Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / XNNPACK / f721e371cfae0087cb95bfa752b896c005d58cb8
  1. f721e37 LRINTF variants of scalar F32->QS8 and F32->QU8 VCVT microkernels by Marat Dukhan · 2 years, 6 months ago
  2. bdf1099 Refactor scalar F32->QS8 and F32->QU8 microkernels by Marat Dukhan · 2 years, 6 months ago
  3. 74ddd27 Run formatting on generate-gemm-test.py by Zhi An Ng · 2 years, 6 months ago
  4. 2ac722e Refactor requantization in scalar QS8/QC8/QU8 microkernels by Marat Dukhan · 2 years, 6 months ago
  5. 0e80137 Refactor parameters in F32 VRND microkernels by Marat Dukhan · 2 years, 6 months ago
  6. d57a5ad Add const keyword for AVX load masks by Marat Dukhan · 2 years, 6 months ago
  7. bbfc27d Refactor NEON/NEONFMA VSIGMOID microkernels by Marat Dukhan · 2 years, 6 months ago
  8. 6853f23 Update amalgamated microkernels by Marat Dukhan · 2 years, 6 months ago
  9. ce834ad Refactor parameters in F32 VSIGMOID microkernels by Marat Dukhan · 2 years, 6 months ago
  10. 05b6cb1 Transpose microkernel tester uses iota instead of rng so that it's easier to debug tests by Alan Kelly · 2 years, 6 months ago
  11. 4a79ff2 Refactor parameters in F32 VELU microkernels by Marat Dukhan · 2 years, 6 months ago
  12. e5efb16 Refactor VUNARY microkernel parameters by Marat Dukhan · 2 years, 6 months ago
  13. a8b3994 Remove mask_table literal from F32 DWCONV AVX microkernels by Marat Dukhan · 2 years, 6 months ago
  14. 9084fc8 Quantized Sigmoid and ELU benchmarks by Marat Dukhan · 2 years, 6 months ago
  15. 3ddc20c Benchmarks for Abs, Negate, and Square operators by Marat Dukhan · 2 years, 6 months ago
  16. 5c7fd89 Benchmark for Leaky ReLU operator by Marat Dukhan · 2 years, 7 months ago
  17. a0129e9 Refactor benchmarks for elementwise operators by Marat Dukhan · 2 years, 7 months ago
  18. e72b282 Refactor parameters in F32 VSQRT microkernels by Marat Dukhan · 2 years, 7 months ago
  19. 98c5215 Move mask_table into VBINARY[C] AVX microkernel parameters by Marat Dukhan · 2 years, 7 months ago
  20. 0f28193 Minor optimization in F32 GEMM/IGEMM AVX512F microkernels by Marat Dukhan · 2 years, 7 months ago
  21. d57186a Refactor F32 VMULCADDC parameters by Marat Dukhan · 2 years, 7 months ago
  22. f600497 Refactor parameter initialization in Vector Binary Elementwise microkernels by Marat Dukhan · 2 years, 7 months ago
  23. b40ee63 Add comment about architecture for each set of inits for ARM. by Frank Barchard · 2 years, 7 months ago
  24. c83ef3b Refactor F32 MINMAX parameters for WAsm SIMD by Marat Dukhan · 2 years, 7 months ago
  25. 2894e99 Refactor F32 VLRELU microkernels by Marat Dukhan · 2 years, 7 months ago
  26. b7c1b71 Refactor F32->F16 VCVT microkernels by Marat Dukhan · 2 years, 7 months ago
  27. 7ddef84 Move mask_table into VCLAMP AVX microkernel parameters by Marat Dukhan · 2 years, 7 months ago
  28. e14e791 Move mask_table into VHSWISH AVX microkernel parameters by Marat Dukhan · 2 years, 7 months ago
  29. 134f984 Refactor F16->F32 VCVT microkernels by Marat Dukhan · 2 years, 7 months ago
  30. 3220551 Use --features wasm_simd rather than --copts -msimd128 for WAsm SIMD builds by Marat Dukhan · 2 years, 7 months ago
  31. 4d738ae Include vcvtnq_s32_f32 polyfill for older gcc versions by Marat Dukhan · 2 years, 7 months ago
  32. dc54e12 Replace vshll_n_u32(v, 0) with vmovl_u32 in C4/C4S2 GEMM/IGEMM microkernels by Marat Dukhan · 2 years, 7 months ago
