https://github.com/halide/Halide

sort by:
Revision Author Date Message Commit Date
0e9162f Bring back predicated store/load 25 November 2019, 22:48:45 UTC
6f30479 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 Merge pull request #4425 from benoitsteiner/master Bounds tracking for StringImm 21 November 2019, 21:12:13 UTC
723ed55 Bounds tracking for StringImm 21 November 2019, 20:18:47 UTC
a81089f Merge pull request #4421 from halide/srj-mp Cherrypick some changes from autoscheduler-plugins branch 21 November 2019, 17:42:05 UTC
8565db9 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 Allow for things with Derivatives 21 November 2019, 00:25:37 UTC
525fda4 Remove unnecessary fill() 20 November 2019, 23:35:46 UTC
a1e261e Support float16, bfloat 20 November 2019, 23:31:50 UTC
a6b2c15 Use correct bounds for propagate_adjoint 20 November 2019, 23:22:13 UTC
b27923b Update Pipeline.cpp 20 November 2019, 22:26:49 UTC
0332911 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 Improved formatting of the code 20 November 2019, 22:18:05 UTC
5194280 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 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 Merge pull request #4414 from benoitsteiner/master Split the code from AutoSchedule.cpp in two files: 20 November 2019, 19:18:12 UTC
5827901 Fixed the order of the #includes 20 November 2019, 01:28:06 UTC
58053ef Improved formatting of the code and deleted dead code. 20 November 2019, 01:22:49 UTC
4331a6f Updated the CMake file to compile LoopNest.cpp when needed 20 November 2019, 01:17:28 UTC
310a5b3 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 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 Moved most of the implementation of the methods of the LoopNest class to LoopNest.cpp 19 November 2019, 22:07:56 UTC
3f15919 Use std::abs instead of abs to prevent ambigious match 19 November 2019, 21:04:34 UTC
1dfe998 Applied clang-format to LoopNest.h 19 November 2019, 19:39:35 UTC
493b6f3 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 Update autograd_aottest.cpp 19 November 2019, 18:50:30 UTC
2a98c69 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 fixes 19 November 2019, 01:40:52 UTC
96ba53e Update Makefile 19 November 2019, 01:21:17 UTC
e1e9273 C 19 November 2019, 01:14:14 UTC
419ba0c gradient-descent generator 18 November 2019, 23:40:09 UTC
79a7e62 Move test to test/correctness 18 November 2019, 22:16:25 UTC
d17a0e7 Add test for OpenCL runtime functions. 18 November 2019, 21:17:30 UTC
0e0c6a2 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 Update HalidePyTorchHelpers.h 18 November 2019, 18:05:37 UTC
fe14cb4 Merge pull request #4403 from halide/srj-wasm2 Update WebAssembly support 18 November 2019, 18:02:05 UTC
ac91d35 Merge pull request #4104 from aankit-ca/lut32 [Hexagon] LUT32 implementation using lut16 15 November 2019, 21:22:24 UTC
4bb6aee Merge branch 'master' into srj-pytorch-1.3 15 November 2019, 19:25:35 UTC
f99face Merge branch 'master' into srj-wasm2 15 November 2019, 19:24:55 UTC
6156f32 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 Merge pull request #4384 from halide/pdb_mul_div_mod_multi_thread Revert PR #4336 15 November 2019, 19:23:25 UTC
7f34940 Actually just set last element to null 15 November 2019, 01:43:28 UTC
0c1de62 Merge branch 'master' into tzumao-gradient-autoscheduler-bug 15 November 2019, 01:36:28 UTC
32e78c8 Merge branch 'master' into srj-wasm2 15 November 2019, 01:36:12 UTC
7db5898 Lock _set_ functions as well 14 November 2019, 23:28:55 UTC
7fb4037 Make sure that strings are null-terminated 14 November 2019, 23:04:41 UTC
f829580 Add halide_opencl_get_build_options/halide_opencl_set_build_options functions 14 November 2019, 22:03:52 UTC
04ec9c0 Merge branch 'master' into pdb_mul_div_mod_multi_thread 14 November 2019, 20:17:17 UTC
accfaf8 Merge branch 'master' into srj-pytorch-1.3 14 November 2019, 19:02:27 UTC
08bd367 Merge pull request #4405 from halide/srj-llvmfix Update for trunk LLVM API changes 14 November 2019, 17:49:04 UTC
64c21d8 Merge branch 'master' into srj-llvmfix 14 November 2019, 02:30:15 UTC
58277ba Merge pull request #4400 from halide/srj-llvm-git LLVM fixes (draft) 14 November 2019, 02:29:50 UTC
