346c37b | Andrew Adams | 07 December 2017, 21:54:28 UTC | Reset branch onto new history Was ab17f01fc00f31db5ed5358307bf39501cb698b4 | 07 December 2017, 21:54:28 UTC |
8a00cac | Andrew Adams | 16 December 2016, 00:00:24 UTC | Minor fix to vectorization Former-commit-id: 0a8b31b221dcdc184304e428f73da14ea3cee8ad | 16 December 2016, 00:00:24 UTC |
78fb337 | Andrew Adams | 15 December 2016, 22:46:11 UTC | Fix passing bool types into gpu kernels Former-commit-id: 831bd12bc7a9bb77951e52c6365b4f66f12aaa6c | 15 December 2016, 22:46:11 UTC |
9a39e0f | Andrew Adams | 15 December 2016, 21:50:41 UTC | Merge pull request #1689 from halide/no_autovectorize_in_runtime Disable early autovectorization of runtime Former-commit-id: bf81d73b2629646bf91392b2ccda1a0683c413b6 | 15 December 2016, 21:50:41 UTC |
90356ab | Andrew Adams | 15 December 2016, 18:31:27 UTC | Merge pull request #1692 from halide/float_api_fix Adapt to new Float api for llvm_ver >= 40 Former-commit-id: e7faa786c6ce050bec0ef24d671f3eba7f32f34d | 15 December 2016, 18:31:27 UTC |
6796522 | Ron Lieberman | 15 December 2016, 15:07:19 UTC | Adapt to new Float api for llvm_ver >= 40 Former-commit-id: 97d4e993ec4393f47e5dbb695ac4ac29e34e112c | 15 December 2016, 15:07:19 UTC |
0508e86 | Dillon Sharlet | 14 December 2016, 22:45:34 UTC | Merge pull request #1657 from halide/hexagon-power Added two more methods for powering on HVX Former-commit-id: 065e872fea7d42faef79171c4b8614d757831f20 | 14 December 2016, 22:45:34 UTC |
ee327f9 | Dillon Sharlet | 14 December 2016, 19:34:31 UTC | Merge pull request #1682 from halide/hex-add-sim-readme Add addtional needed path for hexagon LD_LIBRARY_PATH Former-commit-id: 1e838002086368a5ef371a1b9135d4ea4e472b67 | 14 December 2016, 19:34:31 UTC |
087b9c0 | Ron Lieberman | 14 December 2016, 19:29:08 UTC | use relative path Former-commit-id: 40ab1048ce54695fef7549adfe616babf2c964aa | 14 December 2016, 19:29:08 UTC |
cdfedf5 | Dillon Sharlet | 14 December 2016, 02:13:44 UTC | Merge pull request #1686 from halide/HelloHexagon_Buffer Update HelloHexagon to use Halide::Buffer Former-commit-id: dfff62e09b352aa71b8b0d8c15a5806d691ba313 | 14 December 2016, 02:13:44 UTC |
d126703 | Andrew Adams | 14 December 2016, 02:10:30 UTC | DRY Former-commit-id: bea16cd79ba7794bebb8f15ebae08e056c45dcd4 | 14 December 2016, 02:10:30 UTC |
8b2aaa6 | Andrew Adams | 14 December 2016, 02:08:24 UTC | Disable early autovectorization of runtime We compile the runtime modules to .ll for a "generic" target at -O3. Apparently in some circumstances this autovectorizes to 128-bits. Not all vector types are supported by all targets (hexagon), so this is bad, and can cause assertion failures inside LLVM during instruction selection. This PR turns this off. The .ll gets a second chance to autovectorize later in codegen once the module is assembled and has a concrete target. Former-commit-id: 457ee7eaa6246419a2a2d0e5cd55f0a0279dd081 | 14 December 2016, 02:08:24 UTC |
6157aa0 | Andrew Adams | 13 December 2016, 22:43:36 UTC | Merge pull request #1679 from halide/fix_openglcompute_app Fix openglcompute app Former-commit-id: e9d4b85b91084bc05fb30012b6672c33a1d882de | 13 December 2016, 22:43:36 UTC |
