Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / 6866099c75e3583a4879f732b76b5716abc81862 / src
  1. 6866099 Harden DWCONV micro-kernels with extra asserts by Marat Dukhan · 4 years, 8 months ago
  2. 1d75a54 Subgraph API by Marat Dukhan · 4 years, 8 months ago
  3. fd8e689 Rename SoftArgMax operator to SoftMax by Marat Dukhan · 4 years, 8 months ago
  4. 1edc454 SoftArgMax operator by Marat Dukhan · 4 years, 8 months ago
  5. 8137e4c NEON/NEONFMA RAddStoreExpMinusMax micro-kernels by Marat Dukhan · 4 years, 8 months ago
  6. b39689d SSE2/PSIMD RAddStoreExpMinusMax micro-kernels by Marat Dukhan · 4 years, 8 months ago
  7. f46f675 Scalar RAddStoreExpMinusMax micro-kernels by Marat Dukhan · 4 years, 9 months ago
  8. d6ebf0c 6x8 a53 use X8 for GPR shadow register. Eliminate GPR push/pop by Frank Barchard · 4 years, 9 months ago
  9. 534375d A53 GEMM / IGEMM kernel prefetches adjust by 1 by Frank Barchard · 4 years, 9 months ago
  10. c03b2bd 4x12 A53 GEMM and IGEMM use X8 for temp GPR by Frank Barchard · 4 years, 9 months ago
  11. 324f2bb 4x8 A53 GEMM use X4 for temp GPR Saves a push/pop of X19. by Frank Barchard · 4 years, 9 months ago
  12. 7693acf 4x8 Cortex-A53 GEMM / IGEMM use 1 GPR instead of 2. by Frank Barchard · 4 years, 9 months ago
  13. f884a7b 6X8 Cortex-A53 GEMM use 1 GPR instead of 2. by Frank Barchard · 4 years, 9 months ago
  14. 54afb13 Use 2 GPR registers instead of 4 for GPR loads. by Frank Barchard · 4 years, 9 months ago
  15. cbb35d0 4x12 IGEMM use prefetch on A and B by Frank Barchard · 4 years, 9 months ago
  16. 3216758 6X8 Cortex-A53 IGEMM use 1 GPR instead of 2. by Frank Barchard · 4 years, 9 months ago
  17. 4cd8907 4x12 A53 kernel use prefetches on A by Frank Barchard · 4 years, 9 months ago
  18. 26cda6d Fix gcc incompatibilities in NEON Sigmoid micro-kernels by Marat Dukhan · 4 years, 9 months ago
  19. c01d8a4 A53 aarch32 pipelined. 19.2% faster 4x8 GEMM, 9.3% faster end to end by Frank Barchard · 4 years, 9 months ago
  20. b177732 Remove prefetch of output buffer from A53 kernels. by Frank Barchard · 4 years, 9 months ago
  21. fa0a432 F32 Sigmoid micro-kernels in AVX2 implementation by Marat Dukhan · 4 years, 9 months ago
  22. 4a24a58 Use 1-step range reduction in NEONFMA Sigmoid micro-kernels by Marat Dukhan · 4 years, 9 months ago
  23. 77221d3 NEON Sigmoid evaluation stubs with 1-step range reduction by Marat Dukhan · 4 years, 9 months ago
  24. 7241600 AVX2 Sigmoid accuracy evaluation stubs by Marat Dukhan · 4 years, 9 months ago
  25. 68b3b45 Complete set of NEON F32 Sigmoid micro-kernels by Marat Dukhan · 4 years, 9 months ago
  26. 1f5d9bc Apply patch to cpuinfo by Marat Dukhan · 4 years, 9 months ago
  27. 8d3c07e Additional Sigmoid micro-kernels and accuracy evaluation stub by Marat Dukhan · 4 years, 9 months ago
  28. 279908a A75 / A53 aarch32 epilogue reordered by B the same as main loop. by Frank Barchard · 4 years, 9 months ago
  29. 3a77ea7 Scalar F32 Sigmoid micro-kernels by Marat Dukhan · 4 years, 9 months ago
  30. dffaa46 Remove sse2-p5-div.c.in Sigmoid template by Marat Dukhan · 4 years, 10 months ago
  31. 5739f70 Evaluation stubs for Sigmoid function in scalar implementation by Marat Dukhan · 4 years, 10 months ago
  32. 5e9a91e Evaluation stubs for ExpMinus function in scalar implementation by Marat Dukhan · 4 years, 10 months ago
  33. 9520fc9 Tighten the compiler detection guards in intrinsics-polyfill.h. by Ashkan Aliabadi · 4 years, 10 months ago
