Google Git
Sign in
opensecura / 3p / openxla / iree / 886ac3e269454180b149abd68e230ca079a3744a / tests
  1. cc71082 Bump Tint to latest. (#12527) by Scott Todd · 2 years, 1 month ago
  2. 70e6e52 Add additional options to the ApplyPatternsOp (#12519) by Nicolas Vasilache · 2 years, 1 month ago
  3. 84b4802 Fully retire CanonicalizedSequenceOp (#12467) by Nicolas Vasilache · 2 years, 1 month ago
  4. 769ffda Evolve transform dialect usage towards non-blanket-canonicalized sequences (#12465) by Nicolas Vasilache · 2 years, 1 month ago
  5. 91e73d3 Adding requirement bits to bytecode modules and bumping version. by Ben Vanik · 2 years, 1 month ago
  6. aac4d64 Avoid hardcoded architecture in CPU test (#12488) by Lei Zhang · 2 years, 1 month ago
  7. 5740497 Rename IREE_BUILD_EXPERIMENTAL_E2E_TEST_ARTIFACTS to IREE_BUILD_E2E_TEST_ARTIFACTS (#12469) by Jerry Wu · 2 years, 1 month ago
  8. a2350a3 Fix the compile flags for FP16 on Mali in new benchmarks (#12448) by Jerry Wu · 2 years, 1 month ago
  9. 17eafc9 [LLVMGPU] Enable tensor.pack op e2e execution on cuda. (#12370) by Han-Chung Wang · 2 years, 1 month ago
  10. 5b7de27 [vulkan][spirv] Disable `reverse` tests failing on Pixel 6 (#12416) by Jakub Kuderski · 2 years, 1 month ago
  11. 4a65a33 Retire most of LinalgExt::(Un)PackOp usages and transformations. (#12253) by Han-Chung Wang · 2 years, 1 month ago
  12. 4a8d063 Drop the tensor.pack/unpack -> LinalgExt lowering from transform dialect (#12401) by Han-Chung Wang · 2 years, 1 month ago
  13. 0246bbf Dump run and compile flags into benchmark JSON config (#12397) by Jerry Wu · 2 years, 1 month ago
  14. e2cfc99 Fix e2e test artifacts to use composite id (#12388) by Jerry Wu · 2 years, 1 month ago
  15. c7b2912 Update references from `iree-org` to `openxla`. (#12304) by Scott Todd · 2 years, 1 month ago
  16. 5c2172c Added ComplexToStandardPass to the LLVM compilation pipelines (#12273) by Rob Suderman · 2 years, 1 month ago
  17. ad8782e Integrate llvm/llvm-project@eb141867 (#12264) by Lei Zhang · 2 years, 1 month ago
  18. 425efcd Fix device_allocator option in new benchmark suite (#12223) by Jerry Wu · 2 years, 1 month ago
  19. 261471c Plumb vector to mma.sync through the transform dialect (#12244) by Nicolas Vasilache · 2 years, 1 month ago
  20. 42b79af Add EfficientNet and PersonDetect int8 to Mali benchmarks (#12224) by Jakub Kuderski · 2 years, 1 month ago
  21. 3a91bd8 Replace `zve32x` with `zve32f` in CI configurations (#12185) by Diego Caballero · 2 years, 1 month ago
  22. 34b2f7f Add BertLargeTF to the new benchmark suite (#12170) by Jerry Wu · 2 years, 1 month ago
  23. b02dfa9 Plumb e2e tensor.(un)pack support through VMVX and microkernels. (#12133) by Han-Chung Wang · 2 years, 1 month ago
  24. b78340f Add Bert-Large to x86 and CUDA benchmarks (#12032) by mariecwhite · 2 years, 2 months ago
  25. da263ba Plumb through tensor.unpack e2e execution for llvm-cpu backend. (#12121) by Han-Chung Wang · 2 years, 2 months ago
  26. 1d76929 Revert commits following a bad test deactivation (#12147) by Nicolas Vasilache · 2 years, 2 months ago
  27. 57b174c Deactivate attention.mlir to mitigate blocking #12129 broken at HEAD (#12143) by Nicolas Vasilache · 2 years, 2 months ago
  28. bc7ff41 Fix vulkan triplet and valhall architecture in benchmark framework (#12139) by Jerry Wu · 2 years, 2 months ago
  29. 5b727bc Add option to compiler to Preprocessing step. (#12140) by MaheshRavishankar · 2 years, 2 months ago
  30. a511be1 Run 'emscripten' CI job on presubmit. (#12081) by Scott Todd · 2 years, 2 months ago
  31. c691b20 Disable some linalg_ext_ops tests on Emscripten while failing. (#12127) by Scott Todd · 2 years, 2 months ago
  32. 1e89706 Enable tensor_ops/ tests on VMVX backend. (#12118) by Han-Chung Wang · 2 years, 2 months ago
