Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / 3357d9de85270a83a0cc8dff8a15e0be43a4603b / src
  1. e111861 1x8 C8 A53 microkernel defer adap by Frank Barchard · 3 years, 3 months ago
  2. 7c4c771 C8 A53 microkernels prefetch A by Frank Barchard · 3 years, 3 months ago
  3. 2a3169d C8 A53 microkernels move 2nd load after MLA by Frank Barchard · 3 years, 3 months ago
  4. ec51a4e Enable QS8 1x8C8 IGEMM microkernel for Cortex A53 by Frank Barchard · 3 years, 3 months ago
  5. dddb38f QS8 1x8C8 IGEMM microkernel for Cortex A53 by Frank Barchard · 3 years, 3 months ago
  6. 21acdd0 Enable QS8 1x8C8 GEMM microkernel for Cortex A53. by Frank Barchard · 3 years, 3 months ago
  7. 46a69c9 QS8 1x8C8 GEMM microkernel for Cortex A53 by Frank Barchard · 3 years, 3 months ago
  8. 042cdaf GCC 11 no longer needs this polyfill by Nenad Mikša · 3 years, 3 months ago
  9. 2de3bce A53 C8 microkernel load A with ldr/ldr/ins by Frank Barchard · 3 years, 3 months ago
  10. 184a8e1 Enable A53 C8 microkernel load A with ldr/ldr/ins by Frank Barchard · 3 years, 3 months ago
  11. 5549735 4X8 and 4x16 mla lane microkernels for A53 by Frank Barchard · 3 years, 3 months ago
  12. 90f520b Enable Cortex A53 tuned C8 gemm/igemm microkernels for Cortex A53 and Cortex A55r0 by Frank Barchard · 3 years, 3 months ago
  13. d68e114 Cortex A53 tuned C8 gemm/igemm microkernels by Frank Barchard · 3 years, 3 months ago
  14. fb5983d Enable prefetch to MLA lane microkernel on Cortex A53 by Frank Barchard · 3 years, 3 months ago
  15. 1f51d38 Add prefetch to MLA lane microkernel by Frank Barchard · 3 years, 3 months ago
  16. 8f15372 Expose QS8 Fully Connected operator in Subgraph API by Marat Dukhan · 3 years, 4 months ago
  17. a999225 Support 2D Convolution and 2D Depthwise Convolution without bias by Marat Dukhan · 3 years, 4 months ago
  18. 281f13e Simplify Fully Connected Node without bias by Marat Dukhan · 3 years, 4 months ago
  19. 4c6640c Disable MSan in QS8 GEMM/IGEMM microkernels with KR>1 by Marat Dukhan · 3 years, 4 months ago
  20. 3dd80b3 Fix allocator initialize issue on Windows by Larry Liu · 3 years, 4 months ago
  21. 676322f Merge pull request #1396 from huningxin:fully_connected by XNNPACK Team · 3 years, 4 months ago
  22. 6ac1d18 Cortex A53 used MLAL lane by Frank Barchard · 3 years, 4 months ago
  23. c77fc4c Bug fix add missing break for qs8 select on big core. by Frank Barchard · 3 years, 4 months ago
  24. ec56b7e Avoid selection of NEON-DOT microkernels on AArch32 iOS by Marat Dukhan · 3 years, 4 months ago
  25. 2a995e7 Enable PRFM variant of QS8 C8 Neon microkernel on Cortex A53, A72, A73 and Kryo. by Frank Barchard · 3 years, 4 months ago
  26. 4a35204 PRFM variant of QS8 C8 Neon microkernel. by Frank Barchard · 3 years, 4 months ago
  27. 3fd4e27 XOP versions of QS8 DWCONV MUL32 microkernels by Marat Dukhan · 3 years, 4 months ago
  28. 4181f94 Optimize QS8 GEMM/IGEMM microkernel selection for AVX by Marat Dukhan · 3 years, 4 months ago
  29. 2e42787 2x4c2/3x4c2 microkernels for SSE2/SSSE3/SSE4.1/AVX/XOP by Marat Dukhan · 3 years, 4 months ago
  30. 30fa853 Support flags and optional bias for fully_connected node by Ningxin Hu · 3 years, 4 months ago
  31. 496389f Make xnn_initialize thread-safe by Marat Dukhan · 3 years, 4 months ago
  32. e696c3f QS8 move loads to end of loop, 1 every 2 neon instructions. by Frank Barchard · 3 years, 4 months ago
  33. 60fc613 Polyfill _mm_loadu_si32 in MUL32 QS8 DWCONV SSE4.1/AVX microkernels by Marat Dukhan · 3 years, 4 months ago
  34. 07feec8 MUL32 versions of SSE4.1 & AVX QS8 DWCONV microkernels by Marat Dukhan · 3 years, 4 months ago
