1. 348c377 QU8 GEMM/IGEMM WAsm SIMD microkernels with SR=4 by Marat Dukhan · 2 years, 5 months ago
  2. e1ff738 Update assembly register usage comments. by Frank Barchard · 2 years, 5 months ago
  3. 901845c QU8 4x8 NEON MLA Lane microkernel AArch32 assembly language by Frank Barchard · 2 years, 5 months ago
  4. 48d74c3 Replicate QC8/QS8/QU8 CONV WAsm SIMD parameters to 64 bit rather than 128 bit by Marat Dukhan · 2 years, 5 months ago
  5. d5a5333 Additional tile sizes for QU8 neon lane microkernel. by Frank Barchard · 2 years, 5 months ago
  6. 7c1115f Reoptimize microkernel selection for WAsm 1.0 by Marat Dukhan · 2 years, 6 months ago
  7. 272d4d9 FP32 IMAGIC variants of scalar QC8/QS8/QU8 GEMM/IGEMM/DWCONV microkernels by Marat Dukhan · 2 years, 6 months ago
  8. 2ac722e Refactor requantization in scalar QS8/QC8/QU8 microkernels by Marat Dukhan · 2 years, 6 months ago
  9. d541fc0 Annotate remaining microkernels with Out-of-Bounds reads with XNN_OOB_READS by Marat Dukhan · 2 years, 6 months ago
  10. 914f57b Aarch64 4x8 lane ld64 GEMM/IGEMM microkernels. by Frank Barchard · 2 years, 6 months ago
  11. 7c0303e Remove the last remnant of GEMMLOWP requantization in QU8 microkernels by Marat Dukhan · 2 years, 6 months ago
  12. 59d6515 Enable FP32 requant variant for QU8 [1,4]x8 Neon MLAL [I]GEMM kernels by Digant Desai · 2 years, 7 months ago
  13. 9982ed3 Enable FP32 requant variant for QU8 NEON dotprod [I]GEMM kernels by Digant Desai · 2 years, 7 months ago
  14. 2e2d179 Enable FP32 requant variant for QU8 4x16c4 NEON asm dotprod [I]GEMM kernels by Digant Desai · 2 years, 7 months ago
  15. 10f9f62 Enable FP32 requant variant for QU8 4x16c4 NEON asm dotprod [I]GEMM kernels for CA55r1 by Digant Desai · 2 years, 7 months ago
  16. 03efa0f Reoptimize FP32 requantization in NEON QS8/QC8/QU8 GEMM/IGEMM/DWCONV by Marat Dukhan · 2 years, 6 months ago
  17. 5a31dc6 Optimize FP32 requantization in NEON QS8/QC8/QU8 GEMM/IGEMM/DWCONV by Marat Dukhan · 2 years, 6 months ago
  18. 8978ac2 Support requantization scale greater than 1 in RNDNU NEON microkernels by Marat Dukhan · 2 years, 6 months ago
  19. 13c9f8d Support requantization scale over 1 in SSE/AVX GEMM/IGEMM/DWCONV by Marat Dukhan · 2 years, 7 months ago
  20. 8999190 Remove GEMMLOWP requantization from QS8 GEMM/IGEMM templates by Marat Dukhan · 2 years, 7 months ago
  21. 411c18d Optimize FP32 requantization in WAsm SIMD QS8/QC8/QU8 GEMM/IGEMM/DWCONV by Marat Dukhan · 2 years, 7 months ago
  22. 5f7cf55 Avoid using gcc-specific intrinsics in NEON microkernels by Marat Dukhan · 2 years, 7 months ago
  23. 9cdc10d QU8 4x16 lane AArch64 NEON GEMM/IGEMM ld64 microkernel by Frank Barchard · 2 years, 7 months ago
  24. 0bf8afa Leverage f32x4.pmin and f32x4.pmax WAsm SIMD instructions by Marat Dukhan · 2 years, 9 months ago
  25. cdf59a5 Add QU8 NR=32 microkernels by Frank Barchard · 2 years, 9 months ago
