Google Git
Sign in
opensecura / 3p / openxla / iree / fdb7054f284477e4cca6b0e7b9aabb223818bd68 / runtime
  1. 1044a85 Return a meaningful message on empty `--input=` flags. (#12192) by Ben Vanik · 2 years, 2 months ago
  2. a0a8bb8 [EmitC] Add support for Buffer Ops in VM Dialect (#11776) by Simon Camphausen · 2 years, 2 months ago
  3. ed10551 Add "Programming Language :: Python :: 3.11" classifier (#12163) by powderluv · 2 years, 3 months ago
  4. b339919 Supporting CUDA importable buffers in compatibility check. (#12093) by Ben Vanik · 2 years, 3 months ago
  5. af5b6fe Get the right `pack`/`unpack` ukernel ARM64 tile functions (#12141) by bjacob · 2 years, 3 months ago
  6. bd302d1 Fix benchmark.py issues (#12082) by Kojo Acquah · 2 years, 3 months ago
  7. 7c72bce Fix `IREE_FLAGS_ENABLE_FLAG_FILE` file IO support (#12098) by CindyLiu · 2 years, 3 months ago
  8. 99fb839 Adding iree_vm_list_swap_storage and iree_vm_list_copy. (#12088) by Ben Vanik · 2 years, 3 months ago
  9. 745e7f9 Fixing aliasing of iree_hal_memory_type_t bit. by Ben Vanik · 2 years, 3 months ago
  10. 33d2d1b Allowing import of CUDA buffers and improving error messages. by Ben Vanik · 2 years, 3 months ago
  11. eadd749 unpack ukernel (ARM64 code, test, benchmark) + pack improvements (#12055) by bjacob · 2 years, 3 months ago
  12. 21d0808 Add command_buffer_push_constants_test. (#11578) by Scott Todd · 2 years, 3 months ago
  13. 9fed940 Switch args/results to heap allocated storage for VM invocations. (#12045) by Ben Vanik · 2 years, 3 months ago
  14. 1f7702e Adding caching allocator configuration flag handling. by Ben Vanik · 2 years, 3 months ago
  15. a217ef3 Adding iree_hal_caching_allocator_t. by Ben Vanik · 2 years, 4 months ago
  16. c33b7dd Properly erroring out when spilling VM result stack storage. (#12030) by Ben Vanik · 2 years, 3 months ago
  17. e309cb3 Add `--output=` flag to iree-run-module/iree-run-mlir. (#12016) by Ben Vanik · 2 years, 3 months ago
  18. f65c5cb Renaming tool flags to --module/function/input. (#12010) by Ben Vanik · 2 years, 3 months ago
  19. 8bedd4b microkernels: simplify architecture code paths (#12015) by bjacob · 2 years, 3 months ago
  20. e026545 Extending `iree_hal_allocator_t` with memory heaps and compat queries. (#12002) by Ben Vanik · 2 years, 3 months ago
  21. 59f3b61 Check the nccl version compatibility (#12000) by Okwan Kwon · 2 years, 3 months ago
  22. df0db84 fix bad stride in pack_benchmark (#12009) by bjacob · 2 years, 3 months ago
  23. b2e4d2a Fixing runtime flag string lists to not grow exponentially. (#12007) by Ben Vanik · 2 years, 3 months ago
  24. 7ab025c Making iree_hal_allocator_query_buffer_compatibility return params. by Ben Vanik · 2 years, 3 months ago
  25. 77f6d26 Renaming `iree_hal_allocator_query_[+buffer_]compatibility`. by Ben Vanik · 2 years, 3 months ago
  26. 1a323b5 Adding iree_hal_allocator_memory_heap_t + query. by Ben Vanik · 2 years, 4 months ago
  27. 4cd7c8d Disabling CUDA replay stream validation. by Ben Vanik · 2 years, 3 months ago
  28. 29ad1ad Adding parsers for common HAL bitfields. by Ben Vanik · 2 years, 3 months ago
  29. 47d0b7c Adding iree_bitfield_parse utility. by Ben Vanik · 2 years, 3 months ago
  30. b14aaf4 pack microkernel padding improvements (#11987) by bjacob · 2 years, 3 months ago
  31. e513433 Add iree_hal_fence_extend helper. (#11989) by Stella Laurenzo · 2 years, 3 months ago
  32. 2e91d14 Fixing disabled tracing/flags functions ala #11962. (#11965) by Ben Vanik · 2 years, 3 months ago
  33. c170ca3 Removing unused iree/base/internal/main.h. (#11964) by Ben Vanik · 2 years, 3 months ago
  34. ed658db Fix CUDA tracing build in Debug build mode. (#11962) by Scott Todd · 2 years, 3 months ago
