https://github.com/halide/Halide

sort by:
Revision Author Date Message Commit Date
f8057f8 Add ability to do parallel random probes in-process 18 August 2020, 23:07:25 UTC
2a2d98e Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 18 August 2020, 02:01:27 UTC
93d23e4 fixed bugs in demosaic apps 18 August 2020, 02:01:17 UTC
f0a5cfa Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 18 August 2020, 01:53:36 UTC
fc09851 fix benchmark models and add tensorflow comparison 18 August 2020, 01:53:15 UTC
cdfd950 Some progress on getting multires working 17 August 2020, 23:40:40 UTC
062777d Reschedule train_cost_model. Use 8 threads when retraining. 17 August 2020, 23:11:31 UTC
0856036 Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 17 August 2020, 19:23:46 UTC
cb4591e Add timing information to retrain_cost_model.cpp 17 August 2020, 19:23:44 UTC
782a166 Update random pipeline data slurm script * Generate more samples * Shut off core dump files! 17 August 2020, 16:20:18 UTC
5a509bd adding process 17 August 2020, 16:18:53 UTC
7ed4f09 :Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 17 August 2020, 16:09:26 UTC
d3c90f7 adding demosaicing apps 17 August 2020, 16:09:09 UTC
88a8269 Add epoch completed message 17 August 2020, 14:26:13 UTC
461b64a modify burst camera pipe (didn't work) 17 August 2020, 13:56:45 UTC
d77ac75 Fix stats for mobilenet 17 August 2020, 13:42:53 UTC
e64ec2b Always consider inline options for partial schedule nodes 17 August 2020, 02:40:14 UTC
2bc7025 Add partial schedule support 17 August 2020, 02:40:14 UTC
035060e Use <= when checking amount of shared mem 17 August 2020, 02:40:14 UTC
5d0766f Skip candidate compute locations with allocations that are too large 17 August 2020, 02:40:13 UTC
b31d52e Skip candidate compute locations that use too much shared memory 17 August 2020, 02:40:13 UTC
e0e43f0 Add state tests 17 August 2020, 02:40:13 UTC
61bb1c1 For inlined funcs, consider all its consumers when finding the deepest common ancestor 17 August 2020, 02:40:13 UTC
4620c4f Use active threads when computing warp utilization 17 August 2020, 02:40:13 UTC
b5ba27c Delete dead TODO 17 August 2020, 00:27:24 UTC
e989614 Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 17 August 2020, 00:26:09 UTC
fa553cd Fast random initialization using xorshift 17 August 2020, 00:26:02 UTC
b60615e fix run all gradient autoschedule 16 August 2020, 22:36:12 UTC
dc9795a Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 16 August 2020, 22:25:14 UTC
165c23b add no gradient autoscheduler flag 16 August 2020, 22:24:38 UTC
edaa15f Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 16 August 2020, 20:56:09 UTC
d6c8a84 Use RunGenMain.o 16 August 2020, 20:55:59 UTC
c079842 Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 16 August 2020, 20:48:52 UTC
1f8296e Reschedule BGU This makes it less sensitive to atomic add vs cas loop flakiness 16 August 2020, 20:48:31 UTC
e118cbc Add missing .mat files 16 August 2020, 19:38:16 UTC
310b34d Add -O3 when compiling RunGen 16 August 2020, 19:26:33 UTC
c693325 Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 16 August 2020, 19:13:58 UTC
a5cbad4 Add manual script 16 August 2020, 19:13:51 UTC
42791b1 Add missing copy_to_host calls 16 August 2020, 18:22:45 UTC
2629b01 remove unused script 16 August 2020, 18:11:51 UTC
1c6f3e7 mobilenet script 16 August 2020, 18:09:03 UTC
10d1f9d Add missing image files 16 August 2020, 17:28:29 UTC
1fbb949 Add missing header and copy_to_host to iir_blur 16 August 2020, 16:56:24 UTC
2b78dd7 Set max registers in ptxas command 16 August 2020, 16:07:39 UTC
6c822b7 Check if best_schedule file is missing 15 August 2020, 15:23:29 UTC
e7f2176 Add 'loading samples' message 15 August 2020, 14:55:04 UTC
f5d27c5 Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 15 August 2020, 14:36:51 UTC
b72941c Remove files after generating data 15 August 2020, 14:36:08 UTC
a7a633f Make random_pipeline zero-initialize buffers for speed during data generation 15 August 2020, 06:10:18 UTC
0721482 Adding autotuning helpers: - Slurm script for random pipeline data gathering on Satori - Slurm one-liner to launch interactive session on Satori 15 August 2020, 03:39:52 UTC
