1. 2456789 Update build_defs.bzl to use linux_armv7a by Marat Dukhan · 4 years, 4 months ago
  2. a720e93 Recognize "armv7a" cpu as Linux/ARM in Bazel build by Marat Dukhan · 4 years, 4 months ago
  3. 9c8e4ca Use the right header in HSWISH microkernels by Marat Dukhan · 4 years, 4 months ago
  4. f870d04 Use exact comparison in PRELU microkernel tests by Marat Dukhan · 4 years, 4 months ago
  5. 0a1970e PSIMD F32-CONV-HWC2CHW kernel by Erich Elsen · 4 years, 4 months ago
  6. 8ada3b1 Clarify XNNPACK/QNNPACK difference in README by Marat Dukhan · 4 years, 4 months ago
  7. 5fab409 Six new unary elementwise operators in Subgraph API by Marat Dukhan · 4 years, 4 months ago
  8. bc69ed6 Fix ARMv7/iOS build by Marat Dukhan · 4 years, 4 months ago
  9. 6e80fdc Add 16x1 SSE f32-SpMM kernels, which is faster than the existing 8x1 kernel. by Erich Elsen · 4 years, 4 months ago
  10. 64e5251 Rounding operators by Marat Dukhan · 4 years, 4 months ago
  11. 290055c Requantization implementation in WAsm SIMD intrinsics by Marat Dukhan · 4 years, 4 months ago
  12. eecf8fd RND microkernels and tests by Marat Dukhan · 4 years, 4 months ago
  13. 34ccfba Fix incompatibilities with gcc by Marat Dukhan · 4 years, 4 months ago
  14. 909564c Update comment for x18 register by Frank Barchard · 4 years, 4 months ago
  15. 5b2e07a Add new x86 sse chw2hwc conv kernel to init.c by Erich Elsen · 4 years, 4 months ago
  16. 4e6f958 Update cpuinfo dependency by Marat Dukhan · 4 years, 4 months ago
  17. 361e44a Re-generate HWC CONV microkernels and SIGMOID tests by Frank Barchard · 4 years, 4 months ago
  18. e8466f4 Simplify remainder processing by Frank Barchard · 4 years, 4 months ago
  19. b123340 Add SSE versions of conv-hwc2chw by Erich Elsen · 4 years, 4 months ago
  20. e080a31 FP16 - Simplify remainder processing in Vector Binary Elementwise microkernels by Frank Barchard · 4 years, 4 months ago
  21. 0219fd5 Simplify remainder processing in Vector Binary Elementwise microkernels by Marat Dukhan · 4 years, 4 months ago
  22. 5020b96 Abs, Negate, and Square NC operators by Marat Dukhan · 4 years, 4 months ago
  23. 1eb743a Remove remnants of Add NC operator by Marat Dukhan · 4 years, 4 months ago
  24. d310214 Fix bugs in ROUND evaluation tests by Marat Dukhan · 4 years, 4 months ago
  25. 2b9efd8 Vector Unary (ABS/NEG/SQR) micro-kernels by Marat Dukhan · 4 years, 4 months ago
  26. 9d3a459 Divide/Subtract/Minimum2/Maximum2/SquaredDifference in Subgraph API by Marat Dukhan · 4 years, 4 months ago
  27. f739926 Squared Difference operator by Marat Dukhan · 4 years, 4 months ago
  28. 16b52e3 Remove Channel Pad NC operator by Marat Dukhan · 4 years, 4 months ago
  29. a5adc1f Remove WAsm versions of SQRDIFF microkernels by Marat Dukhan · 4 years, 4 months ago
  30. d46e12a Fix CMake build by Marat Dukhan · 4 years, 4 months ago
  31. 13bafb0 SQRDIFF (Squared Difference) microkernels by Marat Dukhan · 4 years, 4 months ago
  32. 9c1a735 Include FP16 header for conversions by Frank Barchard · 4 years, 4 months ago
  33. 5a599a6 FP16 DWCONV microkernel by Frank Barchard · 4 years, 4 months ago
  34. 8fb51b6 Remove Add NC operator by Marat Dukhan · 4 years, 4 months ago
  35. b2164a3 Re-generate end-to-end models by Marat Dukhan · 4 years, 4 months ago
