0778a23 | Andrew Adams | 04 March 2019, 22:46:17 UTC | Make it possible to disable the new code | 04 March 2019, 22:46:17 UTC |
cd29614 | Andrew Adams | 04 March 2019, 22:45:43 UTC | swapcontext deprecated on OS X | 04 March 2019, 22:45:43 UTC |
391dee7 | Andrew Adams | 04 March 2019, 20:06:57 UTC | Do lowering on a huge stack using mmap + swapcontext | 04 March 2019, 20:06:57 UTC |
09e20fc | Steven Johnson | 04 March 2019, 17:25:55 UTC | Merge pull request #3692 from halide/srj-tmpfile Remove halide_create_temp_file() | 04 March 2019, 17:25:55 UTC |
51d9390 | Dillon Sharlet | 03 March 2019, 01:38:02 UTC | Merge pull request #3144 from halide/newest_ion_ioctl ION: Support newer ioctl format for kernel 4.12 and up | 03 March 2019, 01:38:02 UTC |
2629e2d | dsharletg | 02 March 2019, 07:00:25 UTC | Small cleanups. | 02 March 2019, 07:00:25 UTC |
cb79785 | dsharletg | 02 March 2019, 06:42:08 UTC | Merge branch 'master' of https://github.com/halide/Halide into newest_ion_ioctl | 02 March 2019, 06:42:08 UTC |
280fc04 | Steven Johnson | 01 March 2019, 22:31:45 UTC | Remove halide_create_temp_file() This runtime module doesn't appear to be used anymore. (We can always resurrect it if we need it again.) | 01 March 2019, 22:31:45 UTC |
f08ba61 | Steven Johnson | 01 March 2019, 20:16:27 UTC | Merge pull request #3673 from halide/hexagon-target Remove explicit target feature numbering | 01 March 2019, 20:16:27 UTC |
1308cd1 | Steven Johnson | 01 March 2019, 19:35:58 UTC | Merge pull request #3690 from halide/srj-hygiene Remove switch-fallthru usage in Target.cpp | 01 March 2019, 19:35:58 UTC |
e4c4fd6 | Steven Johnson | 01 March 2019, 00:32:41 UTC | Remove switch-fallthru usage in Target.cpp We actually decided in https://github.com/halide/Halide/pull/3211 to just forbid switch fallthru in Halide; rewrote the recently injected usage to avoid. Also, drive-by spelling fix. | 01 March 2019, 00:32:41 UTC |
9589f63 | Dillon Sharlet | 28 February 2019, 22:49:22 UTC | Merge pull request #3686 from halide/fix-hexagon-masks Fix if_then_else and require for vectorized conditions on Hexagon | 28 February 2019, 22:49:22 UTC |
8d76a01 | Steven Johnson | 28 February 2019, 20:11:17 UTC | Merge pull request #3685 from halide/srj-entire Add read_entire() and write_entire() | 28 February 2019, 20:11:17 UTC |
4a97b8e | Ahmed S. Taei | 27 February 2019, 20:07:43 UTC | Merge pull request #3652 from halide/ataei-resnet50 Add apps/resnet_50 | 27 February 2019, 20:07:43 UTC |
ee5075c | Steven Johnson | 27 February 2019, 19:44:43 UTC | Rename | 27 February 2019, 19:44:43 UTC |
7e6da25 | Alex Reinking | 27 February 2019, 00:11:47 UTC | Merge pull request #3684 from halide/windows-improvements Fix LoadLibrary call to use UTF-8 instead of ANSI. | 27 February 2019, 00:11:47 UTC |
940456f | = | 26 February 2019, 23:56:33 UTC | Add building app/resnet_50 generator to test_app | 26 February 2019, 23:56:33 UTC |
93617ef | = | 26 February 2019, 23:44:11 UTC | Merge branch 'master' into ataei-resnet50 | 26 February 2019, 23:44:11 UTC |
1398f66 | Steven Johnson | 26 February 2019, 23:25:04 UTC | Add read_entire() and write_entire() Simple utility functions to slurp / spew the entire contents of a file; not much re-use in this PR but I'll need them elsewhere in the future, so this is intended to reduce future PR noise. | 26 February 2019, 23:25:04 UTC |