816fa8b | Andrew Adams | 13 December 2016, 22:41:52 UTC | Update HelloHexagon to use Halide::Buffer Former-commit-id: 10a4b5f2920c9f64bf4f40bc21c2caebf6fe308a | 13 December 2016, 22:41:52 UTC |
9d1ba1d | Andrew Adams | 13 December 2016, 22:09:02 UTC | Merge pull request #1674 from halide/oip Remove deprecated methods from OutputImageParam, plus usage fixes Former-commit-id: 8978a40d9736ebe41ba5f959736bc200c2dbaff9 | 13 December 2016, 22:09:02 UTC |
6528763 | Andrew Adams | 13 December 2016, 22:08:17 UTC | Merge pull request #1665 from halide/BufferRefCollection Fix realizing into multiple existing buffers Former-commit-id: 028f1609fddae010d3cbd5bf095aac2127a372f4 | 13 December 2016, 22:08:17 UTC |
2dae28c | Andrew Adams | 13 December 2016, 22:07:54 UTC | Remove pointless overloads Former-commit-id: 86354b489221e896eea774c31c3112d042d87689 | 13 December 2016, 22:07:54 UTC |
2d3eec5 | Andrew Adams | 13 December 2016, 20:54:56 UTC | Merge pull request #1678 from halide/dim Move Dimension from OutputImageParam into Parameter.h Former-commit-id: 2aeb9694610e9ef2f34355919bf0d173d53aa45d | 13 December 2016, 20:54:56 UTC |
7a2103b | Patricia Suriana | 13 December 2016, 20:15:14 UTC | Vectorized pred test should only run on X86 or Hexagon Former-commit-id: c5b8f369e0be000e61e6301a4af491e6e73baab5 | 13 December 2016, 20:15:14 UTC |
d3bef21 | Andrew Adams | 13 December 2016, 19:51:07 UTC | Merge pull request #1684 from halide/halide-buffer-translated-fix Set correct return type for Buffer::translated Former-commit-id: 98b909f8f44d64a23cfe7f1a988bb4772cddd8f2 | 13 December 2016, 19:51:07 UTC |
f1d7515 | Jonathan Ragan-Kelley | 13 December 2016, 19:47:46 UTC | Set correct return type for Buffer::translated Astonishingly, this was caught by nvcc, of all compilers. /attn @abadams Former-commit-id: 6b5146569525da3869dbe0fdeece995c04936e47 | 13 December 2016, 19:47:46 UTC |
93151be | Andrew Adams | 13 December 2016, 19:38:31 UTC | Merge pull request #1683 from halide/lesson10 lesson 10 was broken for CMake build Former-commit-id: 5452aca8d117c9782e6ce0eef381e0952b671a5b | 13 December 2016, 19:38:31 UTC |
1410445 | Steven Johnson | 13 December 2016, 18:05:43 UTC | lesson 10 was broken for CMake build Former-commit-id: 70fbddcfef5de3356bebc06a61a78168ec9bfec1 | 13 December 2016, 18:05:43 UTC |
d38fa4f | Ron Lieberman | 13 December 2016, 16:41:35 UTC | document need for HL_HEXAGON_SIM_REMOTE in README.md Former-commit-id: cdedf1a3a8049228bf16016f14bf572bb438d897 | 13 December 2016, 16:41:35 UTC |
89a28e3 | Ron Lieberman | 13 December 2016, 15:31:13 UTC | Add addtional needed path for hexagon LD_LIBRARY_PATH Former-commit-id: 0accbe887955c21882f40673bdbd9d200dd0c347 | 13 December 2016, 15:31:13 UTC |
ed9b64c | Dillon Sharlet | 13 December 2016, 01:58:33 UTC | Merge pull request #1345 from halide/vectorized_pred Vectorized pred Former-commit-id: bc334ee1bf2384e7017feb8ef3166ca22c759b1f | 13 December 2016, 01:58:33 UTC |