c0f6a32 typo 14 November 2019, 02:27:39 UTC
3d877e2 Update PyTorch support to work with v1.3 14 November 2019, 02:16:44 UTC
da732f4 Update for trunk LLVM API changes 14 November 2019, 01:39:43 UTC
54c0f95 Adds the ability to pass extra build options for OpenCL kernels. 14 November 2019, 00:24:16 UTC
e2dfef3 Merge branch 'master' into tzumao-gradient-autoscheduler-bug 14 November 2019, 00:09:51 UTC
4057b85 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 Merge branch 'master' into pdb_mul_div_mod_multi_thread 13 November 2019, 22:54:48 UTC
4e4bb48 Merge pull request #4395 from halide/srj-llvm Update README for LLVM build instructions (Issue #4394) 13 November 2019, 22:44:03 UTC
b3631fd Merge branch 'master' into srj-llvm-git 13 November 2019, 22:43:30 UTC
afd9f4d Merge pull request #4391 from halide/srj-onnx-cast avoid reinterpret_cast in onnx_converter 13 November 2019, 22:18:52 UTC
b22d4f6 Fix typo 13 November 2019, 20:18:18 UTC
ee4fbb9 Merge branch 'master' into pdb_mul_div_mod_multi_thread 13 November 2019, 18:22:08 UTC
d3031ab Merge branch 'master' into tzumao-gradient-autoscheduler-bug 13 November 2019, 18:19:41 UTC
59b616f Update README.md 13 November 2019, 18:18:18 UTC
72994e0 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 Merge branch 'master' into pdb_mul_div_mod_multi_thread 13 November 2019, 01:20:42 UTC
64ffb4e Fix comment 13 November 2019, 00:57:11 UTC
a5621ec Merge pull request #4398 from halide/srj-simd Fix set_host_alignment() in simd_op_check 12 November 2019, 23:34:39 UTC
b962486 Update Makefile 12 November 2019, 23:27:23 UTC
cad4b23 add test 12 November 2019, 22:06:08 UTC
99397c4 undo some changes 12 November 2019, 21:42:25 UTC
34c628a Fix gradient autoscheduler's usage of output estimates 12 November 2019, 21:39:29 UTC
e70e688 Update simd_op_check.h 12 November 2019, 19:31:55 UTC
47d70d1 Update simd_op_check_hvx.cpp 12 November 2019, 19:18:05 UTC
8777450 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 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 Update README for LLVM build instructions (Issue #4394) 12 November 2019, 01:50:58 UTC
53bb8ef avoid reinterpret_cast in onnx_converter 11 November 2019, 23:26:21 UTC
568ddfc Fix UB in Halide::Runtime::Buffer<>::size_in_bytes() 11 November 2019, 21:48:42 UTC
f60b8d2 Merge pull request #4383 from halide/srj-pt Misc minor PyTorch cleanups 06 November 2019, 22:02:38 UTC
50f6f92 Merge branch 'master' into pdb_mul_div_mod_multi_thread 06 November 2019, 18:14:37 UTC
d4aace9 Merge pull request #4380 from aankit-ca/offload_autosched_results Fix offload mode autoscheduler results. 06 November 2019, 18:13:08 UTC
aab0cd3 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 Revert "Add default constexpr constructor to ImplicitVar because Clang complaints about it" This reverts commit 9ff00ffe4ed0f2d476ba974ce1bad15bd70d9390. 06 November 2019, 00:33:02 UTC
d76fa09 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 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 Merge branch 'master' of https://github.com/halide/Halide 06 November 2019, 00:04:24 UTC
f2062aa 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 Merge pull request #4373 from halide/srj-pytorch Fix OSX+Homebrew+Python issue for HelloPyTorch 05 November 2019, 21:37:47 UTC
ce5b510 Merge pull request #4375 from halide/srj-fix ScheduleFeatures::num_features() and PipelineFeatures::num_features()… 04 November 2019, 17:06:56 UTC
e3055e9 ScheduleFeatures::num_features() and PipelineFeatures::num_features() should return size_t (Issue #4371) 01 November 2019, 23:06:46 UTC
893d986 Merge pull request #4374 from halide/srj-mangle Fix name-mangling [u]int64 on IOS 01 November 2019, 22:21:04 UTC
0f32df5 Add iOS test cases for mangling 01 November 2019, 22:20:49 UTC
c2a46b7 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 [Hexagon] LUT32 implementation using lut16. Remove unused variable. 01 November 2019, 17:47:25 UTC
149153f Merge branch 'master' into lut32 01 November 2019, 15:17:28 UTC
e035032 [Hexagon] LUT32 implementation using lut16. - Change IRBuilder to intrinsics - Fix failing test/correctness/gather.cpp 01 November 2019, 10:17:56 UTC
38bde2e Makefile reformatting 01 November 2019, 00:39:40 UTC
back to top