  33. e1228e3 Fix .clang-format path by Marat Dukhan · 2 years, 7 months ago
  34. 2700809 Specify -mfp16-format=ieee for AArch32 GCC builds by Marat Dukhan · 2 years, 7 months ago
  35. 70137e4 Enable AArch32 QC8 neon dot product by Frank Barchard · 2 years, 7 months ago
  36. 87fe410 QC8 quantization for all aarch32 GEMM/IGEMM microkernels by Frank Barchard · 2 years, 7 months ago
  37. a2f1891 Add _prfm to names on Neon microkernels in a consistent way. by Frank Barchard · 2 years, 7 months ago
  38. ef0f09c Add cpu clockrate to x16/x32_transpose benchmarks. by Frank Barchard · 2 years, 7 months ago
  39. 447aa7b #include allocator.h header to gemm tests. by Frank Barchard · 2 years, 7 months ago
  40. 1945f0b SSE transpose x16 microkernel (4x8) by Alan Kelly · 2 years, 7 months ago
  41. 57719a2 clang-format for microkernels by Alan Kelly · 2 years, 7 months ago
  42. 0d10cc7 Split VHSWISH parameter initialization functions per ISA by Marat Dukhan · 2 years, 7 months ago
  43. b43b47a Add a script to convert existing assembly microkernels to JIT codegen. by Zhi An Ng · 2 years, 7 months ago
  44. 561d068 Refactor parameter initialization for VHSWISH microkernels by Marat Dukhan · 2 years, 7 months ago
  45. e4d3f76 Mark aarch64 microkernels as assembly for tests by Frank Barchard · 2 years, 7 months ago
  46. 7a03a0f Merge pull request #2191 from xbwee1024:bugfix by XNNPACK Team · 2 years, 7 months ago
  47. 1c852c9 Enable PRFM version of QS8 4x8 lane AArch32 microkernels by Frank Barchard · 2 years, 7 months ago
  48. 0db2e4c Support - (minus) operator for creating S/D register lists, this looks closer to native assembly. by Zhi An Ng · 2 years, 7 months ago
  49. 2493de9 WAsmSIMD transpose microkernel by Alan Kelly · 2 years, 7 months ago
  50. 77b694c Fixes style issues with SSE microkernel by Alan Kelly · 2 years, 7 months ago
  51. 691ec40 Use proper intrinsics header in SSE F32 VHSWISH microkernels by Marat Dukhan · 2 years, 7 months ago
  52. c025831 Refactor declarations of parameter initialization functions by Marat Dukhan · 2 years, 7 months ago
  53. 51c6134 Amalgamate SSE and AVX512 microkernels for TFLite build by Marat Dukhan · 2 years, 7 months ago
  54. e0f15ad Split scalar production microkernels into portable, AArch32, and Wasm by Marat Dukhan · 2 years, 7 months ago
  55. c80ffb0 Fix generation of gemm tests for ADJBLOCK and rerun scripts. by Zhi An Ng · 2 years, 7 months ago
  56. f98f58d Lowering to c++11 as c++14 literals was converted to c++11 in #2192 by xbwee · 2 years, 7 months ago
  57. 0fd983b Adds -Wcast-qual flag to detect cast dropping const. by Alan Kelly · 2 years, 7 months ago
  58. f527d56 Avoid using C++14 features in AArch32 assembler test by Marat Dukhan · 2 years, 7 months ago
  59. 562112e Fix build error with cmake for src/jit. by xbwee · 2 years, 7 months ago
  60. 19bfefe Support Relaxed SIMD in xnnpack_cc_library and xnnpack_aggregate_library by Marat Dukhan · 2 years, 7 months ago
  61. 9519816 Enable QS8 4x8 LD64 Neon on AArch32 by Frank Barchard · 2 years, 7 months ago
  62. e31f29e Declare assembly for QS8 microkernels by Frank Barchard · 2 years, 7 months ago
  63. 4c61779 Minimally support WebAssembly Relaxed SIMD builds by Marat Dukhan · 2 years, 7 months ago
  64. 8c7355a Enable QS8 4x8 LD64 dot product on AArch32 by Frank Barchard · 2 years, 7 months ago
