8 GEMM and IGEMM microkernels. 9% faster end to end on mobile net v2. 16.5% faster on mobile net v1. 6.4% faster on mobile net v3. by Frank Barchard · 4 years, 5 months ago
  27. fe7acb6 Targets for requantization tests and benchmarks by Marat Dukhan · 4 years, 5 months ago
  28. 91e1999 6x8 GEMM and IGEMM microkernels for Cortex A55. 9% faster end to end: by Frank Barchard · 4 years, 5 months ago
  29. f42facc Completely remove NaCl and PNaCl support by Marat Dukhan · 4 years, 5 months ago
  30. 49a5969 More descriptive entry point names for operators with groups by Marat Dukhan · 4 years, 5 months ago
  31. 892687b Fix typo in comment by Marat Dukhan · 4 years, 5 months ago
  32. f092a4a f32-maxpool microkernel for ARM Neon. by Frank Barchard · 4 years, 5 months ago
  33. 5b3185b Merge pull request #381 from mattn:build-windows by XNNPACK Team · 4 years, 5 months ago
  34. 21d3bd6 Support Average Pooling and Max Pooling in Subgraph API by Marat Dukhan · 4 years, 5 months ago
  35. dac1a0e Fix macro for exception to disable exception by Yasuhiro Matsumoto · 4 years, 5 months ago
  36. 462be05 Build on Windows by Yasuhiro Matsumoto · 4 years, 5 months ago
  37. 466da75 Support TF SAME padding in Average Pooling operator by Marat Dukhan · 4 years, 5 months ago
  38. bee7825 Support TF SAME padding in Max Pooling operator by Marat Dukhan · 4 years, 5 months ago
  39. 96171aa Refactor Average Pooling operator by Marat Dukhan · 4 years, 5 months ago
  40. ee1f63e Support input_offset in AVGPOOL and PAVGPOOL micro-kernels by Marat Dukhan · 4 years, 5 months ago
  41. 6ee435a Refactor AVGPOOL & PAVGPOOL micro-kernels & unit tests by Marat Dukhan · 4 years, 5 months ago
  42. 7493bfb Add Qualcomm Krait cpu detect and initial kernel. by Frank Barchard · 4 years, 5 months ago
  43. c8230a4 Remove output_min & output_max arguments in PReLU operator by Marat Dukhan · 4 years, 5 months ago
  44. 7353eea Fix typo in initialization of GEMM micro-kernels for WAsm SIMD by Marat Dukhan · 4 years, 6 months ago
  45. 2995427 Optimized Indirect Deconvolution algorithm for 1x1 subconvolutions by Marat Dukhan · 4 years, 6 months ago
  46. 5b5a062 Use generic LD64 GEMM/IGEMM micro-kernels on Cortex-A5/A7 by Marat Dukhan · 4 years, 6 months ago
  47. b00004d 4x2c4 GEMM micro-kernels for PSIMD and SSE by Marat Dukhan · 4 years, 6 months ago
  48. 52261a8 IGEMM for Cortex-A75 aarch32 pad stack so vector push is aligned. by Frank Barchard · 4 years, 6 months ago
  49. 775d349 Detect Cortex-A53/A55 and use IGEMM optimized for Cortex-A53 on aarch32 by Frank Barchard · 4 years, 6 months ago
  50. 16d7272 ks loop use B.HI instead of B.NE to avoid bugs causing infinite loop. by Frank Barchard · 4 years, 6 months ago
  51. d6f77a6 Fix bug in computing batch size in activations by Marat Dukhan · 4 years, 6 months ago
  52. c87a8fd Cortex A53 IGEMM 32 bit ARM by Frank Barchard · 4 years, 6 months ago
  53. c1a0697 Replace load with mov for ks in xnn_f32_igemm_ukernel_4x8__aarch32_neon_cortex_a75 by Frank Barchard · 4 years, 6 months ago
  54. 9b499d6 Load parameters in order of usage. by Frank Barchard · 4 years, 6 months ago
  55. 52bd86f Support Clamp, HardSwish, Sigmoid, Softmax in Subgraph API by Marat Dukhan · 4 years, 6 months ago
  56. 8155854 Direct branch to source remainder handler for GEMM/IGEMM. by Frank Barchard · 4 years, 6 months ago
  57. 79ade18 LD64 microkernels branch directly to remainder if less than 2 channels. by Frank Barchard · 4 years, 6 months ago
  58. 7cdeede CPU detect and select Cortex-A75 IGEMM for 32 bit ARM. by Frank Barchard · 4 years, 6 months ago
  59. fd262e1 IGEMM 4x8 LD64 pad stack with 4 bytes to align to 8 bytes by Frank Barchard · 4 years, 6 months ago
  60. 90ce789 Cortex A75 IGEMM 32 bit ARM. by Frank Barchard · 4 years, 6 months ago
  61. 90dff80 Work around MemorySanitizer alarm in AVX512 DWCONV micro-kernels by Marat Dukhan · 4 years, 6 months ago
