https://github.com/halide/Halide

sort by:
Revision Author Date Message Commit Date
1f3bddc Revert data generation settings to the same as the last successful x86 batch 14 January 2019, 01:13:54 UTC
ac578eb Start from the arm weights 13 January 2019, 18:10:55 UTC
17f637d Merge branch 'standalone_autoscheduler_arm_worker_amazon' of https://github.com/halide/halide into standalone_autoscheduler_arm_worker_amazon 13 January 2019, 18:03:42 UTC
f2e106a Increment ARM bots to gen5 13 January 2019, 18:03:13 UTC
2a91456 Increment ARM bots to gen5 13 January 2019, 09:13:10 UTC
a895ed3 Merge branch 'standalone_autoscheduler_arm_worker_amazon' of https://github.com/halide/halide into standalone_autoscheduler_arm_worker_amazon 13 January 2019, 08:56:15 UTC
8200216 new arm weights 13 January 2019, 08:56:09 UTC
21bf0aa Increment ARM data generation 13 January 2019, 03:40:41 UTC
9088f8a Reduce max stage size 13 January 2019, 02:47:15 UTC
99f55a7 Some changes to increase chances of things working 13 January 2019, 02:44:27 UTC
c57af49 Fix generation upload of ___started 12 January 2019, 19:30:08 UTC
fcf01df gen3 ARM autotune: keep most sample data 12 January 2019, 19:23:16 UTC
75fa71a Update for gen2 ARM data generation - Only capture sample.sample file in zip - Push to gen2 directory 12 January 2019, 06:46:09 UTC
e64f1a2 Fix random dropout, beam size for sample 0 12 January 2019, 06:28:14 UTC
ddea998 Put s3 objects in a folder for differentiating generations 12 January 2019, 01:38:07 UTC
8d7a5be Use already-existing RunGenMain.o 12 January 2019, 01:31:14 UTC
d96cbd9 Fix autotune_arm_worker.sh (for AWS) - Correct parallelism factor - Parallel compile step - Separately compile RunGenMain.cpp for speed 12 January 2019, 01:26:59 UTC
18a972e Merge remote-tracking branch 'origin/standalone_autoscheduler_arm_worker' into standalone_autoscheduler_arm_worker_amazon 11 January 2019, 23:09:58 UTC
f7e87a5 Merge remote-tracking branch 'origin/standalone_autoscheduler' into standalone_autoscheduler_arm_worker 11 January 2019, 22:37:42 UTC
fa94297 Merge branch 'master' into standalone_autoscheduler 11 January 2019, 22:17:24 UTC
b0178f5 Allow slower training samples 11 January 2019, 22:11:52 UTC
6c9b0b3 Fix machine params mistake 11 January 2019, 22:11:41 UTC
75bffd1 Add some arm weights 11 January 2019, 21:54:36 UTC
0a4f800 Rename fit_and_slice_3x4 -> bgu 11 January 2019, 21:04:23 UTC
9017527 Fix dropout 11 January 2019, 20:38:23 UTC
bf883c1 Merge pull request #3574 from halide/srj-llvm-fix Fix simd_op_check for trunk LLVM on x86 (Issue #3545) 11 January 2019, 18:58:17 UTC
c3d4cbe Merge remote-tracking branch 'origin/standalone_autoscheduler' into standalone_autoscheduler_arm_worker 11 January 2019, 03:06:16 UTC
1369fc1 Fix hostname in autotune_loop_arm.sh 11 January 2019, 01:40:02 UTC
3b2811b Add some Func names 11 January 2019, 01:37:11 UTC
9d18532 Add missing change to FunctionDAG 11 January 2019, 01:33:14 UTC
2f43828 Fix random dropout math 11 January 2019, 01:33:07 UTC
e884692 Merge branch 'standalone_autoscheduler' of https://github.com/Halide/Halide into standalone_autoscheduler 11 January 2019, 01:04:11 UTC
0ad131c Speed up autoscheduling slightly 11 January 2019, 01:04:03 UTC
1aa514a Merge pull request #3572 from halide/srj-hdr-plaid Add apps/burst_camera_pipe 11 January 2019, 00:32:16 UTC
9ecd49f Merge pull request #3562 from halide/srj-pybuf Handle NumPy's 'l' format in PyBuffer 11 January 2019, 00:08:25 UTC