98e6068 | Andrew Adams | 13 December 2016, 01:19:50 UTC | Merge pull request #1680 from halide/glsl_app_buffers Update opengl_test to use Halide::Buffer Former-commit-id: f8dcd439722cd862222a9f504b343de63d9218d4 | 13 December 2016, 01:19:50 UTC |
54921a2 | Andrew Adams | 13 December 2016, 00:50:41 UTC | Update opengl_test to use Buffer Former-commit-id: e6c3811cd8478c1d0d541746f849e9ba8e6a004a | 13 December 2016, 00:50:41 UTC |
12b1305 | Andrew Adams | 13 December 2016, 00:46:38 UTC | Fix openglcompute app Made it use Halide::Buffer. While doing this I discovered that the vector support in OpenGLCompute codegen was broken, and made a dangerous assumption anyway (all vector access is aligned), so I neutered it for now. It needs a pass that actually detects if all buffer access is aligned dense vectors, and if so, declares the buffer as an array of vectors. Former-commit-id: 475808a7d314d21d0d74da7ea7b1333627573fb8 | 13 December 2016, 00:46:38 UTC |
bd7b692 | Steven Johnson | 13 December 2016, 00:03:24 UTC | Move Dimension from OutputImageParam into Parameter.h I need to re-use it for Generator purposes; mostly-decoupling it from OutputImageParam makes that less weird. (“Mostly” because we still grant friend access for ctors, though frankly, we could probably just make them public) Former-commit-id: 3c7c445978ae206f291f669875c71bdf01659c94 | 13 December 2016, 00:03:24 UTC |
401ff52 | Patricia Suriana | 12 December 2016, 23:05:28 UTC | Moved comments Former-commit-id: ff102acf4ce6b560481c840deef40bc1a927cc1c | 12 December 2016, 23:05:28 UTC |
ad19e53 | Dillon Sharlet | 12 December 2016, 22:26:31 UTC | Merge branch 'master' of https://github.com/halide/Halide into hexagon-power Former-commit-id: acb4110fc9a6af348bd7a8866e816ca55ad529bb | 12 December 2016, 22:26:31 UTC |
bc1aebf | Andrew Adams | 12 December 2016, 22:24:49 UTC | Merge branch 'master' of ssh://github.com/halide/Halide Former-commit-id: 9e9e94cd8472455805040f28ae21371e0660c521 | 12 December 2016, 22:24:49 UTC |
b036704 | Andrew Adams | 12 December 2016, 22:24:43 UTC | Fix compilation of simd_op_check Former-commit-id: bea39bd064b4e9735b6627c3cef77facc4266346 | 12 December 2016, 22:24:43 UTC |
8568fd4 | Dillon Sharlet | 12 December 2016, 22:09:35 UTC | Add memset to fake dlsym implementation. Former-commit-id: b0837c4983d4c749dccc9eff2397db063f82e3f5 | 12 December 2016, 22:09:35 UTC |
6f1c449 | Patricia Suriana | 12 December 2016, 22:00:42 UTC | Merge branch 'master' of github.com:halide/Halide into vectorized_pred Former-commit-id: c67f93018ff713b44075f5aba21a54c2c870a9a6 | 12 December 2016, 22:00:42 UTC |
f908350 | Patricia Suriana | 12 December 2016, 21:14:50 UTC | Clean up code and stale comments Former-commit-id: 7b22db865ed8192711ce3c418bf75ba3ac017244 | 12 December 2016, 21:14:50 UTC |
1a1d12c | Steven Johnson | 12 December 2016, 21:08:10 UTC | Merge pull request #1673 from halide/remove_buffer_t_from_tutorials Remove buffer_t from tutorials Former-commit-id: 003b48383b378486e5dd5130d3941f7cc2ba0874 | 12 December 2016, 21:08:10 UTC |
