Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / bef9a4d3efcede42496e6fe4900c71678fcaee43
  1. bef9a4d Do not set ukernel type in operators with a single type of kernel by Marat Dukhan · 3 years, 7 months ago
  2. 9cef5ea dwconv wasm remove shuffle wrappers. by Frank Barchard · 3 years, 7 months ago
  3. db5c32d WasmSIMD dwconv2d generate x86 optimized version. by Frank Barchard · 3 years, 7 months ago
  4. 498cb50 Initialize select SpMM microkernel for x86 or ARM based on cpu detect, by Frank Barchard · 3 years, 7 months ago
  5. 1a95305 Replace DWConv2D PSIMD with WAsm SIMD. by Frank Barchard · 3 years, 8 months ago
  6. e8bfcc8 Add output_stride argument in SpMM microkernels by Marat Dukhan · 3 years, 8 months ago
  7. e278a55 Pre-scale batch_size by element size in SpMM microkernels by Marat Dukhan · 3 years, 8 months ago
  8. 1717075 Check output_channels argument in SpMM microkernels by Marat Dukhan · 3 years, 8 months ago
  9. ee2df51 Use size_t in SpMM arguments by Marat Dukhan · 3 years, 8 months ago
  10. bb781b6 Refactor Depth-To-Space operator by Marat Dukhan · 3 years, 8 months ago
  11. b4ac61d Make DepthToSpace X32 operator consistent with other X32 operators by Marat Dukhan · 3 years, 8 months ago
  12. 13b68f2 Rename CHW2HWC to NCHW2NCHW in DepthToSpace operator by Marat Dukhan · 3 years, 8 months ago
  13. b48802e Remove redundant parameter checks in DepthToSpace operator by Marat Dukhan · 3 years, 8 months ago
  14. 2da0de8 SpMM move prefetch to fetch next input instead of after the current input. by Frank Barchard · 3 years, 8 months ago
  15. f673b2c SpMM microkernels advance output by byte stride by Frank Barchard · 3 years, 8 months ago
  16. 0f1dc18 Add operator level tests for DEPTH_TO_SPACE op by Artsiom Ablavatski · 3 years, 8 months ago
  17. a19cff3 Neon prefetch for MR >= 16 allowing 32xNR to also prefetch by Frank Barchard · 3 years, 8 months ago
  18. bbe8506 Introduce DEPTH_TO_SPACE operator and enable it for graph rewriting by Artsiom Ablavatski · 3 years, 8 months ago
  19. e784186 Basic scalar implementation of CHW-to-HWC Depth-to-Space. by Yury Kartynnik · 3 years, 8 months ago
  20. c2c0d16 SpMM pipelined benchmark. by Frank Barchard · 3 years, 8 months ago
  21. 8ef44cd Pipelined Web Assembly Sparse Matrix Multiply by Frank Barchard · 3 years, 8 months ago
  22. beca652 Rename unroll to x for SpMM microkernels with unrolled loop by Frank Barchard · 3 years, 8 months ago
  23. ccca214 SSE variant of 5x5s2 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 8 months ago
  24. 4fd38b2 Enable 32x1 SpMM microkernels for WAsm and SSE by Frank Barchard · 3 years, 8 months ago
  25. d050389 SSE variants of 5x5 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 8 months ago
  26. 30d4b25 Auto-generate 5x5s2 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 8 months ago
  27. 29c0c33 Auto-generate 5x5s2p2 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 8 months ago
  28. e6beeba Add Bilinear Upsampling 2D to the supported by sparse inference ops by Artsiom Ablavatski · 3 years, 8 months ago
  29. 9791810 Add operator implementation and tests for IBILINEAR CHW microkernel by Artsiom Ablavatski · 3 years, 8 months ago
  30. b392f8e VDIV unrolled for WebAssembly by Frank Barchard · 3 years, 8 months ago
  31. 846c0c6 Add 32x1 32x2 32x4 SPMM microkernels and remove 4x1 4x2 4x4 for WASMSIMD, Neon and SSE by Frank Barchard · 3 years, 8 months ago
  32. 35db7d0 Re-sort filenames in build files alphanumerically. by Frank Barchard · 3 years, 8 months ago
  33. 149f0ea Auto-generate NEON 5x5p2 DWCONV micro-kernels by Marat Dukhan · 3 years, 8 months ago