  62. dc38f07 LD64 IGEMM 32 bit ARM by Frank Barchard · 4 years, 6 months ago
  63. 2fd2ba1 Support PReLU operator in Subgraph API by Marat Dukhan · 4 years, 6 months ago
  64. 54dcb46 Support Add2 and Multiply2 Nodes in Subgraph API by Marat Dukhan · 4 years, 6 months ago
  65. 01a1e98 Fix data pointers for static inputs in Subgraph API by Marat Dukhan · 4 years, 6 months ago
  66. bdb56f5 FP16 versions of SpMM micro-kernels by Marat Dukhan · 4 years, 6 months ago
  67. d16d0f0 Work around msan failured in AVX micro-kernels by Marat Dukhan · 4 years, 6 months ago
  68. 022c659 Support multithreading in Subgraph API by Marat Dukhan · 4 years, 6 months ago
  69. 484bfc4 Kryo, Cortex-A77 and Exynos-M5 use IGEMM 4x8 with no prefetch. by Frank Barchard · 4 years, 6 months ago
  70. fbbb40e Add Cortex-A77 and Exynos-M5 to init. by Frank Barchard · 4 years, 6 months ago
  71. 4d402b4 Fix another typo bug in runtime initialization by Marat Dukhan · 4 years, 6 months ago
  72. 93d61a7 Fix typo bug in XNNPACK runtime construction by Marat Dukhan · 4 years, 6 months ago
  73. 6866099 Harden DWCONV micro-kernels with extra asserts by Marat Dukhan · 4 years, 6 months ago
  74. 1d75a54 Subgraph API by Marat Dukhan · 4 years, 6 months ago
  75. fd8e689 Rename SoftArgMax operator to SoftMax by Marat Dukhan · 4 years, 6 months ago
  76. 1edc454 SoftArgMax operator by Marat Dukhan · 4 years, 6 months ago
  77. 8137e4c NEON/NEONFMA RAddStoreExpMinusMax micro-kernels by Marat Dukhan · 4 years, 6 months ago
  78. b39689d SSE2/PSIMD RAddStoreExpMinusMax micro-kernels by Marat Dukhan · 4 years, 6 months ago
  79. f46f675 Scalar RAddStoreExpMinusMax micro-kernels by Marat Dukhan · 4 years, 7 months ago
  80. d6ebf0c 6x8 a53 use X8 for GPR shadow register. Eliminate GPR push/pop by Frank Barchard · 4 years, 7 months ago
  81. 534375d A53 GEMM / IGEMM kernel prefetches adjust by 1 by Frank Barchard · 4 years, 7 months ago
  82. c03b2bd 4x12 A53 GEMM and IGEMM use X8 for temp GPR by Frank Barchard · 4 years, 7 months ago
  83. 324f2bb 4x8 A53 GEMM use X4 for temp GPR Saves a push/pop of X19. by Frank Barchard · 4 years, 7 months ago
  84. 7693acf 4x8 Cortex-A53 GEMM / IGEMM use 1 GPR instead of 2. by Frank Barchard · 4 years, 7 months ago
  85. f884a7b 6X8 Cortex-A53 GEMM use 1 GPR instead of 2. by Frank Barchard · 4 years, 7 months ago
  86. 54afb13 Use 2 GPR registers instead of 4 for GPR loads. by Frank Barchard · 4 years, 7 months ago
  87. cbb35d0 4x12 IGEMM use prefetch on A and B by Frank Barchard · 4 years, 7 months ago
  88. 3216758 6X8 Cortex-A53 IGEMM use 1 GPR instead of 2. by Frank Barchard · 4 years, 7 months ago
  89. 4cd8907 4x12 A53 kernel use prefetches on A by Frank Barchard · 4 years, 7 months ago
  90. 26cda6d Fix gcc incompatibilities in NEON Sigmoid micro-kernels by Marat Dukhan · 4 years, 7 months ago
  91. c01d8a4 A53 aarch32 pipelined. 19.2% faster 4x8 GEMM, 9.3% faster end to end by Frank Barchard · 4 years, 7 months ago
  92. b177732 Remove prefetch of output buffer from A53 kernels. by Frank Barchard · 4 years, 7 months ago
  93. fa0a432 F32 Sigmoid micro-kernels in AVX2 implementation by Marat Dukhan · 4 years, 7 months ago
  94. 4a24a58 Use 1-step range reduction in NEONFMA Sigmoid micro-kernels by Marat Dukhan · 4 years, 7 months ago
  95. 77221d3 NEON Sigmoid evaluation stubs with 1-step range reduction by Marat Dukhan · 4 years, 7 months ago
  96. 7241600 AVX2 Sigmoid accuracy evaluation stubs by Marat Dukhan · 4 years, 7 months ago
  97. 68b3b45 Complete set of NEON F32 Sigmoid micro-kernels by Marat Dukhan · 4 years, 7 months ago
  98. 1f5d9bc Apply patch to cpuinfo by Marat Dukhan · 4 years, 7 months ago
  99. 8d3c07e Additional Sigmoid micro-kernels and accuracy evaluation stub by Marat Dukhan · 4 years, 7 months ago
  100. 279908a A75 / A53 aarch32 epilogue reordered by B the same as main loop. by Frank Barchard · 4 years, 7 months ago