Google Git
Sign in
opensecura / sw / kelvin / HEAD
  1. fc92b84 Align sections in kelvin_tcm to 16-bytes by Alex Van Damme · 9 days ago master
  2. 6bba748 Add a flag to allow targeting a Kelvin w/ TCMs by Alex Van Damme · 3 weeks ago
  3. 8ca6679 Dhrystone tests in Kelvin by Naveen Dodda · 3 months ago
  4. 3ff81e5 Update rules_python to 0.26.0 by Alex Van Damme · 3 months ago
  5. 58b54fa Improved strategy for filter padding of conv I3xD8 by Naveen Dodda · 3 months ago
  6. d262229 Track spi_flash_init api change. by Sam Leffler · 3 months ago
  7. d62a1e9 Specialized Conv kernel to handle input tensors by Naveen Dodda · 4 months ago
  8. b3e0296 Patch mcsr test to allow any value of mhartid by Alex Van Damme · 4 months ago
  9. 48e6667 Check for ISA extension in startup by Alex Van Damme · 4 months ago
  10. 0388426 Merge "sw/kelvin: add test target for newly added mul op for Kelvin" by Lun Dong · 4 months ago
  11. 8556551 Toggle GPIO for Each Inference of a Benchmark by Stefan Hall · 4 months ago
  12. e10934b GPIO Pulse Before Benchmark Run by Stefan Hall · 4 months ago
  13. 11adf8c Optimizing Depthwise conv depth % 32 by Naveen Dodda · 5 months ago
  14. 4219ffa Merge "Depthwise conv for Depth % == 16" by Naveen Dodda · 5 months ago
  15. af6f048 Depthwise conv for Depth % == 16 by Naveen Dodda · 5 months ago
  16. 8ba4ce2 Improve kelvin isa doc by David Gao · 5 months ago
  17. be6281c sw/kelvin: add test target for newly added mul op for Kelvin by Lun Dong · 5 months ago
  18. c9a931d sw/kelvin: add max_pooling int16 kernel for Kelvin by Lun Dong · 5 months ago
  19. fc7df4e Merge "sw/kelvin: clean up function definitions" by Lun Dong · 5 months ago
  20. a67d4b9 sw/kelvin: clean up function definitions by Lun Dong · 5 months ago
  21. 7f114bd sw/kelvin: add elementwise multiplication kernel for Kelvin by Lun Dong · 5 months ago
  22. b0b66a7 Kelvin Resize nearest neighbors for int8 by Naveen Dodda · 5 months ago
  23. 321c904 Rewrite ConvPerChannelD1OD24_5x5 by David Gao · 5 months ago
  24. 0758fb8 Improve Conv2dD32 by Alex Van Damme · 5 months ago
  25. 008f0ae Restrict ConvS16B64K1xn to height 1 by Alex Van Damme · 5 months ago
  26. f22bdde Fix in_channel calculation in ConvS8D4 by Alex Van Damme · 5 months ago
  27. 108cf32 Remove extra offset addition from ElementwiseAdd by Alex Van Damme · 5 months ago
  28. 5190b46 Merge "Add test_status calls to benchmark_smc" by Alex Van Damme · 5 months ago
  29. 35a67de Merge "Create templated version of Swizzle." by Alex Van Damme · 5 months ago
  30. 109726f Add test_status calls to benchmark_smc by Alex Van Damme · 5 months ago
  31. 5496087 Merge "Implement DepthwiseConvS85x5D32 w/ adwconv" by Alex Van Damme · 5 months ago
  32. 18694e4 Merge "Two outputs per iteration in ConvPerChannelD1OD24_5x5" by Alex Van Damme · 5 months ago
  33. 2cebe31 Implement DepthwiseConvS85x5D32 w/ adwconv by Alex Van Damme · 5 months ago
  34. f427e85 Create templated version of Swizzle. by Derek Chow · 5 months ago
  35. 41f1cec Reduce register pressure in ConvS8W8D4. by Derek Chow · 5 months ago
  36. f353919 Two outputs per iteration in ConvPerChannelD1OD24_5x5 by Alex Van Damme · 5 months ago
  37. 9e0b2ba Merge "Reduce vld calls in ConvS8D4." by Derek Chow · 5 months ago
  38. 2f60851 Reduce vld calls in ConvS8D4. by Derek Chow · 5 months ago
  39. 87cc267 Merge "Process 16 channels per iteration in 1x1 d16" by Alex Van Damme · 5 months ago
  40. cf069b3 Process 16 channels per iteration in 1x1 d16 by Alex Van Damme · 5 months ago
  41. b5caeab Merge "Improve ElementwiseAddS8" by Alex Van Damme · 5 months ago
  42. 74f2f74 Create and apply interleaved output pipeline macros by Alex Van Damme · 5 months ago
  43. 8da6e53 5x5 DepthwiseConv, 4 outputs per loop iteration by Alex Van Damme · 6 months ago
  44. ac91807 Improve ElementwiseAddS8 by Alex Van Damme · 6 months ago
  45. d22d7d6 DepthwiseConv 3x3, 4 per iteration by Alex Van Damme · 6 months ago
  46. 13fe02a Create RUN_KERNEL macro for DepthwiseConvS8 by Alex Van Damme · 6 months ago
  47. 088841b Specialize 3x3, stride 1 DepthwiseConv by Alex Van Damme · 6 months ago
  48. 5106685 Vectorized Logistic for int8 by Alex Van Damme · 6 months ago
  49. b309494 Merge changes I1f0ec9d3,I55e0cf22 by Cindy Liu · 6 months ago