  26. d460d0b Neon IGEMM do remainder with reversed MR for shifts by Frank Barchard · 2 years, 9 months ago
  27. ec5c129 Template bug fix in stores for remainder of 8. by Frank Barchard · 2 years, 9 months ago
  28. 2fee611 Fix compilation warnings in QU8 GEMM/IGEMM NEONDOT microkernels by Marat Dukhan · 2 years, 10 months ago
  29. 1ce78ab Leverage Load-Zero WAsm SIMD instructions in Chrome M88 microkernels by Marat Dukhan · 2 years, 10 months ago
  30. df8e604 4x8 QU8 Neon Dotproduct microkernel rename from ld64 to ld128 by Frank Barchard · 2 years, 10 months ago
  31. bd5b027 4x8 QU8 microkernel use 16 byte UDOT to save 4 UDOT by Frank Barchard · 2 years, 10 months ago
  32. b7a7c30 NEON GEMM/IGEMM microkernels change store/dup to 2 of each by Frank Barchard · 2 years, 10 months ago
  33. 132774e QU8 microkernels change stores to non-lane STR by Frank Barchard · 2 years, 10 months ago
  34. 29833fd Change stores to non-lane STR by Frank Barchard · 2 years, 10 months ago
  35. 1c70764 4x16c4 cortex_a55 microkernel tuning by Frank Barchard · 2 years, 10 months ago
  36. e7e001f Fix bug in QC8/QS8/QU8 IGEMM DOT16x2 LD128 WAsm SIMD microkernels by Marat Dukhan · 2 years, 10 months ago
  37. a49e41f QU8 4x16C4 NEON Dot Product GEMM/IGEMM microkernels for Cortex A55r1 by Frank Barchard · 2 years, 10 months ago
  38. 4810905 Leverage v128.const WAsm SIMD instruction by Marat Dukhan · 2 years, 10 months ago
  39. 8dc106e QC8/QS8/QU8 GEMM/IGEMM WAsm SIMD microkernels using i32x4.dot_i16x8_s instruction by Marat Dukhan · 2 years, 10 months ago
  40. 6b30b73 Remainder branch move before label. by Frank Barchard · 2 years, 10 months ago
  41. fec7363 QU8 C4 4x8 rename registers to avoid 3 push/pops. by Frank Barchard · 2 years, 10 months ago
  42. ca4c68e QU8 C4 NEON Dot Product GEMM/IGEMM microkernels for Cortex A55r1 by Frank Barchard · 2 years, 10 months ago
  43. 56f157c Relabel branches for quantized assembly ARM microkernels by Frank Barchard · 2 years, 10 months ago
  44. 0c76422 QU8 NEON Assembly remove channel wise by Frank Barchard · 2 years, 10 months ago
  45. 4066898 QU8 4x16 C4 NEON Assembly Dot Product GEMM/IGEMM microkernels by Frank Barchard · 2 years, 10 months ago
  46. a38bf33 QU8 4x8c4 rewind params with SUB by Frank Barchard · 2 years, 10 months ago
  47. b48f367 QU8 4x8 C4 NEON reload params during subtract by Frank Barchard · 2 years, 10 months ago
  48. 073185e QU8 4x8 C4 NEON Assembly Dot Product use partial sums on zero point by Frank Barchard · 2 years, 10 months ago
  49. 0049e89 QU8 C4 NEON Assembly Dot Product GEMM/IGEMM microkernels by Frank Barchard · 2 years, 10 months ago
  50. 6fe565e QU8 neondot use C2 partial sum for zero point accumulators. by Frank Barchard · 2 years, 10 months ago
  51. 3f2074f QU8 neondot use uint32x2 for zero point and accumulators by Frank Barchard · 2 years, 10 months ago