1fe17d9 | Andrew Adams | 12 December 2016, 18:22:26 UTC | Merge pull request #1677 from halide/ptx cxx_mangling_gpu should be if(TARGET_PTX) (Issue #1676) Former-commit-id: 23a9a613bee92a86ed1054c66c3a550cb3bff32a | 12 December 2016, 18:22:26 UTC |
0c59c15 | Steven Johnson | 12 December 2016, 18:14:22 UTC | cxx_mangling_gpu should be if(TARGET_PTX) Former-commit-id: 48daf610120cbf6a121e13d45b9f07e36fa2febf | 12 December 2016, 18:14:22 UTC |
9076c54 | Andrew Adams | 12 December 2016, 18:12:15 UTC | Merge pull request #1675 from halide/fix_ptx_passes Fix PTX pass manager. Former-commit-id: 5ddf3ba287d1593749c9a626ef1d84817251f7a2 | 12 December 2016, 18:12:15 UTC |
75fd1b4 | Dan Palermo | 12 December 2016, 17:52:13 UTC | Fine tune performance parameters - increase low max_bus_bw while preserving bits - decrease bus usage percentage for low & nominal - increase bus bw for turbo (safety margin) - sink mipsTotal computation outside of switch Former-commit-id: d2dcca5311b009d3ad349ae02ff9642b4078c458 | 12 December 2016, 17:52:13 UTC |
e894122 | Andrew Adams | 11 December 2016, 01:57:45 UTC | Another slight tweak Former-commit-id: e403404d39a8f7c7197eb657fcc276aaf330a8b5 | 11 December 2016, 01:57:45 UTC |
b1c9bad | Andrew Adams | 11 December 2016, 01:53:48 UTC | Slight schedule improvement Former-commit-id: 57a6d34ff3c8cbe98303a8c79053c049cdd11031 | 11 December 2016, 01:53:48 UTC |
ea8e303 | Andrew Adams | 10 December 2016, 18:11:26 UTC | Slightly better schedule Former-commit-id: a7cfdbde2b68d8c930f0a7f1ec9c7726ccdda5ca | 10 December 2016, 18:11:26 UTC |
b55c82d | Andrew Adams | 10 December 2016, 04:01:04 UTC | Fix PTX pass manager. LLVM was perfectly capable of fragmenting allocations if we just asked it to. Former-commit-id: 0e1662f2382e7134205abcdcd995a54f3441365a | 10 December 2016, 04:01:04 UTC |
abedbcd | Dan Palermo | 10 December 2016, 03:31:03 UTC | Update from 12/8 review comments: halide_hexagon_remote_power_hvx_on_perf(): - change bwBytePerSec to bwMegabytesPerSec - remove unused result halide_hexagon_remote_power_hvx_on_mode(): - don't check power_ref_count when computing values - hoist values out of switch that are set the same in all modes - verified turbo performance stil matches tip (camera_pipe & HelloHexagon) - verified low, nominal, & turbo power modes scale well - camera_pipe increases in performance ~20% on each step Former-commit-id: e093d22a78460718dda221660455da8b7d1444f8 | 10 December 2016, 03:31:03 UTC |
8e1a2ec | Steven Johnson | 09 December 2016, 23:09:21 UTC | Revise HALIDE_ATTRIBUTE_DEPRECATED to use message Former-commit-id: 62693b854e3f4e548ed4489bc8c5854823eb09ca | 09 December 2016, 23:09:21 UTC |
9bb2b35 | Andrew Adams | 09 December 2016, 23:05:17 UTC | Missed two Former-commit-id: 6d9b815ef085705bc6c4be0c939247f350c4f425 | 09 December 2016, 23:05:17 UTC |
1808dfd | Steven Johnson | 09 December 2016, 22:43:15 UTC | define HALIDE_ATTRIBUTE_DEPRECATED; mark OutputImageParam methods with it (rather than deleting them) Former-commit-id: 6d87eddf98ab9cabfa69fc86635e74a60984cd04 | 09 December 2016, 22:43:15 UTC |
0aa7719 | Andrew Adams | 09 December 2016, 22:39:20 UTC | Rename BufferRefCollection to BufferRefs Former-commit-id: 80348692038ac335642c215e176b8eb6b0337c94 | 09 December 2016, 22:39:20 UTC |