ae2cb14 | dsharletg | 26 February 2019, 23:10:38 UTC | Fix if_then_else and require for vectorized conditions on Hexagon. | 26 February 2019, 23:10:38 UTC |
8d37cc4 | Andrew Adams | 26 February 2019, 22:30:32 UTC | Merge pull request #3672 from halide/gpu_camera_pipe Gpu camera pipe | 26 February 2019, 22:30:32 UTC |
e6ccdc0 | Alex Reinking | 26 February 2019, 20:57:40 UTC | Fix windows_get_symbol. Copying in constants and forward declarations. Have to use malloc/free instead of new/delete due to compiler errors. Why? | 26 February 2019, 20:57:40 UTC |
5923956 | Alex Reinking | 26 February 2019, 20:38:31 UTC | Revert windows_get_symbol change. Build wrong target and didn't notice errors. | 26 February 2019, 20:38:31 UTC |
5bc5aaf | Alex Reinking | 26 February 2019, 20:27:10 UTC | Fixing LoadLibrary calls in windows_get_symbol runtime and lesson 12. | 26 February 2019, 20:27:10 UTC |
d694047 | Alex Reinking | 26 February 2019, 20:20:49 UTC | Adding error handling, improved memory management. | 26 February 2019, 20:20:49 UTC |
baed7f1 | Alex Reinking | 26 February 2019, 19:56:18 UTC | Fix LoadLibrary call to use UTF-8 instead of ANSI. | 26 February 2019, 19:56:18 UTC |
8188c00 | Alex Reinking | 25 February 2019, 21:50:24 UTC | Merge pull request #3671 from halide/target-gcd Let generators compute a GCD target when multiple targets are passed to `-r` | 25 February 2019, 21:50:24 UTC |
08370d1 | Dillon Sharlet | 25 February 2019, 18:18:52 UTC | Merge pull request #3680 from halide/is-parallel-refactor Refactor is_parallel helper functions | 25 February 2019, 18:18:52 UTC |
9047e19 | dsharletg | 25 February 2019, 00:59:16 UTC | Fix comment mistake. | 25 February 2019, 00:59:26 UTC |
0987047 | dsharletg | 24 February 2019, 22:13:39 UTC | Refactor of is_parallel helper functions. | 24 February 2019, 22:39:41 UTC |
5a27296 | Steven Johnson | 23 February 2019, 01:58:58 UTC | Merge branch 'master' into target-gcd | 23 February 2019, 01:58:58 UTC |
5d72d48 | Alex Reinking | 23 February 2019, 01:31:50 UTC | Fix bug when one target uses base cuda and the other doesn't. Add test. | 23 February 2019, 01:31:50 UTC |
04fe1f0 | Alex Reinking | 23 February 2019, 01:17:30 UTC | Adding test cases to `target_test` in `test_internal` | 23 February 2019, 01:17:30 UTC |
e0494fe | Alex Reinking | 22 February 2019, 22:55:32 UTC | Adding fall-thru comments to switches. | 22 February 2019, 22:55:32 UTC |
9cb3d07 | Alex Reinking | 22 February 2019, 22:10:14 UTC | Adding help text to gengen for `-r` flag. A couple clang-tidy fixes. | 22 February 2019, 22:10:14 UTC |
6d9b1a9 | Alex Reinking | 22 February 2019, 18:40:40 UTC | Document that out-param can be *this. Write only once to `result`. | 22 February 2019, 18:40:40 UTC |
1335f02 | Steven Johnson | 21 February 2019, 19:11:11 UTC | Merge pull request #3660 from halide/srj-btest Revise Simplify for << and >> to forbid out-of-range constant shifts | 21 February 2019, 19:11:11 UTC |
b220194 | Alex Reinking | 21 February 2019, 19:09:30 UTC | Merge branches 'master' and 'target-gcd' of https://github.com/halide/Halide into target-gcd | 21 February 2019, 19:09:30 UTC |
2365eed | Alex Reinking | 21 February 2019, 19:04:46 UTC | Another hexagon feature fix from @pranavb-ca | 21 February 2019, 19:04:46 UTC |