  36. 4e21b27 Copy NC operator by Marat Dukhan · 4 years, 4 months ago
  37. c3065f5 Unify implementation of unary elementwise operators (Clamp, HardSwish, Sigmoid) by Marat Dukhan · 4 years, 4 months ago
  38. 0bb49a7 FP16 GAVGPOOL microkernel by Frank Barchard · 4 years, 4 months ago
  39. 5a409d8 Generalize Clamp NC setup implementation across datatypes by Marat Dukhan · 4 years, 4 months ago
  40. 210e35d Fix Release build with CMake by Marat Dukhan · 4 years, 4 months ago
  41. 3b59de2 Refactor logging messages in operators and subgraph nodes by Marat Dukhan · 4 years, 4 months ago
  42. febfe59 Cast void * parameters to fp16__ pointers by Frank Barchard · 4 years, 4 months ago
  43. 95e8b7a Split Subgraph API functions into separate files by Marat Dukhan · 4 years, 4 months ago
  44. d960714 FP16 IGEMM benchmark fix log2(sizeof uint16) = 1 by Frank Barchard · 4 years, 4 months ago
  45. 2a1049c FP16 VMULCADDC microkernel by Frank Barchard · 4 years, 4 months ago
  46. 9f3a843 Replace comment Prepare output parameters with Prepare parameters. by Frank Barchard · 4 years, 4 months ago
  47. 5d67652 Update cpuinfo patch by Marat Dukhan · 4 years, 4 months ago
  48. 2b95ea1 f32_dwconv benchmark add missing neon microkernels by Frank Barchard · 4 years, 4 months ago
  49. ea575d9 Improve ROUNDD/ROUNDU evaluation stubs by Marat Dukhan · 4 years, 4 months ago
  50. 40f50e1 f16 benchmarks - add cpuinfo check for FP16 by Frank Barchard · 4 years, 4 months ago
  51. 81c6260 Match WAsm SIMD configuration by -msimd128 compiler flag by Marat Dukhan · 4 years, 4 months ago
  52. b2217dd Disable tsan for micro-kernels which read out-of-bounds by Marat Dukhan · 4 years, 4 months ago
  53. e207b7b Add missing f32_igemm_minmax_test target by Marat Dukhan · 4 years, 4 months ago
  54. 1e5f802 Add link_static=True to clog Bazel target by Marat Dukhan · 4 years, 4 months ago
  55. f3d1205 Fuse Constant Pad into [Depthwise] Convolution 2D by Marat Dukhan · 4 years, 4 months ago
  56. 33fcf78 Add test_mode targets with stricter checks when running unit tests by Marat Dukhan · 4 years, 4 months ago
  57. 1f19872 Node fusion in Subgraph API by Marat Dukhan · 4 years, 4 months ago
  58. a8c34aa Fix cpuinfo patch command in CMake build by Marat Dukhan · 4 years, 4 months ago
  59. 0493fbd Update Raspberry Pi performance in README by Marat Dukhan · 4 years, 4 months ago
  60. fdaf9ae Add missing CONV-HWC microkernels in CMake config by Marat Dukhan · 4 years, 4 months ago
  61. 0ea027e Fix CMake build after refactoring X32 PAD micro-kernels by Marat Dukhan · 4 years, 4 months ago
  62. 467f636 Fused [I]GEMM+RELU micro-kernels by Marat Dukhan · 4 years, 4 months ago
  63. 63523d4 Refactor X32 PAD micro-kernels by Marat Dukhan · 4 years, 4 months ago
  64. f5c4625 Remove redundant TF legacy + align corners mode in Resize Bilinear by Marat Dukhan · 4 years, 4 months ago
  65. 065b11e Rename Pad operator to Constant Pad in Operator API by Marat Dukhan · 4 years, 4 months ago
  66. 54cf510 Minor refactoring in internal subgraph objects by Marat Dukhan · 4 years, 4 months ago
  67. ab2946c Support Static Constant Pad operator in Subgraph API by Marat Dukhan · 4 years, 4 months ago