0cadff4 | Andrew Adams | 09 December 2016, 22:36:47 UTC | Merge branch 'master' into BufferRefCollection # Conflicts: # src/Pipeline.cpp Former-commit-id: 4806c08f83797bdc79c190751cef2b66075f6462 | 09 December 2016, 22:36:47 UTC |
c31178e | Steven Johnson | 09 December 2016, 22:26:26 UTC | Merge branch 'master' into oip # Conflicts: # tutorial/lesson_16_rgb_generate.cpp Former-commit-id: e98d273ac8fcd35e3e2c3563eab4b18fb1df9f05 | 09 December 2016, 22:26:26 UTC |
55c0684 | Steven Johnson | 09 December 2016, 22:25:31 UTC | Remove deprecated methods from OutputImageParam, plus usage fixes Former-commit-id: f65aedc091ad4d5222ef1df610482051d1f44f77 | 09 December 2016, 22:25:31 UTC |
0969337 | Andrew Adams | 09 December 2016, 22:21:13 UTC | Remove buffer_t from tutorials We now want people to always just use Halide::Buffer. Encouraging people to use naked buffer_t was a mistake - everyone just wrote their own wrapper classes. Former-commit-id: 84bda3d1748e826d6f43d66aa7d9d3f68f4b47fb | 09 December 2016, 22:21:13 UTC |
4a1ddcd | Zalman Stern | 09 December 2016, 22:01:12 UTC | Merge pull request #1670 from halide/gpp fix C++ name-mangling for GPU targets Former-commit-id: 3be9cf91db0181efa7f5422cab8347524f365585 | 09 December 2016, 22:01:12 UTC |
010fa69 | Andrew Adams | 09 December 2016, 22:00:02 UTC | Fix tutorial convention Former-commit-id: 15f72946b92ba9c71072dad2fb7f63a89d98a992 | 09 December 2016, 22:00:02 UTC |
58df70f | Andrew Adams | 09 December 2016, 21:59:57 UTC | Upgrade some tests to Buffer<> Former-commit-id: 58d361499c8c5c180ebc9d9356fe8e422cb7da15 | 09 December 2016, 21:59:57 UTC |
1e75589 | Andrew Adams | 09 December 2016, 21:30:44 UTC | Merge branch 'master' of ssh://github.com/halide/Halide Former-commit-id: 3df83169eee01483ce0e587c5ab7a056664e9293 | 09 December 2016, 21:30:44 UTC |
46aacdc | Andrew Adams | 09 December 2016, 21:30:38 UTC | Remove some explicit buffer use from linear algebra Former-commit-id: 3111e0bc01368d20983212c04e200913cbdf8ce2 | 09 December 2016, 21:30:38 UTC |
4a7cba0 | Andrew Adams | 09 December 2016, 21:23:38 UTC | Merge pull request #1672 from halide/bufde Buffer::decref()/decref_dev() need to null alloc and buf.host Former-commit-id: 7bc335e9789615aba25b07f1e9c0adcf5c461a38 | 09 December 2016, 21:23:38 UTC |
f925bdb | Steven Johnson | 09 December 2016, 21:13:12 UTC | Unconditionally zero alloc in decref and decref_dev Former-commit-id: 65543184be3d03d216e5f6200524ab0562dcf128 | 09 December 2016, 21:13:12 UTC |
82f5553 | Steven Johnson | 09 December 2016, 20:25:24 UTC | Also null dev_ref_count in device_deallocate() Former-commit-id: 8bbad2d6ba36b0641c2df095c20983334b91e2dc | 09 December 2016, 20:25:24 UTC |
1e9288f | Steven Johnson | 09 December 2016, 20:24:06 UTC | Buffer::deallocate() needs to null alloc and buf.host Otherwise explicitly calling deallocate() could lead to double-frees later. (Note: do we need a similar fix in device_deallocate()?) Former-commit-id: 459e6c36d558de2115c9a11aa7e81bd0798fe6d2 | 09 December 2016, 20:24:06 UTC |
