Gitiles
Code Review Sign In
review.mlplatform.org / ml / ComputeLibrary / a668f9f8a4eab405df0fe8dd58e7d9425bcf9640 / src / core / NEON / kernels / arm_gemm
  1. a668f9f Add s8f32 kernels and dynamic QuantizationInfo by Jonathan Deakin · 5 months ago
  2. f1f1f87 Add in place summation to CPU GEMM kernels by Radu Salavat · 4 months ago
  3. 905786e Added new NEON fixed format fast math mode hybrid kernel with maximum height of 6 for accumulation and updated heuristics by Milos Puzovic · 3 months ago
  4. 36a75da [ONCPUML-1451] Add matmul kernel to enable bf16 to bf16 operations via PyTorch® autocast() function by Renato Arantes · 5 months ago
  5. 3e4b193 Fix quant. gemv kernel driver by adding set_quantized_bias() by Gunes Bayir · 3 months ago
  6. 5a67733 arm_gemm: Fix bias handling for sme2 FP16 GEMV. by David Mansell · 4 months ago
  7. c1787f0 Fix OpenBSD® build failure caused by patch 11144 by Gunes Bayir · 4 months ago
  8. ef63739 Integrate new pretranspose_b_array with extra fused transpose of B by Gunes Bayir · 5 months ago
  9. e695579 arm_gemm: SME: Remove artificial single-thread constraint on quantized int8 kernels. by David Mansell · 6 months ago
  10. fb92e22 arm_gemm: convolution: optimize convolver.hpp. by David Mansell · 7 months ago
  11. 0eb9cfb [ONCPUML-1387] Add ACL based reorder for f32 to bf16 data type conversion. by Renato Arantes · 7 months ago
  12. 92c3d71 Remove duplicate definitions of BF16 fixed format kernels. by David Mansell · 8 months ago
  13. 0fa92b8 arm_gemm: Add SME2 FP16 GEMV using FP16->FP32 dot product. by David Mansell · 9 months ago
  14. 098efc4 Revert "arm_gemm: Add SME2 FP16 GEMV." by David Mansell · 9 months ago
  15. aeced74 arm_gemm: Add SME2 FP16 GEMV. by David Mansell · 9 months ago
  16. fb9c25d arm_gemm: fix 2D threading mode for SME2 by David Mansell · 9 months ago
  17. b7aefd7 GEMM: AArch32: Split assembler block in a32_merge_float_8x6.hpp by David Mansell · 10 months ago
  18. 246fe08 Fix various static check issues by Viet-Hoa Do · 11 months ago
  19. 6c7cf31 Fix build error for armv7a by Pablo Marquez Tello · 1 year, 1 month ago
  20. 74921ee Update CPU kernel implementations and guard directives by Michael Tyler · 1 year, 3 months ago
  21. 8964c89 Update a64_transpose_interleave_16.hpp by David Svantesson · 1 year, 2 months ago
  22. dba672c Integrate multi-threaded pretranspose_B_array by SiCong Li · 1 year, 3 months ago
  23. 251b514 gemm_interleaved: Set up the accumulation buffer properly in alternate by David Mansell · 1 year, 5 months ago
  24. aaa9da1 arm_gemm: Add SME2 FP16 kernels. by David Mansell · 1 year, 4 months ago
  25. f9225b4 GEMM: SME: Allow threading for quantized GEMMs. by David Mansell · 1 year, 4 months ago
  26. 7d9a626 Update CPU kernels to remove x19 and w19 by Michael Tyler · 1 year, 5 months ago
  27. be13cea Revert "Update CPU kernels to remove x19" by Michael Tyler · 1 year, 5 months ago
  28. ba20975 Update CPU kernels to remove x19 by Michael Tyler · 1 year, 7 months ago
  29. bb1ab05 Fix company name on copyright notice by Viet-Hoa Do · 1 year, 6 months ago
  30. 81f796b Fix various compilation errors by Viet-Hoa Do · 1 year, 6 months ago
  31. 03b2971 Integrate SME2 kernels by Viet-Hoa Do · 2 years, 1 month ago
  32. ce79ac6 CPU GEMM: Fix overreads in SVE merges. by David Mansell · 1 year, 9 months ago
  33. 93581a5 [ONCPUML-970] Fast math mode for fixed format kernels by Pablo Marquez Tello · 2 years ago
