0e9162f | Tzu-Mao Li | 25 November 2019, 22:48:45 UTC | Bring back predicated store/load | 25 November 2019, 22:48:45 UTC |
6f30479 | Steven Johnson | 21 November 2019, 22:02:30 UTC | Merge pull request #4412 from halide/srj-grad Add option to create gradient-descent variant of a Generator | 21 November 2019, 22:02:30 UTC |
93761b5 | Steven Johnson | 21 November 2019, 21:12:13 UTC | Merge pull request #4425 from benoitsteiner/master Bounds tracking for StringImm | 21 November 2019, 21:12:13 UTC |
723ed55 | Benoit Steiner | 21 November 2019, 20:18:47 UTC | Bounds tracking for StringImm | 21 November 2019, 20:18:47 UTC |
a81089f | Steven Johnson | 21 November 2019, 17:42:05 UTC | Merge pull request #4421 from halide/srj-mp Cherrypick some changes from autoscheduler-plugins branch | 21 November 2019, 17:42:05 UTC |
8565db9 | Steven Johnson | 21 November 2019, 02:14:28 UTC | Merge pull request #4420 from benoitsteiner/master Small code simplifications at the beginning of the FunctionDAG constructor | 21 November 2019, 02:14:28 UTC |
5259702 | Steven Johnson | 21 November 2019, 00:25:37 UTC | Allow for things with Derivatives | 21 November 2019, 00:25:37 UTC |
525fda4 | Steven Johnson | 20 November 2019, 23:35:46 UTC | Remove unnecessary fill() | 20 November 2019, 23:35:46 UTC |
a1e261e | Steven Johnson | 20 November 2019, 23:31:50 UTC | Support float16, bfloat | 20 November 2019, 23:31:50 UTC |
a6b2c15 | Steven Johnson | 20 November 2019, 23:22:13 UTC | Use correct bounds for propagate_adjoint | 20 November 2019, 23:22:13 UTC |
b27923b | Steven Johnson | 20 November 2019, 22:26:49 UTC | Update Pipeline.cpp | 20 November 2019, 22:26:49 UTC |
0332911 | Steven Johnson | 20 November 2019, 22:24:46 UTC | Cherrypick some changes from autoscheduler-plugins branch - move MachineParams from AutoSchedule.h to PIpeline.h - move some helper functions from AutoSchedule.h to AutoScheduleUtils.h - minor compilation fix in HalideBuffer.h | 20 November 2019, 22:24:46 UTC |
5e999ca | Benoit Steiner | 20 November 2019, 22:18:05 UTC | Improved formatting of the code | 20 November 2019, 22:18:05 UTC |
5194280 | Benoit Steiner | 20 November 2019, 20:25:41 UTC | Small code simplifications at the beginning of the FunctionDAG constructor: Avoid setting node.func in two separate locations. The second initialization is redundant and confusing Streamlined the initialization of node.stages by avoiding extra stage creation and movements. Also applied clang-format, which accounts for all the other code changes | 20 November 2019, 20:25:41 UTC |
ec9d85b | Steven Johnson | 20 November 2019, 19:19:25 UTC | Merge pull request #4404 from vksnk/opencl-build-opt Adds the ability to pass extra build options for OpenCL kernels. | 20 November 2019, 19:19:25 UTC |
747ab36 | Steven Johnson | 20 November 2019, 19:18:12 UTC | Merge pull request #4414 from benoitsteiner/master Split the code from AutoSchedule.cpp in two files: | 20 November 2019, 19:18:12 UTC |
5827901 | Benoit Steiner | 20 November 2019, 01:28:06 UTC | Fixed the order of the #includes | 20 November 2019, 01:28:06 UTC |
58053ef | Benoit Steiner | 20 November 2019, 01:22:49 UTC | Improved formatting of the code and deleted dead code. | 20 November 2019, 01:22:49 UTC |
4331a6f | Benoit Steiner | 20 November 2019, 01:17:28 UTC | Updated the CMake file to compile LoopNest.cpp when needed | 20 November 2019, 01:17:28 UTC |
310a5b3 | Steven Johnson | 19 November 2019, 23:39:57 UTC | Merge pull request #4408 from timo-zeiss-research/host_dirty_on_device_malloc Bugfix: Empty device buffer on corner case | 19 November 2019, 23:39:57 UTC |