d4da791 | Andrew Adams | 09 December 2016, 19:47:22 UTC | Type fix. Former-commit-id: 86690217a032b336521636c436fbb7db050c92cb | 09 December 2016, 19:47:22 UTC |
feb0f9c | Andrew Adams | 09 December 2016, 19:41:47 UTC | Another type fix Former-commit-id: 6c3673ee127e13714a8df999795a446927630943 | 09 December 2016, 19:41:47 UTC |
99256ad | Andrew Adams | 09 December 2016, 19:31:11 UTC | fix type on halide_error_buffer_allocation_too_large Former-commit-id: fbe3ce78e228c9c24dae374d2952ee2ed292d405 | 09 December 2016, 19:31:11 UTC |
cfc0be4 | Andrew Adams | 09 December 2016, 19:09:25 UTC | Remove pointless extern C Former-commit-id: 4767439f1107ef7cd837ac000995877490116b4f | 09 December 2016, 19:09:25 UTC |
7231cfc | Andrew Adams | 09 December 2016, 18:42:28 UTC | Fix types in tiled_blur test Former-commit-id: 3e4e5821b69c89b97faaf287105e36851289e7f4 | 09 December 2016, 18:42:28 UTC |
d86d3e1 | Andrew Adams | 09 December 2016, 18:42:12 UTC | Remove dead code Former-commit-id: cdd1c4a060c9c14ab650905369194f8ff914b556 | 09 December 2016, 18:42:12 UTC |
7b5dd09 | Andrew Adams | 09 December 2016, 18:21:29 UTC | Add missing _t to halide_device_interface Former-commit-id: 159c11e83de9f9adca48011cefbb57d205392f63 | 09 December 2016, 18:21:29 UTC |
c700eb5 | Steven Johnson | 09 December 2016, 00:53:49 UTC | Revamp tests to only require linkage, not correct runtime execution Former-commit-id: ca566e219fdaa5c274e0801f48afe517c933d5b4 | 09 December 2016, 00:53:49 UTC |
9d267f1 | Steven Johnson | 09 December 2016, 00:07:33 UTC | Merge branch 'master' into gpp Former-commit-id: 1ef21ef3e944f5e87de70585bca74af5e71e89dd | 09 December 2016, 00:07:33 UTC |
bbc6c0f | Zalman Stern | 08 December 2016, 23:38:14 UTC | Merge pull request #1664 from halide/require Add require() operator Former-commit-id: 8511535089b45f60425532955824edaa46d03d54 | 08 December 2016, 23:38:14 UTC |
102b138 | Zalman Stern | 08 December 2016, 23:30:45 UTC | Merge pull request #1667 from halide/cuda_mat_mul_tests cuda matrix multiply fixes Former-commit-id: 1d9450748cb0236c996a0976ae7f0dc0beac870d | 08 December 2016, 23:30:45 UTC |
11f0da8 | Steven Johnson | 08 December 2016, 22:27:41 UTC | Fix typo Former-commit-id: b3448dc59d9ef1941d43807a3a3578bebc7df87c | 08 December 2016, 22:27:41 UTC |
812880f | Steven Johnson | 08 December 2016, 22:23:20 UTC | fix C++ name-mangling for GPU targets We never name-mangled the external functions if the target had a GPU feature; we never noticed this because we didn’t attempt to test it. Former-commit-id: f67e691870b57b3ccae3334e08df9397cf766f53 | 08 December 2016, 22:23:20 UTC |
402a453 | Dan Palermo | 08 December 2016, 21:10:23 UTC | Update from review comments: halide_hexagon_remote_power_hvx_on_perf(): - replace reinterpret casts, with unsigned long [long] in IDL - inline halide_hexagon_HAP_power_hvx_on - only increment power_ref_count in halide_hexagon_remote_power_hvx_on_perf - all power_hvx_on calls now call this function halide_hexagon_remote_power_hvx_on_mode(): - call halide_hexagon_remote_power_hvx_on_perf - change halide_hvx_power_normal to halide_hvx_power_nominal - compute low and nominal modes from max_mips & max_bus_bw - guarantee minimum values for max_mips & max_bus_bw - pass scalars, not halide_hvx_power_perf_t struct Former-commit-id: 35d1db38bf9ae15e011cc442ec118681d278955d | 08 December 2016, 21:10:23 UTC |
