tree: 2044b9f37614f8a5c1712b57ed1939e5b2bd21d2 [path history] [tgz]
  1. llvm_gpu_backend/
  2. tests/
  3. backend_configs.proto
  4. buffer_allocations.cc
  5. buffer_allocations.h
  6. buffer_comparator.cc
  7. buffer_comparator.h
  8. buffer_comparator_test.cc
  9. BUILD
  10. cholesky_thunk.cc
  11. cholesky_thunk.h
  12. conditional_thunk.cc
  13. conditional_thunk.h
  14. convolution_thunk.cc
  15. convolution_thunk.h
  16. copy_thunk.cc
  17. copy_thunk.h
  18. cudnn_batchnorm_rewriter.cc
  19. cudnn_batchnorm_rewriter.h
  20. cudnn_batchnorm_thunk.cc
  21. cudnn_batchnorm_thunk.h
  22. cudnn_conv_algorithm_picker.cc
  23. cudnn_conv_algorithm_picker.h
  24. cudnn_conv_pad_for_tensor_cores.cc
  25. cudnn_conv_pad_for_tensor_cores.h
  26. cudnn_conv_pad_for_tensor_cores_test.cc
  27. cudnn_conv_padding_legalization.cc
  28. cudnn_conv_padding_legalization.h
  29. cudnn_conv_rewriter.cc
  30. cudnn_conv_rewriter.h
  31. cudnn_conv_rewriter_test.cc
  32. cudnn_conv_runner.cc
  33. cudnn_conv_runner.h
  34. cudnn_fused_conv_rewriter.cc
  35. cudnn_fused_conv_rewriter.h
  36. cudnn_fused_conv_rewriter_test.cc
  37. cusolver_context.cc
  38. cusolver_context.h
  39. cusolver_rewriter.cc
  40. cusolver_rewriter.h
  41. custom_call_test.cc
  42. custom_call_thunk.cc
  43. custom_call_thunk.h
  44. elemental_ir_emitter.cc
  45. elemental_ir_emitter.h
  46. fft_thunk.cc
  47. fft_thunk.h
  48. for_thunk.cc
  49. for_thunk.h
  50. fusion_merger.cc
  51. fusion_merger.h
  52. fusion_merger_test.cc
  53. gemm_thunk.cc
  54. gemm_thunk.h
  55. gpu_autotuning.proto
  56. gpu_constants.cc
  57. gpu_constants.h
  58. gpu_copy_insertion.cc
  59. gpu_copy_insertion.h
  60. gpu_executable.cc
  61. gpu_executable.h
  62. gpu_fusible.cc
  63. gpu_fusible.h
  64. gpu_fusible_test.cc
  65. gpu_hlo_schedule.cc
  66. gpu_hlo_schedule.h
  67. gpu_hlo_schedule_test.cc
  68. gpu_hlo_support_checker.cc
  69. gpu_hlo_support_checker.h
  70. gpu_hlo_support_checker_test.cc
  71. gpu_layout_assignment.cc
  72. gpu_layout_assignment.h
  73. gpu_layout_assignment_test.cc
  74. gpu_sanitize_constant_names.cc
  75. gpu_sanitize_constant_names.h
  76. gpu_sanitize_constant_names_test.cc
  77. gpu_transfer_manager.cc
  78. gpu_transfer_manager.h
  79. hlo_execution_profiler.cc
  80. hlo_execution_profiler.h
  81. hlo_to_ir_bindings.cc
  82. hlo_to_ir_bindings.h
  83. infeed_manager.cc
  84. infeed_manager.h
  85. infeed_thunk.cc
  86. infeed_thunk.h
  87. instruction_fusion.cc
  88. instruction_fusion.h
  89. instruction_fusion_test.cc
  90. ir_emission_utils.cc
  91. ir_emission_utils.h
  92. ir_emitter.cc
  93. ir_emitter.h
  94. ir_emitter_context.h
  95. ir_emitter_nested.cc
  96. ir_emitter_nested.h
  97. ir_emitter_unnested.cc
  98. ir_emitter_unnested.h
  99. kernel_thunk.cc
  100. kernel_thunk.h
  101. memset_thunk.cc
  102. memset_thunk.h
  103. multi_output_fusion.cc
  104. multi_output_fusion.h
  105. multi_output_fusion_test.cc
  106. nccl_all_reduce_thunk.cc
  107. nccl_all_reduce_thunk.h
  108. nvptx_compiler.cc
  109. nvptx_compiler.h
  110. outfeed_manager.cc
  111. outfeed_manager.h
  112. outfeed_thunk.cc
  113. outfeed_thunk.h
  114. parallel_loop_emitter.cc
  115. parallel_loop_emitter.h
  116. partition_assignment.cc
  117. partition_assignment.h
  118. redzone_allocator.cc
  119. redzone_allocator.h
  120. redzone_allocator_test.cc
  121. scratch_allocator.cc
  122. scratch_allocator.h
  123. sequential_thunk.cc
  124. sequential_thunk.h
  125. stream_assignment.cc
  126. stream_assignment.h
  127. stream_assignment_test.cc
  128. stream_executor_util.cc
  129. stream_executor_util.h
  130. target_util.cc
  131. target_util.h
  132. thunk.cc
  133. thunk.h
  134. thunk_schedule.cc
  135. thunk_schedule.h
  136. triangular_solve_thunk.cc
  137. triangular_solve_thunk.h
  138. tuple_thunk.cc
  139. tuple_thunk.h
  140. variadic_op_splitter.cc
  141. variadic_op_splitter.h
  142. variadic_op_splitter_test.cc
  143. while_thunk.cc
  144. while_thunk.h
  145. while_transformer_test.cc
  146. xfeed_queue.h