7a57d2d | Steven Johnson | 19 November 2019, 23:13:43 UTC | Merge pull request #4415 from ashishUthama/master Use std::abs instead of abs to prevent ambigious match | 19 November 2019, 23:13:43 UTC |
64b4ee0 | Benoit Steiner | 19 November 2019, 22:07:56 UTC | Moved most of the implementation of the methods of the LoopNest class to LoopNest.cpp | 19 November 2019, 22:07:56 UTC |
3f15919 | Ashish Uthama | 19 November 2019, 21:04:34 UTC | Use std::abs instead of abs to prevent ambigious match | 19 November 2019, 21:04:34 UTC |
1dfe998 | Benoit Steiner | 19 November 2019, 19:39:35 UTC | Applied clang-format to LoopNest.h | 19 November 2019, 19:39:35 UTC |
493b6f3 | Benoit Steiner | 19 November 2019, 19:33:36 UTC | Split the code from AutoSchedule.cpp in 2: * the beam search part of the code itself remains in AutoSchedule.cpp * The generation of valide candidate to search over as well as their featurization moved to LoopNest.h This will enable the development of new search strategies without having to duplicate all the code that now resides in LoopNest.h | 19 November 2019, 19:33:36 UTC |
61a8590 | Steven Johnson | 19 November 2019, 18:50:30 UTC | Update autograd_aottest.cpp | 19 November 2019, 18:50:30 UTC |
2a98c69 | Timo Stich | 19 November 2019, 14:36:18 UTC | Mark all outputs as host_dirty, even in pipelines where the target doesn't contain a GPU feature. | 19 November 2019, 14:37:40 UTC |
56a8b2a | Steven Johnson | 19 November 2019, 01:40:52 UTC | fixes | 19 November 2019, 01:40:52 UTC |
96ba53e | Steven Johnson | 19 November 2019, 01:21:17 UTC | Update Makefile | 19 November 2019, 01:21:17 UTC |
e1e9273 | Steven Johnson | 19 November 2019, 01:14:14 UTC | C | 19 November 2019, 01:14:14 UTC |
419ba0c | Steven Johnson | 18 November 2019, 23:40:09 UTC | gradient-descent generator | 18 November 2019, 23:40:09 UTC |
79a7e62 | Volodymyr Kysenko | 18 November 2019, 22:16:25 UTC | Move test to test/correctness | 18 November 2019, 22:16:25 UTC |
d17a0e7 | Volodymyr Kysenko | 18 November 2019, 21:17:30 UTC | Add test for OpenCL runtime functions. | 18 November 2019, 21:17:30 UTC |
0e0c6a2 | Steven Johnson | 18 November 2019, 18:05:54 UTC | Merge pull request #4406 from halide/srj-pytorch-1.3 Update PyTorch support to work with v1.3 | 18 November 2019, 18:05:54 UTC |
f07b12c | Steven Johnson | 18 November 2019, 18:05:37 UTC | Update HalidePyTorchHelpers.h | 18 November 2019, 18:05:37 UTC |
fe14cb4 | Steven Johnson | 18 November 2019, 18:02:05 UTC | Merge pull request #4403 from halide/srj-wasm2 Update WebAssembly support | 18 November 2019, 18:02:05 UTC |
ac91d35 | Dillon Sharlet | 15 November 2019, 21:22:24 UTC | Merge pull request #4104 from aankit-ca/lut32 [Hexagon] LUT32 implementation using lut16 | 15 November 2019, 21:22:24 UTC |
4bb6aee | Steven Johnson | 15 November 2019, 19:25:35 UTC | Merge branch 'master' into srj-pytorch-1.3 | 15 November 2019, 19:25:35 UTC |
f99face | Steven Johnson | 15 November 2019, 19:24:55 UTC | Merge branch 'master' into srj-wasm2 | 15 November 2019, 19:24:55 UTC |
6156f32 | Steven Johnson | 15 November 2019, 19:24:03 UTC | Merge pull request #4399 from halide/tzumao-gradient-autoscheduler-bug Fix gradient autoscheduler's usage of output estimates | 15 November 2019, 19:24:03 UTC |
4b7054c | Steven Johnson | 15 November 2019, 19:23:25 UTC | Merge pull request #4384 from halide/pdb_mul_div_mod_multi_thread Revert PR #4336 | 15 November 2019, 19:23:25 UTC |