  34. c4efb00 Auto-generate scalar 5x5p2 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 8 months ago
  35. cf5b3c3 Auto-generate scalar versions of DWCONV2D CHW 3x3s2p1 micro-kernels by Marat Dukhan · 3 years, 8 months ago
  36. 82f0c32 Auto-generate NEON/NEONFMA versions of DWCONV2D CHW 3x3s2p1 micro-kernels by Marat Dukhan · 3 years, 8 months ago
  37. 0ff9718 Auto-generate SSE versions of DWCONV2D CHW 3x3s2p1 micro-kernels by Marat Dukhan · 3 years, 8 months ago
  38. b16785a Fix CMake build by Marat Dukhan · 3 years, 8 months ago
  39. 91249d2 Auto-generate scalar versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 8 months ago
  40. c581e48 NEON versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 8 months ago
  41. 1268a24 Auto-generate AArch64 NEONFMA versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 8 months ago
  42. 98f2eeb SSSE3 versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 8 months ago
  43. 470078a Auto-generate SSE versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 8 months ago
  44. 965272b Add WebAssembly SIMD IBILINEAR microkernels for CHW layout by XNNPACK Team · 3 years, 8 months ago
  45. bf715f9 Rename DWCONV CHW microkernels to DWCONV2D CHW by Marat Dukhan · 3 years, 8 months ago
  46. 3155c47 Remove right corners from indirection tables in IBILINEAR CHW microkernel interface by XNNPACK Team · 3 years, 8 months ago
  47. cb2b667 Roll back the decision to split the packed weights for the CHW IBILINEAR microkernel interface by XNNPACK Team · 3 years, 8 months ago
  48. dc6c77f Generate DWCONV CHW microkernel tests from a YAML specification by Marat Dukhan · 3 years, 8 months ago
  49. 0dde1af Split packed weights into horizontal and vertical in IBILINEAR CHW microkernel interface by XNNPACK Team · 3 years, 8 months ago
  50. 6be46b2 Add input increment parameter in IBILINEAR CHW microkernels by XNNPACK Team · 3 years, 8 months ago
  51. f703d4f Merge pull request #1099 from peterjc123:patch-1 by XNNPACK Team · 3 years, 8 months ago
  52. ae2d0f6 Fix build for NDK < r21 with ARM-v8 by peterjc123 · 3 years, 8 months ago
  53. 04336c1 Sort names in build files. by Frank Barchard · 3 years, 8 months ago
  54. fea2680 WAsm SpMM microkernel assign vzero vector once by Frank Barchard · 3 years, 8 months ago
  55. b9deb96 Polyfill missing intrinsics for legacy compilers by Marat Dukhan · 3 years, 8 months ago
  56. e5b5dea Polyfill _kshiftli_mask64 for legacy compilers by Marat Dukhan · 3 years, 8 months ago
  57. b465832 Merge pull request #1093 from peterjc123:patch-1 by XNNPACK Team · 3 years, 8 months ago
  58. 60a3b19 Fix typo by peterjc123 · 3 years, 8 months ago
  59. c371be1 Fixes build for CMake < 3.8 by peterjc123 · 3 years, 8 months ago
  60. 6f469a5 Minor refactoring in DWCONV CHW microkernels by Marat Dukhan · 3 years, 8 months ago
  61. c451e8a WAsm SpMM microkernels unrolled by 2 and 4. by Frank Barchard · 3 years, 8 months ago
  62. 1c6cad9 Suffix DWCONV CHW microkernels with block size by Marat Dukhan · 3 years, 8 months ago
  63. 42c32ce Fix compilation of f32_ibilinear_chw_test for WAsm SIMD by Marat Dukhan · 3 years, 8 months ago
  64. 9f426b4 Fix CMake build by Marat Dukhan · 3 years, 8 months ago
  65. faf332d Optimize PSIMD 5x5 DWCONV CHW microkernels by Marat Dukhan · 3 years, 8 months ago
  66. 7515777 Scale input width in DWCONV CHW interface by sizeof(float) by Marat Dukhan · 3 years, 8 months ago
  67. 7ed0e3c Refactor and simplify DWCONV CHW microkernels by Marat Dukhan · 3 years, 8 months ago