  34. 553f695 [ONCPUML-951] Variable weight support for Convolution. by Francesco Petrogalli · 2 years ago
  35. 1f86449 Fix Neoverse V1 heuristics for FP32 fast mode by ramelg01 · 2 years ago
  36. 84a0941 Fix OpenBSD build errors by Pablo Marquez Tello · 2 years ago
  37. 5fcf22d [arm_gemm] Import fixed-format kernels from gemm_linux. by Francesco.Petrogalli@arm.com · 2 years, 3 months ago
  38. 9d18738 Updating a64_gemm_u8 a64_gemm_s8 kernels headers by ramelg01 · 2 years, 2 months ago
  39. e33c556 [arm_gemm] Use static validate to find arm_gemm kernels. by Francesco.Petrogalli@arm.com · 2 years, 3 months ago
  40. b4cd2dc Remove Non-Inclusive Term "Master" by ramelg01 · 2 years, 3 months ago
  41. 193cad3 Remove deprecated interface from arm_compute. by Francesco.Petrogalli@arm.com · 2 years, 4 months ago
  42. 4e66d70 Added windows native build support by Pablo Tello · 2 years, 4 months ago
  43. 7195f71 Add OpenBSD/arm64 support. by Kevin Lo · 2 years, 6 months ago
  44. b2eba7f Replacing non-inclusive terms with proper terms by ramelg01 · 2 years, 6 months ago
  45. b6e49eb Update A510 arm_gemm cpu Kernels by ramelg01 · 2 years, 7 months ago
  46. 4eea7fd Update GeMM heuristic on CPU by Gian Marco Iodice · 2 years, 8 months ago
  47. 63e0beb Add support for non-constant weights and biases in CpuFullyConnected by Giorgio Arena · 2 years, 9 months ago
  48. 9ac7b99 Revert "Add support for non-constant weights and biases in CpuFullyConnected" by Pablo Marquez Tello · 2 years, 10 months ago
  49. e42a87f Update cpu heuristics for GEMM by Gunes Bayir · 2 years, 10 months ago
  50. aed63ee Add support for non-constant weights and biases in CpuFullyConnected by Michele Di Giorgio · 3 years ago
  51. d216f57 Update cpu depthwise kernels by Freddie Liardet · 2 years, 11 months ago
  52. 6e90c12 Add missing limits include by Freddie Liardet · 2 years, 11 months ago
  53. 9a1e28b Compilation issue: neon=1 armv8.2 on Android with NDKr18beta1 by Gian Marco Iodice · 3 years ago
  54. a76e403 Fix A55 performance constant for fp16 hybrid gemm kernel by Georgios Pinitas · 3 years ago
  55. 120c87b Fix bare metal build issues by Freddie Liardet · 3 years ago
  56. 97426a7 Remove generated kernels that overlap hand-written ones by Georgios Pinitas · 3 years ago
  57. 387f80e Update GEMM assembly performance parameters by Georgios Pinitas · 3 years ago
  58. 5e61cb0 Add missing limits include by Freddie Liardet · 3 years ago
  59. 8bd2556 Fix vector_length identification mechanism for SVE by Georgios Pinitas · 3 years ago
  60. e7012a6 Fix bare metal build error by Freddie Liardet · 3 years ago
  61. 4ee8b15 Update GEMM assembly kernels by Georgios Pinitas · 3 years ago
  62. 20fca52 Create core library using high priority operators by Michalis Spyrou · 3 years, 1 month ago
  63. d02d5ed Integrate improved CPU depthwise convolution kernels by Michele Di Giorgio · 3 years, 5 months ago
  64. 0758c4c Add missing limits include by Michalis Spyrou · 3 years, 2 months ago
  65. 778b95c Update assembly code by Michalis Spyrou · 3 years, 2 months ago
  66. 8a1ac61 Fix incorrect return statement in gemm_uint8 heuristic selection by Georgios Pinitas · 3 years, 3 months ago
  67. b71322d Fix convolution with bias segmentation fault issue by Sheri Zhang · 3 years, 3 months ago
  68. 33f41fa Fix trademarks throughout the codebase by Michele Di Giorgio · 3 years, 4 months ago
  69. a00180a Update U8 mmla kernel by Michalis Spyrou · 3 years, 3 months ago