  35. fa0ab85 AVX versions of QS8 DWCONV microkernels by Marat Dukhan · 3 years, 4 months ago
  36. e9c4b96 AVX versions of QS8 VADD/VADDC microkernels by Marat Dukhan · 3 years, 4 months ago
  37. a3c1633 AVX versions of QS8 GEMM/IGEMM microkernels by Marat Dukhan · 3 years, 4 months ago
  38. b8ad46a Refactor code-generation templates for XOP microkernels by Marat Dukhan · 3 years, 4 months ago
  39. ae5082e QS8 C8 GEMM/IGEMM use load a/b last technique for Cortex A75 performance. by Frank Barchard · 3 years, 4 months ago
  40. c409471 Include XOP headers in clang-cl compatible way. Fix #1382. by Marat Dukhan · 3 years, 4 months ago
  41. d23cb6e Fully Connected operator for QS8 datatype by Marat Dukhan · 3 years, 4 months ago
  42. b3ffd58 Implement bilinear upsampling for SSE architecture by Artsiom Ablavatski · 3 years, 4 months ago
  43. 1f5099e Support quantized inference in Subgraph API with xnn_enable_qs8=true by Marat Dukhan · 3 years, 4 months ago
  44. 09c0591 Validate static tensors in Subgraph API by Marat Dukhan · 3 years, 4 months ago
  45. 43ebc05 Extend Subgraph API to support quantized tensors by Marat Dukhan · 3 years, 4 months ago
  46. ccd3a1d Validate tensor data types in Subgraph API by Marat Dukhan · 3 years, 4 months ago
  47. 6e35de5 QS8 1X8C8 IGEMM microkernel by Frank Barchard · 3 years, 4 months ago
  48. b876263 QS8 1X8C8 GEMM microkernel by Frank Barchard · 3 years, 4 months ago
  49. a0f9bdc Validate tensor types in Subgraph API by Marat Dukhan · 3 years, 4 months ago
  50. 2c525e5 MOV 16b instead of 4s for GCC compatability. Fix #1360 by Frank Barchard · 3 years, 4 months ago
  51. b0da47a QS8 C8 neon microkernel load B at end of loop and PADAP at top of loop. by Frank Barchard · 3 years, 5 months ago
  52. f5f9cec Miscellaneous tweeks to QS8 IGEMM microkernels by Frank Barchard · 3 years, 5 months ago
  53. 8e58994 2x8c8__aarch64_neon_mlal_padal GEMM microkernel load A0 last by Frank Barchard · 3 years, 5 months ago
  54. bbf5182 Enable QS8 2x8c8-aarch64-neon-mlal-padal GEMM / IGEMM microkernels by Frank Barchard · 3 years, 5 months ago
  55. cbb8e70 QS8 2x8c8-aarch64-neon-mlal-padal IGEMM microkernel by Frank Barchard · 3 years, 5 months ago
  56. 7ca54df QS8 2x8c16-aarch64-neondot-ld64 IGEMM microkernel by Frank Barchard · 3 years, 5 months ago
  57. 0ac9b7f Fix bugs in AVX512F LUT-based EXP evaluation stubs by Marat Dukhan · 3 years, 5 months ago
  58. 7825897 C8 mul microkernel labels sorted and registers documented by Frank Barchard · 3 years, 5 months ago
  59. dbb2292 Fix bug in AVX512F RR2 P5 SCALEF EXP evaluation stubs by Marat Dukhan · 3 years, 5 months ago
  60. 2f06150 xnn_qs8_gemm_minmax_ukernel_2x8c8__aarch64_neon_mlal_padal GEMM microkernel by Frank Barchard · 3 years, 5 months ago
  61. 1dc9fef QS8 2x8c8-aarch64 GEMM microkernel by Frank Barchard · 3 years, 5 months ago
  62. 4610854 Disable QS8 1x16c4-aarch64-neondot-ld64 IGEMM microkernel by Frank Barchard · 3 years, 5 months ago
  63. 3522c0a Enable QS8 4x16c4-aarch64-neondot-ld64 IGEMM microkernel by Frank Barchard · 3 years, 5 months ago
  64. 671d1b0 QS8 4x16c4-aarch64-neondot-ld64 IGEMM microkernel by Frank Barchard · 3 years, 5 months ago
  65. 24c2dec QU8 remove prototypes for microkernels that do not exist. by Frank Barchard · 3 years, 5 months ago
  66. baf46fc Tuned QS8 GEMM 2x8c16 MLAL PADAL assembly microkernel for AArch64 by Frank Barchard · 3 years, 5 months ago
  67. 5655cb7 QS8 GEMM 2x8c16 MLAL PADAL assembly microkernel for AArch64 by Frank Barchard · 3 years, 5 months ago
  68. b7941cb Round KC up for assembly microkernels. by Frank Barchard · 3 years, 5 months ago