  65. 1e9c5ac Fix CMake build by Marat Dukhan · 2 years, 7 months ago
  66. c3c6632 Improve compatibility with GCC in AVX512-SKX microkernels by Marat Dukhan · 2 years, 7 months ago
  67. 50b0bd9 Fix encoding and supported immediate values for vldr and vstr. by Zhi An Ng · 2 years, 7 months ago
  68. 1aac8e8 Implement vmrs (FPSCR) by Zhi An Ng · 2 years, 7 months ago
  69. 0a1b7b6 Implement ldrd (immediate) by Zhi An Ng · 2 years, 7 months ago
  70. 26e55ed Implement vstr instruction by Zhi An Ng · 2 years, 7 months ago
  71. a787832 PUSH lr instead of r14 in AArch32 assembly microkernels by Frank Barchard · 2 years, 7 months ago
  72. e0ac223 QS8 IGEMM neon dot comment change float* to int8_t* by Frank Barchard · 2 years, 7 months ago
  73. 97f99fc Return error if fail to get page size by Zhi An Ng · 2 years, 7 months ago
  74. 932e823 Implement str (imm) by Zhi An Ng · 2 years, 7 months ago
  75. 4ebd680 Implement moveq, cmp (imm), sub (imm). by Zhi An Ng · 2 years, 7 months ago
  76. 2b74ddd Implement vld1_8 with offset register by Zhi An Ng · 2 years, 7 months ago
  77. fea422d Implement vld1_32 (single element to one lane). by Zhi An Ng · 2 years, 7 months ago
  78. e48b5c1 QS8 4x8 Neon Lane LD64 IGEMM AArch32 microkernel by Frank Barchard · 2 years, 7 months ago
  79. 1669dd0 aarch32 avoid the VPUSH/VPOP of unused registers by Frank Barchard · 2 years, 7 months ago
  80. 4841021 QS8 4x8 dot product LD64 IGEMM AArch32 microkernel by Frank Barchard · 2 years, 7 months ago
  81. 938ee9b Implement bic, vld1_8 and vld1_32 for QRegisterList, assert encodings don't error out in tests. by Zhi An Ng · 2 years, 7 months ago
  82. 9364bdc Implement vsdot_s8 instruction by Zhi An Ng · 2 years, 7 months ago
  83. a251f87 Implement vqmovn_s16, and_, adds. by Zhi An Ng · 2 years, 7 months ago
  84. 7c8090d Implement vcmpe_f32, vmovpl_f32, vmovmi_f32. by Zhi An Ng · 2 years, 7 months ago
  85. 2d8180c Implement 2-argument add, vmla_f32, vmov_f32, vmov_f64, vstm. by Zhi An Ng · 2 years, 7 months ago
  86. 70e8c99 Format source and BUILD file by Frank Barchard · 2 years, 7 months ago
  87. 9f3f420 QS8 4x8 LD64 dot product GEMM AArch32 microkernel by Frank Barchard · 2 years, 7 months ago
  88. b63e84c Implement b (unconditional branch) by Zhi An Ng · 2 years, 7 months ago
  89. be4e6a5 Add align for aligning instructions (similar to .align in assembly) by Zhi An Ng · 2 years, 7 months ago
  90. ec17e99 Add license to files by Zhi An Ng · 2 years, 7 months ago
  91. 98393ad AVX512 QS8->F32 and QU8->F32 VCVT microkernels by Marat Dukhan · 2 years, 7 months ago
  92. fda06cb SSE transpose microkernel by Alan Kelly · 2 years, 7 months ago
  93. 7b5f779 AVX2 QS8->F32 and QU8->F32 VCVT microkernels by Marat Dukhan · 2 years, 7 months ago
  94. cd4089f AVX QS8->F32 and QU8->F32 VCVT microkernels by Marat Dukhan · 2 years, 7 months ago
  95. 2edf863 AVX512 F32->QS8 and F32->QU8 VCVT microkernels by Marat Dukhan · 2 years, 7 months ago
  96. 0d399ca AVX2 F32->QS8 and F32->QU8 VCVT microkernels by Marat Dukhan · 2 years, 7 months ago
  97. 3bdbe9f Fix xnn_release_code_memory to unmap entire capacity of buffer by Zhi An Ng · 2 years, 7 months ago
  98. b91432c AVX F32->QS8 and F32->QU8 VCVT microkernels by Marat Dukhan · 2 years, 7 months ago
  99. 6fac719 Implement vqmovn_s32 and vext_8 by Zhi An Ng · 2 years, 7 months ago
  100. 4a58583 Implement vdup_8, vdup_16, vdup_32 by Zhi An Ng · 2 years, 7 months ago