bdb4cf4 Add Func names to lens_blur_generator.cpp 15 August 2020, 02:19:36 UTC
1436f6b Fix benchmark queue timeout 15 August 2020, 01:26:13 UTC
5b72a8b Update generate_autotune_results to compute capability 7.0 15 August 2020, 01:15:35 UTC
394e23c Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 15 August 2020, 00:02:39 UTC
683d4b5 Add more cuda generations. Compile to SASS if possible 15 August 2020, 00:02:29 UTC
2c75927 Order benchmark files by time 14 August 2020, 23:07:13 UTC
476f971 Add copy-to-host to lens blur 14 August 2020, 22:29:07 UTC
d669c68 Add multi-batch support to autotune_loop 14 August 2020, 21:39:33 UTC
31f0eb5 Remove scatter plot data point limit 14 August 2020, 13:54:27 UTC
80526b7 Fix date in generate_autotune_results.sh 14 August 2020, 00:45:07 UTC
46e3933 Don't print name if node is null 13 August 2020, 19:48:16 UTC
f77bce8 Reduce benchmark timeout and prevent dir name collisions 13 August 2020, 19:03:36 UTC
a5d91b4 Fix GPU barrier deadlocks Partition loops and trim no ops were messing with loops containing thread barriers, potentially causing warp divergence and deadlock. Also we were generating too many thread barriers in some cases, possibly due to new unordered block mutation stuff. Made detection of whether we need to inject a barrier at the end of a serial loop more explicit. 13 August 2020, 17:37:30 UTC
a21f917 Use 3 bytes for random batch ids 13 August 2020, 15:46:18 UTC
45a400e Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 13 August 2020, 15:10:35 UTC
8df04e8 Add random batch ids 13 August 2020, 15:08:58 UTC
bd2762f Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 13 August 2020, 14:53:51 UTC
a7ed332 add mobilenet benchmark 13 August 2020, 14:53:35 UTC
cec69af silent mkdir error message 13 August 2020, 14:44:12 UTC
8d786fc Add -p when creating 'best' 13 August 2020, 14:30:47 UTC
d00f3cb Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 13 August 2020, 14:25:13 UTC
292acc4 add missing mkdir 13 August 2020, 14:23:52 UTC
7c3a3c9 Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 13 August 2020, 14:23:35 UTC
7b2b5e0 Add mkdir for 'best' directory 13 August 2020, 14:23:30 UTC
7088d0f Enable benchmark queue as default 13 August 2020, 14:22:40 UTC
25aaa8e Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 13 August 2020, 01:44:23 UTC
dbe9768 fix autotuning scripts 13 August 2020, 01:44:06 UTC
100f4f9 Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 12 August 2020, 22:26:12 UTC
0a97eaa Remove scatter plot 12 August 2020, 22:25:59 UTC
76bd752 fix autotune script for older bash 12 August 2020, 22:16:46 UTC
2f7697b Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 12 August 2020, 22:16:07 UTC
30e4b0c Remove old scripts 12 August 2020, 22:15:51 UTC
985c68d splitted mobilenet 12 August 2020, 20:08:40 UTC
275fe43 Move GPU selection to before benchmark job is launched 12 August 2020, 16:01:30 UTC
d0594cb Change debug level for mem accesses 12 August 2020, 15:59:58 UTC
1105e8f Reset weights 12 August 2020, 13:46:46 UTC
4ac91c9 Change beam search default 12 August 2020, 13:46:41 UTC
0f951c6 Add data point limit to scatter plot 12 August 2020, 03:37:15 UTC
b62e157 Fix generator Makefile rule 12 August 2020, 02:53:47 UTC
5556922 Add flag to enable beam search to autotune_loop.sh 12 August 2020, 02:42:39 UTC
62351d0 Merge branch 'standalone_autoscheduler_gpu' of https://github.com/halide/Halide into standalone_autoscheduler_gpu 12 August 2020, 02:15:26 UTC
4202902 Append a filename suffix when a GPU is in use in the benchmark queue 12 August 2020, 02:15:08 UTC
abc3bc3 Remove host-cuda and HL_TARGET from Makefiles 11 August 2020, 20:12:45 UTC
d233fa0 Schedule last stage of stencil chain on GPU 11 August 2020, 19:11:57 UTC
2b70263 Tidy up scripts 11 August 2020, 16:39:54 UTC
07d7ba8 Remove loop opt flag 11 August 2020, 01:54:17 UTC
ba7ac59 Skip comments in LoopNestParser 10 August 2020, 20:33:59 UTC
0af7517 Add test_pointwise_generator 10 August 2020, 19:37:58 UTC
fb1c9af Fix default variable naming in scripts 10 August 2020, 19:19:52 UTC
a26aae5 Don't fuse blocks that have constant extent = 1 10 August 2020, 18:14:52 UTC
back to top