  33. bd01143 Plumb through tensor.pack e2e execution for llvm-cpu backend. (#11875) by Han-Chung Wang · 2 years, 2 months ago
  34. def748f Undo special-case 1x1 tiling for VMVX (#12061) by bjacob · 2 years, 2 months ago
  35. 537b07c Add an example of generalized packing (#12076) by Nicolas Vasilache · 2 years, 2 months ago
  36. 9691c91 Functional support mma.sync.1688.f32.tf32 for F32 datatype (#12054) by Manish Gupta · 2 years, 2 months ago
  37. 8abd1bd Integrate LLVM at llvm/llvm-project@7d3a181c (#12047) by Thomas · 2 years, 2 months ago
  38. 321df7e Replace `riscv-v-vector-bits-min` with `+zvl*b` in RISC-V configs (#12037) by Diego Caballero · 2 years, 2 months ago
  39. 6a59ff6 Fix processing of preprocessing flags. (#12029) by MaheshRavishankar · 2 years, 2 months ago
  40. f65c5cb Renaming tool flags to --module/function/input. (#12010) by Ben Vanik · 2 years, 2 months ago
  41. b2e4d2a Fixing runtime flag string lists to not grow exponentially. (#12007) by Ben Vanik · 2 years, 2 months ago
  42. 1428941 Add a `--iree-preprocessing-pass-pipeline` to allow user control on preprocessing passes before IREE compilation. (#11986) by MaheshRavishankar · 2 years, 2 months ago
  43. 5f6f989 Fixup tests/e2e/linalg/ test definitions. (#11990) by Scott Todd · 2 years, 2 months ago
  44. 8773676 Add attention op to linalg_ext (#11928) by harsh-nod · 2 years, 2 months ago
  45. fafde87 Flip the switch to turn on the transform dialect by default. (#11737) by Nicolas Vasilache · 2 years, 2 months ago
  46. 80b3577 Swapping hal.interface.binding.subspan offset and alignment. by Ben Vanik · 2 years, 2 months ago
  47. acd5e6b Pull in the rematerialization pass into CPU lowering pipeline. (#11940) by MaheshRavishankar · 2 years, 2 months ago
  48. 52c5d14 Add a more controllable ShareForeachThreadOperandsOp (#11915) by Nicolas Vasilache · 2 years, 2 months ago
  49. 2231682 Adds Native Tensor Core (F16) Support [mma.sync.16816.f16.f16 and ldmatrix] (#11817) by Manish Gupta · 2 years, 2 months ago
  50. 190885e Fix and re-enable cuda transform dialect tests (#11925) by Thomas · 2 years, 2 months ago
  51. 837151d Integrate llvm-project at https://github.com/llvm/llvm-project/commit/9936064d6677 (#11891) by MaheshRavishankar · 2 years, 2 months ago
  52. 1e907e8 Add softmax op to linalg_ext (#11911) by harsh-nod · 2 years, 2 months ago
  53. a922768 Generate `non-coherent cache` loads and `noalias` for CUDA (#11494) by Guray Ozen · 2 years, 2 months ago
  54. db085cc [NFC] Split rank_reducing patterns in transform dialect. (#11892) by Thomas · 2 years, 2 months ago
  55. 91c1df6 Fix ID format in benchmark framework (#11890) by Jerry Wu · 2 years, 2 months ago
  56. 548ff96 Sync RISC-V benchmark definitions (#11856) by Jerry Wu · 2 years, 2 months ago
  57. 1185334 Cullen's fix for 16bit shifts in VMVX (#11826) by bjacob · 2 years, 2 months ago
  58. 3dd670f Switch e2e/matmul tests on vmvx+ukernel to data-tiling (#11522) by bjacob · 2 years, 3 months ago
  59. badd598 Integrate llvm-project at 3589885d82b6 and bump submodules (#11781) by Han-Chung Wang · 2 years, 3 months ago
  60. 7e3847a [LLVMGPU] Support aggressive fusion (#11747) by Thomas · 2 years, 3 months ago
  61. 37983c6 Introduce Collapse Pass (#11713) by Guray Ozen · 2 years, 3 months ago
  62. a81c3cf [Transform] Fix CPU reduction strategy and uniformize code across bac… (#11760) by Nicolas Vasilache · 2 years, 3 months ago
  63. 5435fc1 Integrate llvm-project and bump dependencies. (#11741) by Manish Gupta · 2 years, 3 months ago
  64. 03a114c [Transform] Drop transform stub test file (#11669) by Nicolas Vasilache · 2 years, 3 months ago
  65. 674297e Fix performance bugs and add a benchmarking stub (#11597) by Nicolas Vasilache · 2 years, 3 months ago
  66. fb87ad1 Generate compile statistics modules in e2e test artifacts (#11572) by Jerry Wu · 2 years, 3 months ago