  70. a50f193 Updated cpu detection by Pablo Marquez Tello · 3 years, 4 months ago
  71. aac71e5 Update int8 A55 kernels by Georgios Pinitas · 3 years, 4 months ago
  72. 6f45cf7 Account Ksections correctly for interleaved and hybrid_indirect gemm kernels by Georgios Pinitas · 3 years, 4 months ago
  73. 85e16c2 Use vector resizing instead of temporary assign in gemm_hybrid_indirect by Georgios Pinitas · 3 years, 4 months ago
  74. 0ad0129 Remove unreachable code in gemm_hybrid_quantized for computing k_block by Georgios Pinitas · 3 years, 4 months ago
  75. ac6499a Comply with Trademark rules for use of Neon, Arm and Mali by Sheri Zhang · 3 years, 5 months ago
  76. e28cf39 Regenerate kernels and update A55 versions by Georgios Pinitas · 3 years, 5 months ago
  77. 33e0307 Cycle estimate-based kernel selection for dot product quantized s8/u8 kernels by Georgios Pinitas · 3 years, 6 months ago
  78. 7229182 Add missing std headers by Sang-Hoon Park · 3 years, 6 months ago
  79. 410e21e Fix baremetal arm_compute_validation build errors by SiCongLi · 3 years, 7 months ago
  80. e5a9ad8 COMPMID-3869: Update Sconstruct to support SVE/SVE2 by Manuel Bottini · 3 years, 7 months ago
  81. cd22cbf Update GEMV heuristics for quantized types for A53 by Georgios Pinitas · 3 years, 7 months ago
  82. 827817e COMPMID-3987: Nightly failure - Android builds failing in dataset and validation by Manuel Bottini · 3 years, 7 months ago
  83. 40943df Update tuning numbers for A55 for both fp16 and fp32 by Georgios Pinitas · 3 years, 7 months ago
  84. 6c62d7a COMPMID-3970: Failure when building with GCC < 6 by Georgios Pinitas · 3 years, 8 months ago
  85. c0b6f76 COMPMID-3776: Indirect GEMM by Georgios Pinitas · 3 years, 8 months ago
  86. 9e698d5 COMPMID-3757: (u)int8: Don't select the 16-bit route on A53 for cases with very few rows by David Mansell · 3 years, 10 months ago
  87. fa269bb MLCE-229: Fixed requantization per channel in asm kernel by morgolock · 3 years, 10 months ago
  88. 0bc80da MLCE-229: Support for negative shifts in asm kernels by morgolock · 3 years, 11 months ago
  89. 6c6619b [ONCPUML-120]: Tweak of the launch heuristics for hybrid_u8u32_dot_16x4 kernel by Aleksandr Nikolaev · 4 years ago
  90. 318c9f4 COMPMID-3578: Update FP32/int8 kernel selection. by David Mansell · 4 years ago
  91. a084b46 [ONCPUML-97]: Implement "int8" support for 2D decomposition at high core counts by Aleksandr Nikolaev · 4 years ago
  92. 534fdea [ONCPUML-96] FP16 support for 2D decomposition at high core counts. by cfRod · 4 years ago
  93. d9eaf61 COMPMID-3324: Adjusting capitalization of Arm copyright claim to reflect Arm preferred presentation by Michele Di Giorgio · 4 years ago
  94. 0cc50ed COMPMID-3324: Remove pretransposed support from NEON backend by Georgios Pinitas · 4 years ago
  95. 5aa1a0b COMPID-3324: Clean GEMM kernels by Georgios Pinitas · 4 years ago
  96. af56d52 COMPMID-3324: Fix per-channel quantization on N blocking by Georgios Pinitas · 4 years ago
  97. 7375548 COMPMID-3324: Handle unused variable in SVE based GEMM kernels. by Georgios Pinitas · 4 years ago
  98. 6ad60af COMPMID-3520: Move ndrange.hpp header from arm_gemm to assembly by Michele Di Giorgio · 4 years, 1 month ago
  99. 8aa8764 COMPMID-3324: Remove extra bracket by Georgios Pinitas · 4 years, 1 month ago
  100. 04c8e63 move ndrange.hpp header into arm_compute directory by Vincent ABRIOU · 4 years, 1 month ago