09039d8 Merge pull request #3573 from halide/revert-3564-srj-llvm-fix Revert "Update for trunk LLVM" 11 January 2019, 00:06:36 UTC
63f370d Fix simd_op_check for trunk LLVM on x86 (Issue #3545) From https://reviews.llvm.org/rL349892 10 January 2019, 23:32:02 UTC
2a12974 ARM worker tweaks for AWS 10 January 2019, 23:05:01 UTC
a2e96de fix 10 January 2019, 23:04:59 UTC
492f788 Revert "Update for trunk LLVM" 10 January 2019, 23:00:27 UTC
0e3492e Update apps/blur for autotuning work Note that a BoundaryConditions::repeat_edge() was added to the algorithm, to facilitate autotuning more easily 10 January 2019, 22:42:36 UTC
dafab96 Add machine_params=$(HL_MACHINE_PARAMS) 10 January 2019, 21:55:19 UTC
6bff69d Merge branch 'standalone_autoscheduler' into srj-hdr-plaid 10 January 2019, 21:54:40 UTC
193be4e rename hdrplaid -> burst_camera_pipe 10 January 2019, 21:54:05 UTC
cd84247 Merge pull request #3571 from halide/srj-classic-autotune Add autotune_classic.sh and support 10 January 2019, 21:10:57 UTC
53435b9 Add autotune_classic.sh and support This is a trivial script to try running 'classic' autoscheduler with the multiple variants of MachineParams used in the original paper; all it does is disable benchmarking of non-classic variants, and run 'make test' in the current directory repeatedly with different values (removing any classic artifacts from bin to ensure a rebuild occurs). 10 January 2019, 21:05:59 UTC
0ff9222 Update readme 10 January 2019, 20:52:27 UTC
3f4d9c4 Merge branch 'srj-hdr-plaid' of https://github.com/Halide/Halide into srj-hdr-plaid 10 January 2019, 20:44:17 UTC
2e50655 Make demosaic more idiomatic 10 January 2019, 20:44:12 UTC
de76334 Fix issue with empty options list 10 January 2019, 20:44:00 UTC
a774ec0 Convert various funcs to buffers 10 January 2019, 20:15:26 UTC
3c0ab8e Add apps/hdr_plaid 10 January 2019, 19:52:47 UTC
1e05349 Monkey-patch class AutoSchedule 10 January 2019, 19:50:15 UTC
0305d46 Force-inline pointwise stages before boundary conditions 10 January 2019, 19:49:43 UTC
0eed105 Merge branch 'standalone_autoscheduler' of https://github.com/Halide/Halide into standalone_autoscheduler 10 January 2019, 18:14:11 UTC
4752f41 Fresh weights 10 January 2019, 18:13:57 UTC
2708be7 Merge pull request #3469 from vgundlur/hex-dma3 Hex dma3 10 January 2019, 18:08:29 UTC
b6b7b28 Remove explicit setting of HL_MACHINE_PARAMS 10 January 2019, 09:08:03 UTC
24e0f8f Physical cores instead of logical cores 10 January 2019, 09:04:37 UTC
2b48014 Fix erroneous comparison 10 January 2019, 09:03:24 UTC
9888c16 Merge branch 'master' into hex-dma3 10 January 2019, 06:22:58 UTC
e94808d Merge pull request #3568 from halide/precompiled-test-headers Precompiled test headers 10 January 2019, 05:56:56 UTC
b82ebe4 Extra simplification pass before unrolling 10 January 2019, 05:52:58 UTC
b52bf57 Make it possible to autoschedule the cost model itself 10 January 2019, 05:52:41 UTC
ad2a0cd Use proper variable to point to weights dir in resnet makefile 10 January 2019, 05:51:36 UTC
e537ca4 Increase benchmarking time in random pipeline generator 10 January 2019, 05:51:03 UTC
49fab26 Fix possible factorization simplification in random pipeline generator 10 January 2019, 05:50:45 UTC
7570aea Use explicit bounds in camera pipe to make autotuner work 10 January 2019, 05:49:20 UTC
9084f2c Use more consistent benchmarking methodology 10 January 2019, 05:49:06 UTC
24db4f2 Always use large buffers for lens blur 10 January 2019, 05:47:25 UTC