8dc88b4 | Alex Reinking | 20 February 2019, 23:34:16 UTC | Fixing Hexagon usage detection. | 20 February 2019, 23:34:16 UTC |
f9349ce | Steven Johnson | 20 February 2019, 23:32:00 UTC | Merge branch 'master' into srj-btest | 20 February 2019, 23:32:00 UTC |
23064ae | Alex Reinking | 20 February 2019, 22:11:40 UTC | Merge remote-tracking branch 'origin/target-gcd' into target-gcd # Conflicts: # src/Target.cpp | 20 February 2019, 22:11:40 UTC |
56dc950 | Alex Reinking | 20 February 2019, 21:58:36 UTC | Fixing hexagon flag handling per @pranavb-ca's comments. | 20 February 2019, 22:10:48 UTC |
cfb880d | Alex Reinking | 20 February 2019, 21:58:36 UTC | Fixing hexagon flag handling per @pranavb-ca's comments. | 20 February 2019, 21:58:36 UTC |
406cd21 | Andrew Adams | 20 February 2019, 18:57:37 UTC | Merge pull request #3565 from jia-kai/fix-runtime-cuda-init Fix race conditions during CUDA runtime initialization | 20 February 2019, 18:57:37 UTC |
fb6f3e2 | Alex Reinking | 20 February 2019, 11:42:32 UTC | Allow multiple targets for generator's `-r`. Add debug print. | 20 February 2019, 11:42:32 UTC |
edb8962 | dsharletg | 20 February 2019, 07:05:28 UTC | Add comment about compatibility of standalone runtimes. | 20 February 2019, 07:05:28 UTC |
3d45ba9 | Ahmed S. Taei | 20 February 2019, 01:53:52 UTC | Merge pull request #3675 from halide/ataei-skip_nongpu Skip canonicalize_gpu_vars for non-gpu targets | 20 February 2019, 01:53:52 UTC |
84fab56 | Steven Johnson | 20 February 2019, 00:40:21 UTC | Merge pull request #3674 from halide/srj-tgz Fix Makefile building of halide.tgz | 20 February 2019, 00:40:21 UTC |
430e40d | Alex Reinking | 20 February 2019, 00:21:20 UTC | Fixing indentation. | 20 February 2019, 00:21:20 UTC |
82aa74d | Alex Reinking | 19 February 2019, 23:55:27 UTC | Using lower bound for CUDA & HVX. Fixing features lists per discussion. | 19 February 2019, 23:55:27 UTC |
8c2d9ab | Ahmed Taei | 19 February 2019, 23:37:48 UTC | Skip canonicalize_gpu_vars for non-gpu targets | 19 February 2019, 23:37:48 UTC |
64eb4c7 | Alex Reinking | 19 February 2019, 21:42:07 UTC | Splitting up union_features and matching_features. | 19 February 2019, 21:42:07 UTC |
1f1e74a | Alex Reinking | 19 February 2019, 21:29:46 UTC | Adding doxygen comments and an advisory to HalideRuntime.h | 19 February 2019, 21:29:46 UTC |
41c2f07 | Alex Reinking | 19 February 2019, 21:15:28 UTC | Adjusting Hexagon handling to be more like CUDA. Still need advice. | 19 February 2019, 21:15:28 UTC |
d34f739 | Alex Reinking | 19 February 2019, 21:01:03 UTC | Commenting get_runtime_compatible_target, adding matching features list. | 19 February 2019, 21:03:30 UTC |
b215b73 | Steven Johnson | 19 February 2019, 20:14:27 UTC | Also fix some drift between the Make and CMake distrib builds | 19 February 2019, 20:14:27 UTC |
3c6b74a | Steven Johnson | 19 February 2019, 19:19:27 UTC | Fix Makefile building of halide.tgz | 19 February 2019, 19:19:27 UTC |
50d7d5c | Steven Johnson | 19 February 2019, 18:52:19 UTC | Add >= 0 check | 19 February 2019, 18:52:19 UTC |
a6c717c | dsharletg | 19 February 2019, 07:35:47 UTC | Fix use of unused target feature flag. | 19 February 2019, 07:35:47 UTC |
