tree: a1e88d239b140dece222b0f591fb387244ada6a8 [path history] [tgz]
  1. data/
  2. llvm_gpu_backend/
  3. tests/
  4. alias_passthrough_params.cc
  5. alias_passthrough_params.h
  6. alias_passthrough_params_test.cc
  7. amdgpu_compiler.cc
  8. amdgpu_compiler.h
  9. amdgpu_compiler_registration.cc
  10. backend_configs.proto
  11. buffer_allocations.cc
  12. buffer_allocations.h
  13. buffer_comparator.cc
  14. buffer_comparator.h
  15. buffer_comparator_test.cc
  16. BUILD
  17. cholesky_thunk.cc
  18. cholesky_thunk.h
  19. collective_permute_thunk.cc
  20. collective_permute_thunk.h
  21. conditional_thunk.cc
  22. conditional_thunk.h
  23. convolution_thunk.cc
  24. convolution_thunk.h
  25. copy_thunk.cc
  26. copy_thunk.h
  27. cublas_gemm_pad_for_tensor_cores.cc
  28. cublas_gemm_pad_for_tensor_cores.h
  29. cublas_gemm_pad_for_tensor_cores_test.cc
  30. cudnn_batchnorm_rewriter.cc
  31. cudnn_batchnorm_rewriter.h
  32. cudnn_batchnorm_runner.cc
  33. cudnn_batchnorm_runner.h
  34. cudnn_batchnorm_thunk.cc
  35. cudnn_batchnorm_thunk.h
  36. cudnn_fused_conv_rewriter.cc
  37. cudnn_fused_conv_rewriter.h
  38. cudnn_fused_conv_rewriter_test.cc
  39. cudnn_pad_for_convolutions.cc
  40. cudnn_pad_for_convolutions.h
  41. cudnn_pad_for_convolutions_test.cc
  42. cusolver_context.cc
  43. cusolver_context.h
  44. cusolver_rewriter.cc
  45. cusolver_rewriter.h
  46. custom_call_test.cc
  47. custom_call_thunk.cc
  48. custom_call_thunk.h
  49. dummy_all_reduce_thunk.cc
  50. elemental_ir_emitter.cc
  51. elemental_ir_emitter.h
  52. fft_thunk.cc
  53. fft_thunk.h
  54. for_thunk.cc
  55. for_thunk.h
  56. fusion_merger.cc
  57. fusion_merger.h
  58. fusion_merger_test.cc
  59. gemm_algorithm_picker.cc
  60. gemm_algorithm_picker.h
  61. gemm_rewriter.cc
  62. gemm_rewriter.h
  63. gemm_thunk.cc
  64. gemm_thunk.h
  65. gpu_autotuning.proto
  66. gpu_compiler.cc
  67. gpu_compiler.h
  68. gpu_constants.cc
  69. gpu_constants.h
  70. gpu_conv_algorithm_picker.cc
  71. gpu_conv_algorithm_picker.h
  72. gpu_conv_padding_legalization.cc
  73. gpu_conv_padding_legalization.h
  74. gpu_conv_rewriter.cc
  75. gpu_conv_rewriter.h
  76. gpu_conv_rewriter_test.cc
  77. gpu_conv_runner.cc
  78. gpu_conv_runner.h
  79. gpu_copy_insertion.cc
  80. gpu_copy_insertion.h
  81. gpu_debug_info_manager.cc
  82. gpu_debug_info_manager.h
  83. gpu_debug_info_manager_test.cc
  84. gpu_executable.cc
  85. gpu_executable.h
  86. gpu_fusible.cc
  87. gpu_fusible.h
  88. gpu_fusible_test.cc
  89. gpu_hlo_schedule.cc
  90. gpu_hlo_schedule.h
  91. gpu_hlo_schedule_test.cc
  92. gpu_layout_assignment.cc
  93. gpu_layout_assignment.h
  94. gpu_layout_assignment_test.cc
  95. gpu_sanitize_constant_names.cc
  96. gpu_sanitize_constant_names.h
  97. gpu_sanitize_constant_names_test.cc
  98. gpu_scatter_expander.cc
  99. gpu_scatter_expander.h
  100. gpu_transfer_manager.cc
  101. gpu_transfer_manager.h
  102. gpu_types.h
  103. hlo_algorithm_blacklist.cc
  104. hlo_algorithm_blacklist.h
  105. hlo_algorithm_blacklist_test.cc
  106. hlo_execution_profiler.cc
  107. hlo_execution_profiler.h
  108. hlo_to_ir_bindings.cc
  109. hlo_to_ir_bindings.h
  110. horizontal_fusion.cc
  111. horizontal_fusion.h
  112. horizontal_fusion_test.cc
  113. infeed_manager.cc
  114. infeed_manager.h
  115. infeed_thunk.cc
  116. infeed_thunk.h
  117. instruction_fusion.cc
  118. instruction_fusion.h
  119. instruction_fusion_test.cc
  120. ir_emission_utils.cc
  121. ir_emission_utils.h
  122. ir_emitter.cc
  123. ir_emitter.h
  124. ir_emitter_context.h
  125. ir_emitter_nested.cc
  126. ir_emitter_nested.h
  127. ir_emitter_unnested.cc
  128. ir_emitter_unnested.h
  129. kernel_mapping_scheme.h
  130. kernel_thunk.cc
  131. kernel_thunk.h
  132. memset_thunk.cc
  133. memset_thunk.h
  134. multi_output_fusion.cc
  135. multi_output_fusion.h
  136. multi_output_fusion_test.cc
  137. nccl_all_reduce_thunk.cc
  138. nccl_all_reduce_thunk.h
  139. nvptx_compiler.cc
  140. nvptx_compiler.h
  141. nvptx_compiler_registration.cc
  142. outfeed_manager.cc
  143. outfeed_manager.h
  144. outfeed_thunk.cc
  145. outfeed_thunk.h
  146. parallel_loop_emitter.cc
  147. parallel_loop_emitter.h
  148. partition_assignment.cc
  149. partition_assignment.h
  150. reduction_degenerate_dim_remover.cc
  151. reduction_degenerate_dim_remover.h
  152. reduction_dimension_grouper.cc
  153. reduction_dimension_grouper.h
  154. reduction_layout_normalizer.cc
  155. reduction_layout_normalizer.h
  156. replica_id_thunk.cc
  157. replica_id_thunk.h
  158. sequential_thunk.cc
  159. sequential_thunk.h
  160. stream_assignment.cc
  161. stream_assignment.h
  162. stream_assignment_test.cc
  163. stream_executor_util.cc
  164. stream_executor_util.h
  165. target_constants.h
  166. target_util.cc
  167. target_util.h
  168. thunk.cc
  169. thunk.h
  170. thunk_emitter.cc
  171. thunk_emitter.h
  172. thunk_schedule.cc
  173. thunk_schedule.h
  174. tree_reduction_rewriter.cc
  175. tree_reduction_rewriter.h
  176. triangular_solve_thunk.cc
  177. triangular_solve_thunk.h
  178. tuple_thunk.cc
  179. tuple_thunk.h
  180. variadic_op_splitter.cc
  181. variadic_op_splitter.h
  182. variadic_op_splitter_test.cc
  183. while_thunk.cc
  184. while_thunk.h
  185. while_transformer_test.cc
  186. xfeed_queue.h