  67. e20bcb4 Cherry-pick llvm-project changes and fix #11586 (#11595) by Matthias Springer · 2 years, 3 months ago
  68. 79b90d3 Integrate llvm/llvm-project@4bb85698d69c (#11576) by Lei Zhang · 2 years, 3 months ago
  69. 79df77c Limit tiling sizes for unpack op kernels (#11503) by Han-Chung Wang · 2 years, 3 months ago
  70. 1f98cc5 Collapse `linalg.generic` (#11295) by Guray Ozen · 2 years, 3 months ago
  71. 2d91b37 Cherry-pick and use subview folding pattern (#11582) by Matthias Springer · 2 years, 3 months ago
  72. 891ca02 CanonicalizedSequenceOp: Do not hoist buffer transfers (#11580) by Matthias Springer · 2 years, 3 months ago
  73. f55f292 Integrate llvm-project and bump dependencies 20221213 (#11552) by Okwan Kwon · 2 years, 3 months ago
  74. 2327aeb Port reduction-v3 to C++ (#11539) by Nicolas Vasilache · 2 years, 4 months ago
  75. 289e8de Split iree.bufferize_op to enable additional canonicalization (#11570) by Matthias Springer · 2 years, 4 months ago
  76. 1f5d7ab Enable rank_reducing patterns in reduction_v3_codegen_spec (#11569) by Matthias Springer · 2 years, 4 months ago
  77. d16b02f Add Winograd support for NCHW convolutions (#11475) by harsh-nod · 2 years, 4 months ago
  78. 628af76 Use better Linalg transform op builders (#11551) by Nicolas Vasilache · 2 years, 4 months ago
  79. e919b8b Emit better reduction schedule from JIT (#11548) by Nicolas Vasilache · 2 years, 4 months ago
  80. ee167be Relax block size constraints: dynamic reduction-v3 @peak (#11547) by Nicolas Vasilache · 2 years, 4 months ago
  81. 33b994b Add a reduction-v3 strategy for dynamic cases. (#11546) by Nicolas Vasilache · 2 years, 4 months ago
  82. a973914 Update some very old TODOs. (#11540) by Scott Todd · 2 years, 4 months ago
  83. ddbd2fd Enable a few tests that are passing now. (#11541) by Scott Todd · 2 years, 4 months ago
  84. cc0c10c Integrate llvm/llvm-project@32cc7d349750 (#11506) by Lei Zhang · 2 years, 4 months ago
  85. 528366e Use single-level directory for e2e test artifacts (#11511) by Jerry Wu · 2 years, 4 months ago
  86. 85ff57f [NFC] Canonicalize the "platform" in CI (#11413) by Jerry Wu · 2 years, 4 months ago
  87. 8325361 Plumb e2e support for packing on dynamic inner tiles. (#11487) by Han-Chung Wang · 2 years, 4 months ago
  88. fc0442f Fixes necessary to enable const hoisting and eval. (#11440) by Stella Laurenzo · 2 years, 4 months ago
  89. 7f36706 Re-organize transform dialect codegen tests (#11473) by Thomas · 2 years, 4 months ago
  90. d3b3cc1 Fix bug in tile_to_foreach_thread mapping computation (#11312) by Matthias Springer · 2 years, 4 months ago
  91. 849e227 [vulkan] Enable MobileBERT i8 benchmark on Mali (#11464) by Jakub Kuderski · 2 years, 4 months ago
  92. 8e0022d Split `iree-dispatch-linalg-on-tensors-pass` into two (#11313) by Guray Ozen · 2 years, 4 months ago
  93. 52c2e35 Relands "Switch e2e tests and benchmarks to `--iree-flow-enable-data-tiling` on `llvm-cpu`" (#11443) by Han-Chung Wang · 2 years, 4 months ago
  94. 0573f4f Transform dialect bringup (#11422) by Nicolas Vasilache · 2 years, 4 months ago
  95. 01cf67a Add e2e tests for winograd (#11428) by harsh-nod · 2 years, 4 months ago
  96. b3fa021 Revert "Switch e2e tests and benchmarks to `--iree-flow-enable-data-tiling` on `llvm-cpu`" (#11435) by Jerry Wu · 2 years, 4 months ago
  97. c781d6a Re-enabling cuda's split-k test (#11431) by Murali Vijayaraghavan · 2 years, 4 months ago
  98. 044017f Switch e2e tests and benchmarks to `--iree-flow-enable-data-tiling` on `llvm-cpu` (#11411) by bjacob · 2 years, 4 months ago
  99. 895cf38 [spirv] Add support for Winograd output op (#11409) by harsh-nod · 2 years, 4 months ago
  100. a06805f Improve generated cmake files verification and update lint.sh (#11381) by Jerry Wu · 2 years, 4 months ago