7f34940 | Volodymyr Kysenko | 15 November 2019, 01:43:28 UTC | Actually just set last element to null | 15 November 2019, 01:43:28 UTC |
0c1de62 | Steven Johnson | 15 November 2019, 01:36:28 UTC | Merge branch 'master' into tzumao-gradient-autoscheduler-bug | 15 November 2019, 01:36:28 UTC |
32e78c8 | Steven Johnson | 15 November 2019, 01:36:12 UTC | Merge branch 'master' into srj-wasm2 | 15 November 2019, 01:36:12 UTC |
7db5898 | Volodymyr Kysenko | 14 November 2019, 23:28:55 UTC | Lock _set_ functions as well | 14 November 2019, 23:28:55 UTC |
7fb4037 | Volodymyr Kysenko | 14 November 2019, 23:04:41 UTC | Make sure that strings are null-terminated | 14 November 2019, 23:04:41 UTC |
f829580 | Volodymyr Kysenko | 14 November 2019, 22:03:52 UTC | Add halide_opencl_get_build_options/halide_opencl_set_build_options functions | 14 November 2019, 22:03:52 UTC |
04ec9c0 | Steven Johnson | 14 November 2019, 20:17:17 UTC | Merge branch 'master' into pdb_mul_div_mod_multi_thread | 14 November 2019, 20:17:17 UTC |
accfaf8 | Steven Johnson | 14 November 2019, 19:02:27 UTC | Merge branch 'master' into srj-pytorch-1.3 | 14 November 2019, 19:02:27 UTC |
08bd367 | Steven Johnson | 14 November 2019, 17:49:04 UTC | Merge pull request #4405 from halide/srj-llvmfix Update for trunk LLVM API changes | 14 November 2019, 17:49:04 UTC |
64c21d8 | Steven Johnson | 14 November 2019, 02:30:15 UTC | Merge branch 'master' into srj-llvmfix | 14 November 2019, 02:30:15 UTC |
58277ba | Steven Johnson | 14 November 2019, 02:29:50 UTC | Merge pull request #4400 from halide/srj-llvm-git LLVM fixes (draft) | 14 November 2019, 02:29:50 UTC |
c0f6a32 | Steven Johnson | 14 November 2019, 02:27:39 UTC | typo | 14 November 2019, 02:27:39 UTC |
3d877e2 | Steven Johnson | 14 November 2019, 02:16:44 UTC | Update PyTorch support to work with v1.3 | 14 November 2019, 02:16:44 UTC |
da732f4 | Steven Johnson | 14 November 2019, 01:39:43 UTC | Update for trunk LLVM API changes | 14 November 2019, 01:39:43 UTC |
54c0f95 | Volodymyr Kysenko | 14 November 2019, 00:24:16 UTC | Adds the ability to pass extra build options for OpenCL kernels. | 14 November 2019, 00:24:16 UTC |
e2dfef3 | Steven Johnson | 14 November 2019, 00:09:51 UTC | Merge branch 'master' into tzumao-gradient-autoscheduler-bug | 14 November 2019, 00:09:51 UTC |
4057b85 | Steven Johnson | 13 November 2019, 23:11:59 UTC | Update WebAssembly support - require V8 7.5 as baseline (rather than 7.3) - add half-float glue code - blacklist correctness_atomics from wasm testing - Update readme | 13 November 2019, 23:11:59 UTC |
7f73523 | Steven Johnson | 13 November 2019, 22:54:48 UTC | Merge branch 'master' into pdb_mul_div_mod_multi_thread | 13 November 2019, 22:54:48 UTC |
4e4bb48 | Steven Johnson | 13 November 2019, 22:44:03 UTC | Merge pull request #4395 from halide/srj-llvm Update README for LLVM build instructions (Issue #4394) | 13 November 2019, 22:44:03 UTC |
b3631fd | Steven Johnson | 13 November 2019, 22:43:30 UTC | Merge branch 'master' into srj-llvm-git | 13 November 2019, 22:43:30 UTC |
afd9f4d | Steven Johnson | 13 November 2019, 22:18:52 UTC | Merge pull request #4391 from halide/srj-onnx-cast avoid reinterpret_cast in onnx_converter | 13 November 2019, 22:18:52 UTC |
b22d4f6 | Volodymyr Kysenko | 13 November 2019, 20:18:18 UTC | Fix typo | 13 November 2019, 20:18:18 UTC |
ee4fbb9 | Steven Johnson | 13 November 2019, 18:22:08 UTC | Merge branch 'master' into pdb_mul_div_mod_multi_thread | 13 November 2019, 18:22:08 UTC |