  68. 6e15532 Fix MSVC build of the Pad operator by Marat Dukhan · 4 years, 4 months ago
  69. 2b65daa Update cpuinfo patch by Marat Dukhan · 4 years, 4 months ago
  70. 4662b19 N-dimensional Pad operator by Marat Dukhan · 4 years, 4 months ago
  71. 6c74cd1 Test generator for gavgpool by Frank Barchard · 4 years, 4 months ago
  72. dcc8321 Fix stride in F32_GAVGPOOL_MINMAX_7P7X__SSE2_C4, channels_eq_4_2pass_subtile_with_input_stride by Frank Barchard · 4 years, 4 months ago
  73. 3bb3bfc X32 FILL micro-kernels by Marat Dukhan · 4 years, 4 months ago
  74. eb8897b Update psimd dependency by Marat Dukhan · 4 years, 4 months ago
  75. 56b10cd CONV-HWC NEONFMA micro-kernels with width tile 1 by Marat Dukhan · 4 years, 4 months ago
  76. d18cec3 Add more missing "assembly: true" specifications by Marat Dukhan · 4 years, 4 months ago
  77. ce7a3f8 Auto-generate NEON CONV micro-kernels by Marat Dukhan · 4 years, 4 months ago
  78. 32f9381 4x4 LD64 GEMM microkernel in AArch32+VFP assembly by Marat Dukhan · 4 years, 4 months ago
  79. 0085ae3 Document Windows support in README by Marat Dukhan · 4 years, 4 months ago
  80. 569583e Update cpuinfo dependency by Marat Dukhan · 4 years, 4 months ago
  81. d536072 DWCONV add input_offset and zero parameters by Frank Barchard · 4 years, 4 months ago
  82. 3b98f6b 4x4 LD64 GEMM+MINMAX microkernel in AArch32+VFP assembly by Marat Dukhan · 4 years, 4 months ago
  83. f606806 Add missing "assembly: true" specifications by Marat Dukhan · 4 years, 4 months ago
  84. 20550ef Optimize output row variables in CONV-HWC microkernels by Marat Dukhan · 4 years, 4 months ago
  85. 3217d31 Simplify remainder processing in 3x3s2 CONV NEONFMA microkernels by Marat Dukhan · 4 years, 4 months ago
  86. b64f617 Fix f32-gavgpool-cw-test target in CMake by Marat Dukhan · 4 years, 4 months ago
  87. ae89be6 Refactor common macros by Marat Dukhan · 4 years, 4 months ago
  88. b112088 Use MinNum/MaxNum instructions where available by Marat Dukhan · 4 years, 4 months ago
  89. 1f29b80 Refactor CHW micro-kernels by Marat Dukhan · 4 years, 4 months ago
  90. 7e4ca40 3x3s2c3 CONV NEONFMA microkernel with 0+1 padding by Marat Dukhan · 4 years, 4 months ago
  91. b9a9958 Simplify q8 dwconv to remove unrolled aarch64 code by Frank Barchard · 4 years, 4 months ago
  92. 8bd4cba Fix ARM/gcc build or ROUNDZ evaluation stubs by Marat Dukhan · 4 years, 4 months ago
  93. cc55f81 Fix CMake build of rounding-bench by Marat Dukhan · 4 years, 4 months ago
  94. ffbf96a Benchmark for ROUND evaluation stubs by Marat Dukhan · 4 years, 4 months ago
  95. b389f35 Rename pooling_2d.input_padding_* into pooling_2d.padding_* by Marat Dukhan · 4 years, 4 months ago
  96. d9a7e85 Add reference to "Efficient Memory Management for Deep Neural Net Inference" paper by Marat Dukhan · 4 years, 4 months ago
  97. 6ddfc60 Implement "Greedy by size planner" memory optimization by Chao Mei · 4 years, 4 months ago
  98. c9852ba ROUNDU and ROUNDD evaluation stubs by Marat Dukhan · 4 years, 4 months ago
  99. 737a3a1 IGEMM 4x8 a53/a55 - Replace STP x19, x19 with STR by Frank Barchard · 4 years, 5 months ago
  100. 942b576 Increase size of explicit zero vector in NCHW Convolution by Marat Dukhan · 4 years, 5 months ago