  69. b75840f Enable QS8 IGEMM for Cortex A55 by Frank Barchard · 3 years, 5 months ago
  70. 89e12f8 QS8 IGEMM for Cortex A55 by Frank Barchard · 3 years, 5 months ago
  71. 62b4ff7 Remove 12x8 QS8 GEMM and IGEMM Neon dotproduct microkernels. by Frank Barchard · 3 years, 5 months ago
  72. fb0ab0b QS8 enable 4x8c4__neondot for ARM32 by Frank Barchard · 3 years, 5 months ago
  73. da78da1 QS8 C8 Neon microkernels with MUL and MLA versions. by Frank Barchard · 3 years, 5 months ago
  74. 618d85d QS8 Neon dot product intrinsics GEMM and IGEMM microkernels reduced remainder code. by Frank Barchard · 3 years, 5 months ago
  75. d76a37b Re-label branch targets in c4-neondot assembly QS8 GEMM microkernels. by Frank Barchard · 3 years, 5 months ago
  76. 4a4be4e QS8 1x16c4 ld32 GEMM microkernel using NEON dot product by Frank Barchard · 3 years, 5 months ago
  77. 7aa4bfd QS8 Cortex A55 GEMM microkernel bump kc to be a multiple of channels. by Frank Barchard · 3 years, 5 months ago
  78. 6d8ca7d Quantized GEMM/IGEMM microkernels bump kc to be a multiple of channels. by Frank Barchard · 3 years, 5 months ago
  79. 02121ca QS8 Neon IGEMM microkernels with 8 bit MUL using DUP by Frank Barchard · 3 years, 5 months ago
  80. 8f6a1ed QS8 LD64 C4 dot product GEMM microkernel reduced remainder handling by Frank Barchard · 3 years, 5 months ago
  81. fd1dee7 QS8 C16 GEMM microkernel source renamed from mull to mlal by Frank Barchard · 3 years, 5 months ago
  82. 77e93a2 Fix mismatch in block layout in mixed-layout Depth-To-Space operator by Marat Dukhan · 3 years, 5 months ago
  83. a5e242c QS8 LD32 GEMM microkernel for big cores with dotproduct by Frank Barchard · 3 years, 5 months ago
  84. 01c341b C8 MLA Neon GEMM/IGEMM microkernels count k down from kc. by Frank Barchard · 3 years, 5 months ago
  85. a414daa Enable Quantized C2 microkernel for Neon by Frank Barchard · 3 years, 5 months ago
  86. 36f95cf QS8 Neon IGEMM C16 microkernel with two 8 bit multiplies and vpadal to accumulate. by Frank Barchard · 3 years, 5 months ago
  87. 55d53a4 Fix bug in NHWC Convolution with depthwise kernels by Marat Dukhan · 3 years, 5 months ago
  88. 71c4d1a QS8 Neon GEMM C16 microkernel with two 8 bit multiplies and vpadal to accumulate. by Frank Barchard · 3 years, 5 months ago
  89. 6d138db Remove scalar C4 QS8 and QU8 gemm microkernels. by Frank Barchard · 3 years, 6 months ago
  90. a0fe11d QS8 C8 Neon remove remainder handling code and rewind the A pointers by kc by Frank Barchard · 3 years, 6 months ago
  91. 32389c6 QS8 e2e benchmark for C2 neon microkernels by Frank Barchard · 3 years, 6 months ago
  92. 6fa8078 QS8 C2 Neon igemm by Frank Barchard · 3 years, 6 months ago
  93. d79391d QS8 C8 Neon igemm by Frank Barchard · 3 years, 6 months ago
  94. aaafdc7 QS8 scalar gemm remove bias variables. by Frank Barchard · 3 years, 6 months ago
  95. fe14b85 Add space after casting by Frank Barchard · 3 years, 6 months ago
  96. 10f9f05 Remove 0 from ranges where not needed by Frank Barchard · 3 years, 6 months ago
  97. 4baa2ac Process 32 pixels at a time in ARM64 SpMM microkernels by Marat Dukhan · 3 years, 6 months ago
  98. c8532ae Unroll KC loop to do MULL and then MLAL to 16 bit before lengthening to 32 bit. by Frank Barchard · 3 years, 6 months ago
  99. 2d6bcbb Reorder a few gemm1 initializations to match end to end order of gemm, igemm, gemm1, igemm1 by Jared Duke · 3 years, 6 months ago
  100. 9b7562b Reorder a few gemm1 initializations to match end to end order of gemm, igemm, gemm1, igemm1 by Frank Barchard · 3 years, 6 months ago