2eba9bf | dsharletg | 19 February 2019, 07:01:15 UTC | Fix accidentally removed hvx_v65 target flag. | 19 February 2019, 07:01:15 UTC |
50ee393 | dsharletg | 19 February 2019, 06:58:41 UTC | Remove unused enum value. | 19 February 2019, 06:58:41 UTC |
6e60d7c | dsharletg | 19 February 2019, 06:52:37 UTC | Remove explicit target feature numbering. | 19 February 2019, 06:52:37 UTC |
788b9f1 | Alex Reinking | 19 February 2019, 06:26:55 UTC | Fixing CUDA flag handling. Using bitmasks for union/intersect. | 19 February 2019, 06:26:55 UTC |
8152281 | Andrew Adams | 17 February 2019, 22:27:06 UTC | Remove duplicated comment | 17 February 2019, 22:27:06 UTC |
2be6a0f | Andrew Adams | 17 February 2019, 22:26:00 UTC | Reduce code churn | 17 February 2019, 22:26:00 UTC |
bc06953 | Andrew Adams | 17 February 2019, 22:23:35 UTC | Fix for old autoscheduler | 17 February 2019, 22:23:35 UTC |
58db6f3 | Andrew Adams | 17 February 2019, 21:34:48 UTC | Add camera pipe GPU schedule | 17 February 2019, 22:19:55 UTC |
3d1f4e2 | Andrew Adams | 17 February 2019, 22:19:50 UTC | Add device_sync to camera pipe benchmark | 17 February 2019, 22:19:50 UTC |
ccc3049 | Alex Reinking | 16 February 2019, 01:16:28 UTC | Fixing comparison between signed and unsigned integer expressions | 16 February 2019, 01:16:28 UTC |
9117243 | Alex Reinking | 16 February 2019, 01:06:52 UTC | Implementing draft of runtime target merging. Some feature flags outstanding. | 16 February 2019, 01:06:52 UTC |
2fe73b5 | Alex Reinking | 16 February 2019, 01:01:43 UTC | Apply a few clang-tidy suggestions | 16 February 2019, 01:02:08 UTC |
629cdd9 | Steven Johnson | 15 February 2019, 18:49:56 UTC | More robust tweaks. | 15 February 2019, 18:49:56 UTC |
8bbd586 | Steven Johnson | 14 February 2019, 21:41:54 UTC | Add more checks on bounds for shift-right | 14 February 2019, 21:41:54 UTC |
843242e | Steven Johnson | 14 February 2019, 20:40:55 UTC | Merge branch 'master' into srj-btest | 14 February 2019, 20:40:55 UTC |
f5b2237 | Steven Johnson | 14 February 2019, 20:40:31 UTC | Merge pull request #3668 from halide/srj-llvm-fix API fix for trunk LLVM | 14 February 2019, 20:40:31 UTC |
42b635d | Steven Johnson | 14 February 2019, 18:34:07 UTC | API fix for trunk LLVM | 14 February 2019, 18:34:07 UTC |
fd1b7e6 | Steven Johnson | 09 February 2019, 03:04:03 UTC | Merge branch 'master' into srj-btest | 09 February 2019, 03:04:03 UTC |
d02247b | Steven Johnson | 09 February 2019, 03:02:29 UTC | Merge pull request #3662 from halide/srj-ctlz Improve handling of clz, ctz, popcount | 09 February 2019, 03:02:29 UTC |
504adc6 | Steven Johnson | 09 February 2019, 03:01:53 UTC | Merge pull request #3659 from halide/srj-bitwise Bounds for shift_right with signed-ints was incorrect | 09 February 2019, 03:01:53 UTC |
460ea86 | Steven Johnson | 09 February 2019, 01:17:34 UTC | Fix bug/test, part 2: bonehead boogaloo | 09 February 2019, 01:17:34 UTC |
34a45e3 | Steven Johnson | 08 February 2019, 18:44:02 UTC | Fix more MSVC nonsense | 08 February 2019, 18:44:02 UTC |
4c92390 | Steven Johnson | 08 February 2019, 17:47:00 UTC | Fix bug, add test | 08 February 2019, 17:47:00 UTC |
3384e64 | Steven Johnson | 08 February 2019, 02:02:37 UTC | Merge branch 'master' into srj-bitwise | 08 February 2019, 02:02:37 UTC |