e5f3d23 Use explicit bounds in resnet 10 January 2019, 05:46:26 UTC
3eb429e Add disabled code to turn estimates into bound directives 10 January 2019, 05:45:42 UTC
92c4996 autotune_loop does one iteration. Run it in a loop if you want more 10 January 2019, 05:45:21 UTC
99d67f9 Change the meaning of dropout to be normalized across the number of decisions to be made 10 January 2019, 05:45:03 UTC
a0fa880 Fix wrong estimate on harris 10 January 2019, 03:36:11 UTC
85484e7 remove oopsie 10 January 2019, 00:22:09 UTC
c18a851 Add apps/fit_and_slice_3x4 10 January 2019, 00:21:36 UTC
9e3614e Moving test precompilation to Halide.h target 10 January 2019, 00:16:39 UTC
ea61b9a nuke useless files 09 January 2019, 23:43:02 UTC
0364432 Merge branch 'standalone_autoscheduler' of https://github.com/halide/Halide into standalone_autoscheduler 09 January 2019, 23:38:07 UTC
2252bf1 Add apps/iir_blur_generator This is basically a clone of the IIR Blur generator from apps/HelloMatlab, with appropriate machinery to do autoscheduler testing and tuning. 09 January 2019, 23:37:47 UTC
c69b33a Merge branch 'standalone_autoscheduler' of https://github.com/Halide/Halide into standalone_autoscheduler 09 January 2019, 23:32:50 UTC
77c8965 Fresh weights 09 January 2019, 23:32:43 UTC
e48909e Make resnet parallel 09 January 2019, 23:25:43 UTC
1ba89f9 Removing -H flag that was used for debugging. 09 January 2019, 23:24:24 UTC
ad77bd9 Fix namespace nonsense 09 January 2019, 23:16:24 UTC
03cfea3 Precompile separate headers for tests vs default 09 January 2019, 23:15:48 UTC
74b16d8 Merge branch 'standalone_autoscheduler' of https://github.com/Halide/Halide into standalone_autoscheduler 09 January 2019, 23:01:15 UTC
9d96eba Inline things that should trivially be inlined 09 January 2019, 23:00:30 UTC
31c207f Merge pull request #3567 from halide/srj-resnet Add classic auto-schedule testing to apps/resnet 09 January 2019, 22:59:32 UTC
b73863a Add classic auto-schedule testing to apps/resnet Note that (unlike most other apps) this doesn't attempt to run all three in the same run; it selects one of the options via command-line flag. 'make test' runs all three in sequence. Note also that the 'manual' schedule is known to be awful (it's just enough compute-roots added to make the runtime tractable); improvement is left as an exercise to the reader. 09 January 2019, 22:52:58 UTC
eebc6fe Move Halide.h to front of correctness test includes to precompile header 09 January 2019, 22:51:05 UTC
934281c Merge pull request #3566 from benoitsteiner/standalone_autoscheduler autoscheduler improvements 09 January 2019, 22:27:34 UTC
0835680 Merge branch 'standalone_autoscheduler' of https://github.com/Halide/Halide into standalone_autoscheduler 09 January 2019, 22:25:24 UTC
335f2f6 Fresh weights 09 January 2019, 22:25:12 UTC
2ba4544 Fixed the spelling of halide 09 January 2019, 21:36:21 UTC
f5a8c10 Added an API to be able to call the autoscheduler code from c++ 09 January 2019, 21:35:54 UTC
872b556 Track versions of the featurization. This simplifies the lifecycle management features extracted ahead of time, for example in order to build a training set for the cost model. 09 January 2019, 21:35:09 UTC
bc0df86 Code cleanup Added the definition of the new autoscheduler API 09 January 2019, 21:35:09 UTC
57f9320 Moved the cost model and network size code into the halide namespace 09 January 2019, 21:35:09 UTC
back to top