  68. a982bb7 Rollback the renaming of indirection map since we can reuse the code for CHW and HWC layouts by XNNPACK Team · 3 years, 8 months ago
  69. c808c97 Simplify output pointer updates in DWCONV CHW microkernels by Marat Dukhan · 3 years, 8 months ago
  70. a690c09 Minor refactoring of DWCONV CHW microkernels by Marat Dukhan · 3 years, 8 months ago
  71. 04d91c8 Remove redundant m variable in DWCONV CHW microkernels by Marat Dukhan · 3 years, 8 months ago
  72. bc967c7 Simplify pointer arithmetics in DWCONV CHW microkernels by Marat Dukhan · 3 years, 8 months ago
  73. a5cb677 Add "nhwc" into the naming of indirection map function and tests by XNNPACK Team · 3 years, 8 months ago
  74. ae7e8b2 Remove remnants of SpCHW layout in DWCONV-CHW microkernels by Marat Dukhan · 3 years, 8 months ago
  75. 2143267 IBILINEAR CHW microkernels by XNNPACK Team · 3 years, 8 months ago
  76. 9e05340 Replace PSIMD SpMM microkernels with WAsm SIMD. by Frank Barchard · 3 years, 8 months ago
  77. d923d7f Rename parameters in prototypes to reflect their meanings in microkernel implementations. by XNNPACK Team · 3 years, 8 months ago
  78. 39ab16f Evaluation stub for AVX Sigmoid with 1 Newton-Raphson iteration by Marat Dukhan · 3 years, 9 months ago
  79. 45aec16 Fix bug in QS8 Global Average Pooling by Marat Dukhan · 3 years, 9 months ago
  80. ac5f160 SSE2 Sigmoid evaluation stubs using Newton-Raphson reciprocal by Marat Dukhan · 3 years, 9 months ago
  81. 36173d2 Evaluation stubs for gather-based AVX2/AVX512 Sigmoid by Marat Dukhan · 3 years, 9 months ago
  82. c79427c Avoid batch-replication of indirection buffer in DW Conv and Avg Pooling by Marat Dukhan · 3 years, 9 months ago
  83. dc2b29c AVX float32 sigmoid ukernels. by T.J. Alumbaugh · 3 years, 9 months ago
  84. 31677ad Enable Cortex-A55 QS8 GEMM microkernel on HMP systems by Marat Dukhan · 3 years, 9 months ago
  85. 146e999 Replace QS8 4x8 with 2x8 neon microkernel. Improves performance for aarch32. by Frank Barchard · 3 years, 9 months ago
  86. 1e8590e Enable QS8 A55 GEMM microkernel by Frank Barchard · 3 years, 9 months ago
  87. f2742c4 Cortex A55r1 QS8 GEMM microkernel by Frank Barchard · 3 years, 9 months ago
  88. 31328cb Add RUY benchmark to qs8_gemm_bench by Frank Barchard · 3 years, 9 months ago
  89. 0797eb1 Rename QS8 assembly GEMM kernels to ld64 by Frank Barchard · 3 years, 9 months ago
  90. a463285 4x16 QS8 GEMM use 4 less registers, avoiding push/pop. by Frank Barchard · 3 years, 9 months ago
  91. ab8c4c8 Add basic unit tests for graph rewriting procedure by XNNPACK Team · 3 years, 9 months ago
  92. 46aadda Enable 1x16 QS8 assembly GEMM for Neon dotproduct by Frank Barchard · 3 years, 9 months ago
  93. 59df88b 4x16 QS8 GEMM defer params by Frank Barchard · 3 years, 9 months ago
  94. f1fd89e 1x16 QS8 GEMM AARCH64 assembly microkernel using dot product. by Frank Barchard · 3 years, 9 months ago
  95. a5237a5 Rename 4x16 GEMM dot product microkernel file name to allow for future variations. by Frank Barchard · 3 years, 9 months ago
  96. bc0c729 Enable GEMM 4x16 QS8 using dot product microkernels. by Frank Barchard · 3 years, 9 months ago
  97. d2750b0 Limit testing range for FP16 global-average-pooling to 1.0e-3f to 1 to avoid by Frank Barchard · 3 years, 9 months ago
  98. 31bb45b 4x16 QS8 GEMM AARCH64 assembly microkernel using dot product. by Frank Barchard · 3 years, 9 months ago
  99. a117ce7 Fix graph rewriting procedure for graph without NCHW2NHWC compatible nodes/ops by XNNPACK Team · 3 years, 9 months ago
  100. 3b26206 Renumber labels in assembly sequentially by Frank Barchard · 3 years, 9 months ago