Dehao Chen
7d230325ef
Increases full-unroll threshold.
Summary:
The default threshold for fully unroll is too conservative. This patch doubles the full-unroll threshold
This change will affect the following speccpu2006 benchmarks (performance numbers were collected from Intel Sandybridge):
Performance:
403 0.11%
433 0.51%
445 0.48%
447 3.50%
453 1.49%
464 0.75%
Code size:
403 0.56%
433 0.96%
445 2.16%
447 2.96%
453 0.94%
464 8.02%
The compiler time overhead is similar with code size.
Reviewers: davidxl, mkuper, mzolotukhin, hfinkel, chandlerc
Reviewed By: hfinkel, chandlerc
Subscribers: mehdi_amini, zzheng, efriedma, haicheng, hfinkel, llvm-commits
Differential Revision: https://reviews.llvm.org/D28368
llvm-svn: 295538
2017-02-18 03:46:51 +00:00
..
2017-02-14 16:28:32 +00:00
2017-02-11 01:53:04 +00:00
2016-12-03 00:41:43 +00:00
2017-02-18 03:46:51 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-07-27 23:53:58 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-12-16 19:12:02 +00:00
2016-10-06 23:57:25 +00:00
2016-12-16 19:12:02 +00:00
2016-11-11 22:51:46 +00:00
2016-10-06 23:57:25 +00:00
2016-12-22 00:45:21 +00:00
2016-10-19 19:22:02 +00:00
2016-11-09 22:25:19 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-12-19 17:13:37 +00:00
2017-02-10 21:09:07 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-07-24 07:24:54 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-07-06 14:26:59 +00:00
2016-09-26 17:08:37 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-07 15:20:13 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-12-07 15:03:32 +00:00
2016-10-06 23:57:25 +00:00
2016-12-16 19:12:02 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2017-02-17 16:09:07 +00:00
2017-02-14 16:28:32 +00:00
2016-10-31 13:17:31 +00:00
2016-10-31 13:17:31 +00:00
2016-10-31 13:17:31 +00:00
2016-12-16 19:12:02 +00:00
2016-09-02 16:19:22 +00:00
2016-10-06 23:57:25 +00:00
2017-01-09 19:05:29 +00:00
2017-01-26 10:41:09 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2017-02-12 09:32:53 +00:00
2016-06-15 00:35:26 +00:00
2016-11-11 22:51:46 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2017-01-19 00:42:28 +00:00
2016-10-06 23:57:25 +00:00
2016-08-12 22:47:13 +00:00
2017-02-12 09:32:53 +00:00
2017-01-19 00:42:28 +00:00
2016-10-06 23:57:25 +00:00
2016-06-29 10:01:06 +00:00
2016-10-06 23:57:25 +00:00
2017-01-18 19:02:52 +00:00
2016-09-21 16:50:24 +00:00
2017-02-14 16:28:32 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-09-26 17:08:37 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-12-13 20:38:18 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00
2016-10-06 23:57:25 +00:00