  50. db10d3b Merge changes from topic "nexus-benchmark" by Cindy Liu · 6 months ago
  51. 627a3ba Lint cleanup benchmark_kelvin.cc by Cindy Liu · 6 months ago
  52. 2ec00d9 Fix carry over benchmark mismatch count by Cindy Liu · 6 months ago
  53. 8ef6f11 Use 1x1 d=32n kernel more aggressively. by Derek Chow · 6 months ago
  54. aaf9d30 Update benchmark device rule to support tags by Cindy Liu · 6 months ago
  55. f6ec59d Format benchmarks.bzl by Cindy Liu · 6 months ago
  56. 1ad0284 Point wise convolution input_depth = 16 by Derek Chow · 6 months ago
  57. 5160bc6 Add specialized pointwise convolution. by Derek Chow · 6 months ago
  58. dd44caa Allow specifying benchmark arena size by Alex Van Damme · 6 months ago
  59. d2aca97 Add additional ops to benchmark by Alex Van Damme · 6 months ago
  60. 78538b3 Use dwconv on input_depth == 1, 5x5 by Alex Van Damme · 6 months ago
  61. 0d75a42 Refactor kernel selection. by Derek Chow · 6 months ago
  62. 2aeaaa8 Enable O2 optimizations. by Derek Chow · 6 months ago
  63. 5971487 Improvements to elementwise_add_{s8,s16} by Alex Van Damme · 6 months ago
  64. ca72b40 Improve ConvS8D4 by Alex Van Damme · 6 months ago
  65. cd3d0e3 3x3 DepthwiseConv w/ adwconv by Alex Van Damme · 6 months ago
  66. b1afda6 Specialize 5x5 DepthwiseConv by Alex Van Damme · 7 months ago
  67. a99c93d Add support for checking output in benchmark by Alex Van Damme · 7 months ago
  68. fd54c9e Relax output_depth for ConvS8D4 by Alex Van Damme · 7 months ago
  69. 86806b3 Add input_depth == 1 specialized convolution. by Derek Chow · 7 months ago
  70. 456ed80 Merge "Support running a different Kelvin benchmark binary" by Michael Brooks · 6 months ago
  71. 40a8300 Fix swizzling and rounding for depthwise conv by Alex Van Damme · 7 months ago
  72. e617f61 Relax restrictions on aconv-based Conv2D by Alex Van Damme · 7 months ago
  73. 3b8d3cb sw/kelvin: Refactoring TFLM Kelvin kernel optimization codes by Lun Dong · 7 months ago
  74. d7880e8 Add doc on tflm op support in Kelvin. by Derek Chow · 7 months ago
  75. 2d626f6 Support running a different Kelvin benchmark binary by Michael Brooks · 7 months ago
  76. b11ad17 Specialized int8 conv kernels by Alex Van Damme · 7 months ago
  77. be4ab97 WIP Depthwise conv for 2d kernels by Naveen Dodda · 7 months ago
  78. c62ec01 Add wall-time measurement to Benchmark by Alex Van Damme · 8 months ago
  79. c47ddc8 Increasing memory to support models for benchmarks. by Naveen Dodda · 8 months ago
  80. 1eb552e Updating resolver to support mobilenet models by Naveen Dodda · 8 months ago
  81. ff78446 Add support for using test data in model benchmarks by Michael Brooks · 8 months ago
  82. 5f67634 Merge "Add Support for Profiling TFLM Models in Benchmarks" by Michael Brooks · 8 months ago
  83. d884926 Fix hw test script to support extra flags by Cindy Liu · 8 months ago
  84. fe2b2a8 Add Support for Profiling TFLM Models in Benchmarks by Michael Brooks · 8 months ago
  85. a1e166f Pass through extra flags to the hardware sim by Julian Mullings-Black · 8 months ago
  86. d48c5a4 Patches for benchmark on ASIC by Alex Van Damme · 8 months ago
  87. 3bdf8f4 Add minstret to perf_counters by Alex Van Damme · 10 months ago
  88. c0214c3 Add ecall/mret test by Alex Van Damme · 9 months ago
  89. 8d688e2 Fix Benchmark SMC Print Format by Michael Brooks · 8 months ago
  90. 03b3adf Additonal Benchmark Targets by Michael Brooks · 8 months ago
  91. dc03ded Add benchmark suite to sw/kelvin by Michael Brooks · 8 months ago
  92. 215d48a Enabling kelvin_test outside of sw/kelvin. by Naveen Dodda · 10 months ago
  93. 0b2b7fb Type-check around find_cc_toolchain result usage by Alex Van Damme · 10 months ago
  94. 2b6d459 Mark `model_input` and `output_header` as NOLOAD by Alex Van Damme · 12 months ago
  95. 0cc464f Make pooling_test "large" to adjust timeout by Julian Mullings-Black · 10 months ago
  96. 24619c5 Add perf_counters test by Alex Van Damme · 11 months ago
  97. 78e3bc3 Update .bazelversion to 6.2.1 by Alex Van Damme · 12 months ago
  98. 3285c6a Changes to optimize max_pool for Kelvin int8 dtype by Naveen-Dodda · 12 months ago
  99. 0c9118e Add riscv CSR tests, enable zicsr by Alex Van Damme · 12 months ago
  100. 4054485 Merge "sw/kelvin: revamp layout to support setting model input data" by Sam Leffler · 1 year ago