73f176a | Andrew Adams | 08 December 2016, 19:30:01 UTC | Merge branch 'master' of ssh://github.com/halide/Halide Former-commit-id: 2124b52cfca852b598ebf176e4c0b3b2a5ed5861 | 08 December 2016, 19:30:01 UTC |
5493c0f | Andrew Adams | 08 December 2016, 19:29:53 UTC | Avoid naked used of buffer_t in infer_input_bounds Former-commit-id: 1dd989c291f56ab027b3a356811fd9a77aefbef0 | 08 December 2016, 19:29:53 UTC |
15816ca | Steven Johnson | 08 December 2016, 17:47:20 UTC | Merge pull request #1669 from parkhc/refactor-runtime-build Refactoring src/CMakeLists.txt Former-commit-id: 401bea4650419bbb0d23184cebca7219f821293a | 08 December 2016, 17:47:20 UTC |
a8b2517 | Steven Johnson | 08 December 2016, 01:29:40 UTC | Merge pull request #1668 from halide/stubby Add more variants to stubtest Former-commit-id: a7db4d5316b7cca6d7edff257b2eddc51f2d4bb5 | 08 December 2016, 01:29:40 UTC |
9872c36 | Steven Johnson | 07 December 2016, 23:58:37 UTC | Add more variants to stubtest Add both simple and array inputs; rationalize names accordingly. Former-commit-id: 47c3c80adff70a0d9c74047e614acacc4712b77b | 07 December 2016, 23:58:37 UTC |
84b7196 | Andrew Adams | 07 December 2016, 22:55:39 UTC | Add missing code Former-commit-id: 804776807d0895bcde12f751adea1342ece2de94 | 07 December 2016, 22:55:39 UTC |
5954141 | Andrew Adams | 07 December 2016, 22:37:34 UTC | Formatting tweaks Former-commit-id: e5828b3e9f97c33c9eea8f03d261ff3b376d577f | 07 December 2016, 22:37:34 UTC |
b656537 | Andrew Adams | 07 December 2016, 22:33:14 UTC | Cleanups Moved the allocation fragmenting logic into Halide proper Made it a generator and added a makefile Former-commit-id: 844d969e8f5df401857ff866814a79f82ad0521f | 07 December 2016, 22:33:14 UTC |
9d002a1 | Andrew Adams | 07 December 2016, 21:24:32 UTC | Testing branch for fast cuda mat mul Former-commit-id: 92b3c1f42735f64e03cc695c3a064c7f3a6d700d | 07 December 2016, 21:24:32 UTC |
7552c23 | Zalman Stern | 07 December 2016, 18:57:43 UTC | Merge pull request #1666 from halide/llvm Update llvm error handling Former-commit-id: 5b3a8da1ee21e636207a2cec168748e04b7a218b | 07 December 2016, 18:57:43 UTC |
9c89eae | Hyunchul Park | 07 December 2016, 05:17:53 UTC | Refactoring src/CMakeLists.txt Using macro for runtime module generation. Former-commit-id: df4ed1ed509be003327d9584eeddbf1581a134dc | 07 December 2016, 18:52:52 UTC |
4186661 | Steven Johnson | 07 December 2016, 02:02:37 UTC | Fix Part 2 Former-commit-id: e84d1d2d2af4071e960f72f8814d4633060906f8 | 07 December 2016, 02:02:37 UTC |
a1822ec | Steven Johnson | 07 December 2016, 01:51:36 UTC | Update llvm error handling LLVM >= 4.0 should prefer explicit llvm::expectedToErrorOr(). Former-commit-id: a1cfa8b592aec25a8068419d60c2fff1af6c37e2 | 07 December 2016, 01:51:36 UTC |