  35. 042e2c9 Create spans from non-temporaries. (#11958) by Jacques Pienaar · 2 years, 3 months ago
  36. 9242287 Attaching proper alignment to HAL binding subspans. (#11952) by Ben Vanik · 2 years, 3 months ago
  37. 80b3577 Swapping hal.interface.binding.subspan offset and alignment. by Ben Vanik · 2 years, 3 months ago
  38. f41856b Fixing PDB file naming to match DLL file naming. by Ben Vanik · 2 years, 3 months ago
  39. 0331769 Supporting symbol-relative relocations in the ELF loader. by Ben Vanik · 2 years, 3 months ago
  40. ca9bc42 Adding --task_worker_stack_size= flag and defaulting to 128KB. (#11867) by Ben Vanik · 2 years, 3 months ago
  41. 66fef01 Fixing MSVC compilation error with IREE_TRACE macro in a struct. by Ben Vanik · 2 years, 3 months ago
  42. 6a53867 Adding CUDA device-side tracing support (`--cuda_tracing`). (#11943) by Ben Vanik · 2 years, 3 months ago
  43. 9fa5de7 Enable CUDA (compiler and runtime) by default in CMake builds. (#11832) by Scott Todd · 2 years, 3 months ago
  44. a6de54c Refactor microkernel headers (#11920) by bjacob · 2 years, 3 months ago
  45. 48fa0da Supporting host memory registration in CUDA via external buffers. (#11899) by Ben Vanik · 2 years, 3 months ago
  46. 1006842 Make ukernels assert their validation, remove `iree_uk_status_t`. (#11900) by bjacob · 2 years, 3 months ago
  47. 3c78102 Revert "Supporting host memory registration in CUDA via external buff… (#11895) by Thomas · 2 years, 3 months ago
  48. e5f143f Use nested initializer list for iree_string_pair_t (#11871) by Lei Zhang · 2 years, 3 months ago
  49. 5932920 Discard root tasks before leaf tasks. (#11853) by bjacob · 2 years, 3 months ago
  50. 3c0aaab Supporting host memory registration in CUDA via external buffers. (#11848) by Ben Vanik · 2 years, 3 months ago
  51. c31c8a0 Nccl integration (#11585) by Okwan Kwon · 2 years, 4 months ago
  52. a92999e Use new `IREE_HOST_BIN_DIR` CMake variable in scripts/docs. (#11831) by Scott Todd · 2 years, 4 months ago
  53. 2126488 Adding iree_hal_device_replace_allocator API. (#11809) by Ben Vanik · 2 years, 4 months ago
  54. 0d33d96 Relax the assumption of only one padding tile in `iree_uk_pack` (#11642) by bjacob · 2 years, 4 months ago
  55. 7958fc9 Adding IREE_FLAG_LIST utility for repeated string flags. (#11806) by Ben Vanik · 2 years, 4 months ago
  56. 43f516e Roll forward stateful loop_emscripten changes. (#11801) by Scott Todd · 2 years, 4 months ago
  57. 813d431 Update QueryAvailableDevices to also return path value of device (#11064) by Phaneesh Barwaria · 2 years, 4 months ago
  58. 11c4049 Revert "Make loop_emscripten stateful and allow for multiple instances." (#11799) by Scott Todd · 2 years, 4 months ago
  59. 84d9957 Make loop_emscripten stateful and allow for multiple instances. (#11507) by Scott Todd · 2 years, 4 months ago
  60. 5b9a761 Add a `query_tile_sizes` ukernel. (#11640) by bjacob · 2 years, 4 months ago
  61. aa03d23 [NFC] Cleanup EmitC Conversion (#11793) by Simon Camphausen · 2 years, 4 months ago
  62. 3bb67d3 Reworking task API to provide iree_task_executors_create_from_flags. (#11614) by Ben Vanik · 2 years, 4 months ago
  63. 6a7b8f0 Update pybind11 to 2.10.1 and rebuild Docker images. (#11728) by Scott Todd · 2 years, 4 months ago
  64. c8ee571 Enable some now-passing HAL CTS tests. (#11537) by Scott Todd · 2 years, 4 months ago
  65. b073d4a [NumPy] Remove references to deprecated NumPy type aliases. (#11624) by Geoffrey Martin-Noble · 2 years, 4 months ago
  66. a9d23f6 Overhaul CMake and Bazel CUDA support (#11651) by Stella Laurenzo · 2 years, 4 months ago