  34. 387c2d1 Generate A57 micro-kernels from A75 source. by Frank Barchard · 4 years, 10 months ago
  35. 005feb8 A53 push r1, r2 so they can be used as scratch. Reorder FMA by B by Frank Barchard · 4 years, 10 months ago
  36. 0090f5b 4x8 FMA sorted by B to match load order by Frank Barchard · 4 years, 10 months ago
  37. 5cc1cc2 Select a default kernel optimized for big cores. by Frank Barchard · 4 years, 10 months ago
  38. abf8154 Code generator for PLD and non-PLD versions of aarch32 4x8 Cortex-A75 kernel by Frank Barchard · 4 years, 10 months ago
  39. 9e0e8ee Fix gcc-6 build by Marat Dukhan · 4 years, 10 months ago
  40. 4d281a5 Enable PLD prefetch version of a75 microkernel for aarch32 by Frank Barchard · 4 years, 10 months ago
  41. 07efec4 Run generator for A73 kernel NOP by Frank Barchard · 4 years, 10 months ago
  42. f9a3484 Detect A53 in aarch32 and use a53 specific micro kernel. by Frank Barchard · 4 years, 10 months ago
  43. 9f7d555 Prefetch version of the aarch32 a75 GEMM kernel by Frank Barchard · 4 years, 10 months ago
  44. 73ccfb4 Move SUBS to 2nd instruction of clamp code. by Frank Barchard · 4 years, 10 months ago
  45. c659140 a73 kernel move SUBS before clamp and add NOP before branch by Frank Barchard · 4 years, 10 months ago
  46. 1391604 Initial Cortex A53 kernel for aarch32 by Frank Barchard · 4 years, 10 months ago
  47. d94b856 Rename strided gemm and igemm fma3 broadcasts. by Ashkan Aliabadi · 4 years, 10 months ago
  48. 9a88efe AVX & AVX512F versions of binary elementwise micro-kernels by Marat Dukhan · 4 years, 10 months ago
  49. f52eff5 Fix typos in AVX/AVX512 HSWISH micro-kernels by Marat Dukhan · 4 years, 10 months ago
  50. b738ad2 fix for linux arm 32 bit by Frank Barchard · 4 years, 10 months ago
  51. 662faa0 Refactor HardSwish micro-kernels by Marat Dukhan · 4 years, 10 months ago
  52. 2712132 FMA3 microkernels with 4-wide shuffle by Marat Dukhan · 4 years, 10 months ago
  53. 4c4eb00 Additional variants of Softmax microkernels by Marat Dukhan · 4 years, 10 months ago
  54. eccfd71 NR=16 GEMM and IGEMM micro-kernels in AVX and FMA3 implementations by Marat Dukhan · 4 years, 10 months ago
  55. 6918050 ND Divide operator with broadcasting support by Marat Dukhan · 4 years, 10 months ago
  56. 77ca630 Elementwise Divide micro-kernels by Marat Dukhan · 4 years, 10 months ago
  57. bd8a962 Fix incorrect indirection buffer size in pooling operators by Marat Dukhan · 4 years, 10 months ago
  58. 79e7f84 ND Maximum and Minimum operators (with broadcasting support) by Marat Dukhan · 4 years, 10 months ago
  59. 403b7d4 Elementwise minimum and maximum micro-kernels by Marat Dukhan · 4 years, 10 months ago
  60. 65a0139 Polyfill _mm512_reduce_add_ps and _mm512_reduce_max_ps for old gcc by Marat Dukhan · 4 years, 10 months ago
  61. cfb3134 Polyfill missing _cvtu32_mask16 intrinsic on old gcc by Marat Dukhan · 4 years, 10 months ago
  62. 03ff294 Fix incorrect indirection size computation for DWCONV by Marat Dukhan · 4 years, 10 months ago
  63. 3e237f2 AARCH32 4x8 for Cortex A75 by Frank Barchard · 4 years, 10 months ago
  64. f917cbd AARCH32 4x8 LD64 stores simplified by Frank Barchard · 4 years, 10 months ago
  65. 6383f49 Assembly GEMM kernel NC loop use SUBS instead of CMP+SUBS by Frank Barchard · 4 years, 10 months ago
  66. 441e221 Scalar 3x3s2c3 HWC dconv micro-kernel with 0+1 width padding by Marat Dukhan · 4 years, 10 months ago
  67. 6b7dfae Refactor scalar 3x3s2c3 HWC->HWC2CHW dconv, add 3x3s2c3 HWC dconv by Marat Dukhan · 4 years, 10 months ago