6ca21ab | Andrew Adams | 07 December 2016, 01:33:48 UTC | Add missing consts Former-commit-id: 5f873c2c85bb1ad9f8c77e79bba961a0fecc6217 | 07 December 2016, 01:33:48 UTC |
db46cc5 | Andrew Adams | 07 December 2016, 01:24:57 UTC | Fix realizing into multiple existing buffers The natural way to realize into multiple existing buffers currently is to put them in a temporary Realization: f.realize({im1, im2}); This doesn't do precisely you want (it used to, before the Buffer change). The Realization constructor makes a copy of those buffer objects that it can own, so you'll lose any mutation of the metadata (e.g. device allocations). It's also different to this: f.realize(im1); which takes im1 by reference and updates the metadata This PR adds a new realization-like class that collects an array of mutable references to existing buffers. It's a temporary type solely used for passing groups of buffers to realize and infer_input_bounds. It changes the meaning of f.realize({im1, im2}) to take im1 and im2 by reference, the way it used to be. Former-commit-id: 73ee0d68d2f0d9b0b36631cf18c70fc6979111f6 | 07 December 2016, 01:24:57 UTC |
095adc1 | Steven Johnson | 06 December 2016, 19:39:42 UTC | Add require() operator require() is essentially a runtime assertion; it verifies that an Expr satisfies a precondition (terminating via halide_error() if it does not). Since this inserts runtime checks, it needs to be used with caution: inserting into an inner loop could severely degrade performance. The intended use is for: — preconditions on Param<> inputs that need failure rather than silent clamping — debugging, in situations where print()/print_when() aren’t adequate — in the future: unit testing, via enhancements to Generator Former-commit-id: fd348df611db756d9ede2e625768108037ed6611 | 06 December 2016, 19:39:42 UTC |
e7b04e5 | Z Stern | 06 December 2016, 09:08:07 UTC | Reformat comment into Doxygen comment for file. Former-commit-id: f651d51d97b75f12ba68f1cbfca914724136d121 | 06 December 2016, 09:08:07 UTC |
efeb9c6 | Zalman Stern | 06 December 2016, 09:02:23 UTC | Merge pull request #1663 from kgnk/readd_halide_image_h Re-add halide_image.h Former-commit-id: 743b96c37a36b08494d42b737c7a782c0abf7098 | 06 December 2016, 09:02:23 UTC |
b396d85 | Khouri Giordano | 06 December 2016, 07:09:18 UTC | add comment explaining use Former-commit-id: e1db28d4762d6e2d75ff53354606a5500e48cdb1 | 06 December 2016, 07:09:18 UTC |
1cce424 | Khouri Giordano | 06 December 2016, 01:10:04 UTC | readd tools/halide_image.h Former-commit-id: e222c5e47034c2c3ea4322ff293caaf04596d831 | 06 December 2016, 01:10:04 UTC |
0f1d237 | Khouri Giordano | 06 December 2016, 00:44:54 UTC | Merge remote-tracking branch 'refs/remotes/halide/master' Former-commit-id: 8bb2148917f777f811e2045f3036ff6ce508b778 | 06 December 2016, 00:44:54 UTC |
5931768 | Z Stern | 06 December 2016, 00:12:26 UTC | Update Metal demo to match runtime declarations for halide_metal_acquire_context and halide_metal_release_context. Update to support all ipad orientations. Former-commit-id: 20e0e00ca4e16fab48ce7b462fa669add9a54253 | 06 December 2016, 00:16:10 UTC |