  67. 4cf4b5a Support runtime tracing with Tracy in bazel builds. (#11650) by Stella Laurenzo · 2 years, 4 months ago
  68. 68c4ec2 Adding tracy memory pool visualization for Vulkan VMA buffers. (#11622) by Ben Vanik · 2 years, 4 months ago
  69. 830820e Adding tracing annotations for VMA buffer allocation sizes. (#11621) by Ben Vanik · 2 years, 4 months ago
  70. 742cf6a Rename `ukernel/exported_flag_bits` to `exported_bits` (#11609) by bjacob · 2 years, 4 months ago
  71. 41c5c07 Add vmvx.query_tile_sizes op (#11600) by bjacob · 2 years, 4 months ago
  72. 964ce61 Fix implementations of allocators' query_compatibility (#11599) by Ben Vanik · 2 years, 4 months ago
  73. a9aaebe Revert "Integrate NCCL" (#11584) by Ben Vanik · 2 years, 4 months ago
  74. 399adb3 Integrate NCCL (#11481) by Okwan Kwon · 2 years, 4 months ago
  75. a973914 Update some very old TODOs. (#11540) by Scott Todd · 2 years, 5 months ago
  76. fe9cb17 Touch up Python build instructions. (#11424) by Scott Todd · 2 years, 5 months ago
  77. ad23611 Adding plumbing and samples of custom CUDA/SPIR-V/CPU dispatch code. (#11287) by Ben Vanik · 2 years, 5 months ago
  78. 05f29e2 Supporting omitted subgroup sizes when none are needed (from PR #11406). by Ben Vanik · 2 years, 5 months ago
  79. b71aa53 Adds support for HAL executable object linkage. by Ben Vanik · 2 years, 5 months ago
  80. 8b92a9f Adding hal.command_buffer.collective & co runtime imports. by Ben Vanik · 2 years, 6 months ago
  81. 9a1ab32 Adding iree_hal_channel_t and the iree_hal_command_buffer_collective API. by Ben Vanik · 2 years, 5 months ago
  82. fdc340e ukernel tweaks (#11280) by bjacob · 2 years, 5 months ago
  83. 8eff5dd [vulkan] Add support for VK_EXT_subgroup_size_control (#11406) by Lei Zhang · 2 years, 5 months ago
  84. 30356ad Cleanup unused variables from a few build system files. (#11358) by Scott Todd · 2 years, 5 months ago
  85. b79ca72 Fixing race in task wait poller timeout handling. (#11352) by Ben Vanik · 2 years, 5 months ago
  86. bb2ff50 Adding iree_runtime_session_append_bytecode_module_from_stdin util. by Ben Vanik · 2 years, 5 months ago
  87. f7dfda3 Adding iree_hal_buffer_view_create_like helper. by Ben Vanik · 2 years, 5 months ago
  88. 31162eb Adding iree_status_to_string comment from review feedback. by Ben Vanik · 2 years, 5 months ago
  89. 34a5166 Exporting iree_status_to_string. (#11235) by Ben Vanik · 2 years, 5 months ago
  90. 2deecf3 Initial iree_loop_t implementation for web browsers. (#11204) by Scott Todd · 2 years, 5 months ago
  91. 4fd7a1d [docker] More code sharing and use development clang for Bazel builds (#11108) by Geoffrey Martin-Noble · 2 years, 5 months ago
  92. acb2688 Fix layering issues in Bazel build (#11166) by Geoffrey Martin-Noble · 2 years, 5 months ago
  93. 03190c6 initial `unpack` microkernel (#11157) by bjacob · 2 years, 6 months ago
  94. 691ab41 pack ukernel: optimized ARM64 code, benchmark,+refactorings (#11134) by bjacob · 2 years, 6 months ago
  95. a389b9a Some strictness to bring Clang, GCC and MSVC more in line with each other (#11140) by bjacob · 2 years, 6 months ago
  96. 0a6cdf0 Add support for GEMM e2e Test For CUDA backend on F16 input (#10842) by Manish Gupta · 2 years, 6 months ago
  97. c074522 Create Docker images for the latest software (#11083) by Geoffrey Martin-Noble · 2 years, 6 months ago
  98. 8ee5738 Prevent inlining of ukernel elementwise ops into shims. (#11091) by Ben Vanik · 2 years, 6 months ago
  99. c149d61 Adding vm::ref<T> support for non-iree_vm_ref_t ref types. (#11065) by Ben Vanik · 2 years, 6 months ago
  100. da03073 Changing default bytecode dispatch away from computed goto. (#11090) by Ben Vanik · 2 years, 6 months ago