  68. 436ebe6 Separate WAsm micro-kernels and scalar micro-kernels by Marat Dukhan · 4 years, 10 months ago
  69. 05f3f6d Subtract ND operator by Marat Dukhan · 4 years, 10 months ago
  70. c4f0ff9 Support built-in transposition of static weights in Fully Connected operator by Marat Dukhan · 4 years, 10 months ago
  71. fc2b96e Support up to 6 dimensions in ND operators with broadcasting by Marat Dukhan · 4 years, 10 months ago
  72. bfd02cd Fix assert in AVX/AVX512 Clamp micro-kernels by Marat Dukhan · 4 years, 10 months ago
  73. b1a0fc3 Add ND operator with broadcasting by Marat Dukhan · 4 years, 10 months ago
  74. 61cad89 AARCH32 4x8 GEMM kernel fully register based. by Frank Barchard · 4 years, 10 months ago
  75. 3267092 Enable AARCH32 4x8 GEMM kernel by Frank Barchard · 4 years, 10 months ago
  76. 72d6afb AARCH32 4x8 kernel code clean up. by Frank Barchard · 4 years, 10 months ago
  77. 8b0f026 AARCH32 4x8 NEON GEMM Assembly version of 4x8 for 32 bit ARM. Based on LD64. by Frank Barchard · 4 years, 10 months ago
  78. e2c3f29 F32 CLAMP micro-kernels in AVX and AVX512F implementations by Marat Dukhan · 4 years, 10 months ago
  79. 479f87e AVX512F implementation of DWCONV micro-kernels by Marat Dukhan · 4 years, 10 months ago
  80. 91f8d86 Accuracy evaluation stubs for LUT-based Sigmoid implementations by Marat Dukhan · 4 years, 10 months ago
  81. 0f349c4 AVX512F implementation of GEMM & IGEMM micro-kernels by Marat Dukhan · 4 years, 10 months ago
  82. c72fa1e Use XNN_ARCH_* macros for architecture-specific parts in micro-kernels by Marat Dukhan · 4 years, 10 months ago
  83. 69172d9 6x8 ld128 GEMM microkernels by Frank Barchard · 4 years, 10 months ago
  84. 189ae80 Additional implementation of expminus function by Marat Dukhan · 4 years, 10 months ago
  85. 40a672f Move generated micro-kernels into a subdirectory by Marat Dukhan · 4 years, 10 months ago
  86. 9f08af4 Fix remaining incompatibility with ARM64 gcc in DWCONV SpCHW micro-kernel by Marat Dukhan · 4 years, 10 months ago
  87. 22aae13 Evaluation stubs for NEONFMA Sigmoid with alternative division implementations by Marat Dukhan · 4 years, 11 months ago
  88. 5243bb0 DUP Neon GEMM kernels for Exynos by Frank Barchard · 4 years, 11 months ago
  89. 17ec5f3 AVX and FMA3 microkernels for DWCONV by Marat Dukhan · 4 years, 11 months ago
  90. e3fad19 Fix wrong vreinterpret intrinsics in NEONFMA SpCHW DWCONV micro-kernels by Marat Dukhan · 4 years, 11 months ago
  91. 8c3b028 Fix wrong vget_low/high intrinsics in FP16 GEMM micro-kernels by Marat Dukhan · 4 years, 11 months ago
  92. 91317c5 Rename neon intrinsics to lane. by Frank Barchard · 4 years, 11 months ago
  93. 5743193 Fix typos in END_FUNCTION arguments in ARM64 assembly kernels by Marat Dukhan · 4 years, 11 months ago
  94. 1e782c4 Rename vunop and vbinop functions by Marat Dukhan · 4 years, 11 months ago
  95. 1025ea3 Enable AVX and FMA3 GEMM micro-kernels for non-mobile x86 by Marat Dukhan · 4 years, 11 months ago
  96. 496e735 SSE4.1 Sigmoid microkernels by Marat Dukhan · 4 years, 11 months ago
  97. fda12b8 AVX and FMA3 microkernels for GEMM/GEMMINC/IGEMM by Marat Dukhan · 4 years, 11 months ago
  98. 5480997 Replace IDLETTERS with ABC by Frank Barchard · 4 years, 11 months ago
  99. 866f7b3 Fix bugs in Depthwise Convolution and Average Pooling by Marat Dukhan · 4 years, 11 months ago
  100. d7a2c5f Remove erroneous assert in NEON DWCONV micro-kernels by Marat Dukhan · 4 years, 11 months ago