d3031ab | Steven Johnson | 13 November 2019, 18:19:41 UTC | Merge branch 'master' into tzumao-gradient-autoscheduler-bug | 13 November 2019, 18:19:41 UTC |
59b616f | Steven Johnson | 13 November 2019, 18:18:18 UTC | Update README.md | 13 November 2019, 18:18:18 UTC |
72994e0 | Steven Johnson | 13 November 2019, 18:13:23 UTC | Merge pull request #4401 from vksnk/fix-doc Fix comment on how to build tutorial_lesson_05 with make | 13 November 2019, 18:13:23 UTC |
291bc72 | Steven Johnson | 13 November 2019, 01:20:42 UTC | Merge branch 'master' into pdb_mul_div_mod_multi_thread | 13 November 2019, 01:20:42 UTC |
64ffb4e | Volodymyr Kysenko | 13 November 2019, 00:57:11 UTC | Fix comment | 13 November 2019, 00:57:11 UTC |
a5621ec | Steven Johnson | 12 November 2019, 23:34:39 UTC | Merge pull request #4398 from halide/srj-simd Fix set_host_alignment() in simd_op_check | 12 November 2019, 23:34:39 UTC |
b962486 | Steven Johnson | 12 November 2019, 23:27:23 UTC | Update Makefile | 12 November 2019, 23:27:23 UTC |
cad4b23 | Tzu-Mao Li | 12 November 2019, 22:06:08 UTC | add test | 12 November 2019, 22:06:08 UTC |
99397c4 | Tzu-Mao Li | 12 November 2019, 21:42:25 UTC | undo some changes | 12 November 2019, 21:42:25 UTC |
34c628a | Tzu-Mao Li | 12 November 2019, 21:39:29 UTC | Fix gradient autoscheduler's usage of output estimates | 12 November 2019, 21:39:29 UTC |
e70e688 | Steven Johnson | 12 November 2019, 19:31:55 UTC | Update simd_op_check.h | 12 November 2019, 19:31:55 UTC |
47d70d1 | Steven Johnson | 12 November 2019, 19:18:05 UTC | Update simd_op_check_hvx.cpp | 12 November 2019, 19:18:05 UTC |
8777450 | Steven Johnson | 12 November 2019, 18:54:41 UTC | Fix set_host_alignment() in simd_op_check We have been calling set_host_alignment(128) on our input params for ~ever, but this has always been wrong; as the argument is in bytes (not bits), and most of our targets provide only a 32-byte guarantee at the memory allocator level (x86 does 64-bytes, see LLVM_Runtime_Linker.cpp) (Note that I'm not sure if the _hvx variant really should be 128 bytes or not, please review carefully.) | 12 November 2019, 18:54:41 UTC |
a47d58e | Steven Johnson | 12 November 2019, 01:59:27 UTC | Merge pull request #4389 from halide/srj-ub Fix UB in Halide::Runtime::Buffer<>::size_in_bytes() | 12 November 2019, 01:59:27 UTC |
fd3da4d | Steven Johnson | 12 November 2019, 01:50:58 UTC | Update README for LLVM build instructions (Issue #4394) | 12 November 2019, 01:50:58 UTC |
53bb8ef | Steven Johnson | 11 November 2019, 23:24:33 UTC | avoid reinterpret_cast in onnx_converter | 11 November 2019, 23:26:21 UTC |
568ddfc | Steven Johnson | 11 November 2019, 21:48:42 UTC | Fix UB in Halide::Runtime::Buffer<>::size_in_bytes() | 11 November 2019, 21:48:42 UTC |
f60b8d2 | Steven Johnson | 06 November 2019, 22:02:38 UTC | Merge pull request #4383 from halide/srj-pt Misc minor PyTorch cleanups | 06 November 2019, 22:02:38 UTC |
50f6f92 | Steven Johnson | 06 November 2019, 18:14:37 UTC | Merge branch 'master' into pdb_mul_div_mod_multi_thread | 06 November 2019, 18:14:37 UTC |
d4aace9 | Steven Johnson | 06 November 2019, 18:13:08 UTC | Merge pull request #4380 from aankit-ca/offload_autosched_results Fix offload mode autoscheduler results. | 06 November 2019, 18:13:08 UTC |
aab0cd3 | Shubham Pawar | 06 November 2019, 16:11:05 UTC | Add null pointer check for results Check if autoscheduler results are present before copying to the lowered module after resolving submodules. | 06 November 2019, 16:11:05 UTC |