d679792 | Steven Johnson | 08 February 2019, 02:02:01 UTC | Fix C backend for 64-bit types | 08 February 2019, 02:02:01 UTC |
8e407e5 | Steven Johnson | 08 February 2019, 01:01:00 UTC | Make clz, ctz well-defined at zero (Note that we were already providing this behavior by mistake, we just didn't document or test it as such.) - fixed comments for count_leading_zeros() and count_trailing_zeros - rename misnamed arg in Codegen_LLVM - revised Simplify code to handle zero properly - revised Bounds code to allow for zero - added missing definitions of count_trailing_zeros and popcount to the C backend, and added scalarizing | 08 February 2019, 01:01:00 UTC |
5b1b1d4 | Steven Johnson | 07 February 2019, 22:26:40 UTC | Fix another bonehead mistake | 07 February 2019, 22:26:40 UTC |
0fca279 | Steven Johnson | 07 February 2019, 21:02:00 UTC | Fix overload ambiguity | 07 February 2019, 21:02:00 UTC |
8836f50 | Steven Johnson | 07 February 2019, 20:14:34 UTC | Ensure Bounds calc doesn't trigger known illegal shifts | 07 February 2019, 20:14:34 UTC |
1a30a16 | Steven Johnson | 07 February 2019, 19:57:37 UTC | Use intrin.h instead of forward-declaring | 07 February 2019, 19:57:37 UTC |
0dcc0f8 | Steven Johnson | 07 February 2019, 19:56:31 UTC | use min() instead of select() | 07 February 2019, 19:56:31 UTC |
86285ad | Steven Johnson | 07 February 2019, 19:34:44 UTC | Merge branch 'master' into srj-btest | 07 February 2019, 19:34:44 UTC |
abd4ab0 | Steven Johnson | 07 February 2019, 19:32:15 UTC | Attempt to appease MSVC | 07 February 2019, 19:32:15 UTC |
b545b3b | Steven Johnson | 07 February 2019, 18:12:25 UTC | Use intrinsics; make clz/ctz(0) a compile error | 07 February 2019, 18:12:25 UTC |
dec062c | Steven Johnson | 07 February 2019, 02:44:38 UTC | Fix cast mistake | 07 February 2019, 02:44:38 UTC |
5d71861 | Steven Johnson | 07 February 2019, 02:05:59 UTC | Improve handling of clz, ctz, popcount - Add special-casing of these to the Simplifier, so that constant values are simplified to constants - Improve handling of bounds-calculation for clz to allow narrower min and max when the intervals are bounded | 07 February 2019, 02:05:59 UTC |
821b3a7 | Steven Johnson | 06 February 2019, 22:37:13 UTC | Merge pull request #3656 from halide/srj-rg2 Extend registration mechanism to be extensible | 06 February 2019, 22:37:13 UTC |
cad0cfc | Steven Johnson | 06 February 2019, 01:49:55 UTC | Fix bonehead mistake | 06 February 2019, 01:49:55 UTC |
3b0c453 | Steven Johnson | 06 February 2019, 01:30:20 UTC | Revise Simplify for << and >> to forbid out-of-range constant shifts Formerly we tried to handle negative shifts by flipping the operation, and out-of-range shifts by clipping to zero or -1. This isn't necessarily *wrong* -- these are UB in C++ (and poison-producing in LLVM) -- but I'd argue that if we can statically detect UB/poison values, we're better off producing a hard error at compile time. See also https://github.com/halide/Halide/issues/3325 | 06 February 2019, 01:30:20 UTC |
15be77d | Steven Johnson | 06 February 2019, 00:16:36 UTC | Bounds for shift_right with signed-ints was incorrect The boundaries didn't take into account the differing behavior of signed values, so the constant bounds signed ints was wildly wrong in some cases (eg int16 >> int16 -> [-1, 0]) | 06 February 2019, 00:16:36 UTC |