  52. 7a8dd87 Work around generating v128.storeXX_lane for quantized WAsm SIMD microkernels by Marat Dukhan · 2 years, 10 months ago
  53. a74310a Remove UDOT by zero point along the N axis by Frank Barchard · 2 years, 10 months ago
  54. e033126 Generate more tile sizes for QU8 gemm/igemm by Frank Barchard · 2 years, 10 months ago
  55. 88e839c QU8 C4 NEON Dot Product GEMM/IGEMM microkernels by Frank Barchard · 2 years, 10 months ago
  56. 07706f6 Replace generic shuffle with narrow instructions in WAsm SIMD QS8/QU8/QC8 microkernels by Marat Dukhan · 2 years, 10 months ago
  57. dfc2db0 Add prefix to QC8/QS8/QU8 WAsm SIMD GEMM/IGEMM microkernels by Marat Dukhan · 2 years, 10 months ago
  58. ebb6207 QU8 4x16 IGEMM remove push for X21 register by Frank Barchard · 2 years, 11 months ago
  59. 2c6d196 Q8 4x16 and 1x16 Neon GEMM/IGEMM quantize using V0-V3 by Frank Barchard · 2 years, 11 months ago
  60. fbe0c6f Q8 4x16 Neon IGEMM quantize using V0-V3 by Frank Barchard · 2 years, 11 months ago
  61. fb3a94f QU8 4x16 Neon assembly microkernel for Cortex A75 by Frank Barchard · 2 years, 11 months ago
  62. 86a1618 QU8 Neon params replace pad with duplicated zero_point by Frank Barchard · 2 years, 11 months ago
  63. 59ed1da QU8 4x16 Neon assembly microkernel by Frank Barchard · 2 years, 11 months ago
  64. 173661d QU8 GEMM/IGEMM NEON microkernels with RNDNU requantization by Marat Dukhan · 2 years, 11 months ago
  65. efa123d Update Neon code with generators for added comment by Frank Barchard · 2 years, 11 months ago
  66. 89cd59b Remove legacy QU8 GEMM/IGEMM/DWCONV microkernels by Marat Dukhan · 3 years ago
  67. 927d474 Scalar implementations of QU8 GEMM/IGEMM microkernels by Marat Dukhan · 3 years ago
  68. 43bee05 WAsm SIMD implementation of QU8 GEMM/IGEMM microkernels by Marat Dukhan · 3 years ago
  69. 69c8a29 NEON-MLAL implementations of QU8 GEMM/IGEMM microkernels by Marat Dukhan · 3 years ago
  70. 3cf2e22 QU8 GEMM/IGEMM microkernels for AVX512 by Marat Dukhan · 3 years ago
  71. 902ef7f QU8 GEMM/IGEMM AVX2 microkernels with FP32 requantization by Marat Dukhan · 3 years ago
  72. ef47f8d QU8 GEMM/IGEMM microkernels for SSE/AVX/XOP with FP32 requantization by Marat Dukhan · 3 years ago
  73. cdbe9a3 Code-generate QU8 GEMM and IGEMM microkernels for SSE2/SSSE3/SSE4.1 by Marat Dukhan · 3 years ago
  74. c698c11 Refactor xnn_qu8_conv_minmax_params by Marat Dukhan · 3 years ago
  75. c2e8f66 Unify naming of QU8 GEMM/IGEMM/DWCONV microkernels with QS8/QC8 by Marat Dukhan · 3 years ago
  76. f86ee8b Refactor requantization helper functions by Marat Dukhan · 3 years, 1 month ago
  77. e3d17bf Rename microkernel-related types and structures by Marat Dukhan · 3 years, 1 month ago
  78. 6d8ca7d Quantized GEMM/IGEMM microkernels bump kc to be a multiple of channels. by Frank Barchard · 3 years, 4 months ago
  79. 08b7a97 Rename Q8 microkernels and operators to QU8 by Marat Dukhan · 4 years ago