1f0179b | Pranav Bhandarkar | 06 November 2019, 00:33:02 UTC | Revert "Add default constexpr constructor to ImplicitVar because Clang complaints about it" This reverts commit 9ff00ffe4ed0f2d476ba974ce1bad15bd70d9390. | 06 November 2019, 00:33:02 UTC |
d76fa09 | Pranav Bhandarkar | 06 November 2019, 00:21:08 UTC | Revert PR #4336 as underlying issue in LLVM has been addressed by LLVM commit 041f35c Link - https://github.com/llvm/llvm-project/commit/041f35c468088d315bae6c2a71ec901a12cca1b5 | 06 November 2019, 00:27:22 UTC |
6104128 | Steven Johnson | 06 November 2019, 00:12:31 UTC | Misc minor PyTorch cleanups - remove no-longer-needed .gitignore - trim all trailing blank space - add estimates to add_generator.cpp - Codegen_PyTorch declares the `_th_` functions as `inline` | 06 November 2019, 00:12:31 UTC |
befed33 | Pranav Bhandarkar | 06 November 2019, 00:04:24 UTC | Merge branch 'master' of https://github.com/halide/Halide | 06 November 2019, 00:04:24 UTC |
f2062aa | Shubham Pawar | 05 November 2019, 22:30:58 UTC | Fix offload mode autoscheduler results. Currently, when autoscheduler is invoked in offload mode, the the emit options {featurization and schedule} are not working as expected and bailing out due to auto_scheduler_results not present in the lowered module, resulting in empty feature and schedule files produced. This happens because, when offloaded submodules are recursively resolved, the autoscheduler results are not copied back into the lowered module. This change fixes this issue by setting back the auto_scheduler_results in the ModuleContents of the module that is lowered after resolving submodules. | 05 November 2019, 22:58:31 UTC |
d10ca19 | Steven Johnson | 05 November 2019, 21:37:47 UTC | Merge pull request #4373 from halide/srj-pytorch Fix OSX+Homebrew+Python issue for HelloPyTorch | 05 November 2019, 21:37:47 UTC |
ce5b510 | Steven Johnson | 04 November 2019, 17:06:56 UTC | Merge pull request #4375 from halide/srj-fix ScheduleFeatures::num_features() and PipelineFeatures::num_features()… | 04 November 2019, 17:06:56 UTC |
e3055e9 | Steven Johnson | 01 November 2019, 23:06:46 UTC | ScheduleFeatures::num_features() and PipelineFeatures::num_features() should return size_t (Issue #4371) | 01 November 2019, 23:06:46 UTC |
893d986 | Steven Johnson | 01 November 2019, 22:21:04 UTC | Merge pull request #4374 from halide/srj-mangle Fix name-mangling [u]int64 on IOS | 01 November 2019, 22:21:04 UTC |
0f32df5 | Steven Johnson | 01 November 2019, 22:20:49 UTC | Add iOS test cases for mangling | 01 November 2019, 22:20:49 UTC |
c2a46b7 | Steven Johnson | 01 November 2019, 20:23:47 UTC | Fix name-mangling [u]int64 on IOS The iOS SDK defines int64 as `long long` and uint64 as `unsigned long long`, but we are currently mangling them as `long` and `unsigned long`, so we will get linker errors for compiled filters that use one of these types as an input (assuming c_plus_plus_name_mangling is enabled). | 01 November 2019, 20:23:47 UTC |
3144e6e | Ankit Aggarwal | 01 November 2019, 17:47:25 UTC | [Hexagon] LUT32 implementation using lut16. Remove unused variable. | 01 November 2019, 17:47:25 UTC |
149153f | Ankit Aggarwal | 01 November 2019, 15:17:28 UTC | Merge branch 'master' into lut32 | 01 November 2019, 15:17:28 UTC |
e035032 | Ankit Aggarwal | 01 November 2019, 10:17:56 UTC | [Hexagon] LUT32 implementation using lut16. - Change IRBuilder to intrinsics - Fix failing test/correctness/gather.cpp | 01 November 2019, 10:17:56 UTC |
38bde2e | Steven Johnson | 01 November 2019, 00:39:40 UTC | Makefile reformatting | 01 November 2019, 00:39:40 UTC |