Matt Arsenault
ab262a454f
LoopUnroll: Allow analyzing intrinsic call costs
...
I'm not sure why the code here is skipping calls since
TTI does try to do something for general calls, but it
at least should allow intrinsics.
Skip intrinsics that should not be omitted as calls, which
is by far the most common case on AMDGPU.
llvm-svn: 335645
2018-06-26 18:51:17 +00:00
..
2017-06-28 18:53:09 +00:00
2018-06-26 18:51:17 +00:00
2017-10-23 08:05:14 +00:00
2018-04-03 03:39:43 +00:00
2017-10-19 18:16:31 +00:00
2017-08-20 12:34:29 +00:00
2017-08-02 20:35:29 +00:00
2018-03-15 21:34:43 +00:00
2018-03-02 16:22:32 +00:00
2018-05-09 02:40:45 +00:00
2017-03-04 05:20:02 +00:00
2017-08-02 20:35:29 +00:00
2018-03-26 11:31:46 +00:00
2017-10-31 10:47:46 +00:00
2017-05-12 15:30:58 +00:00
2017-08-02 20:35:29 +00:00
2017-03-26 16:46:53 +00:00
2018-04-18 12:29:24 +00:00
2017-03-16 21:07:48 +00:00
2017-04-17 05:38:28 +00:00
2018-04-06 13:57:21 +00:00
2017-08-03 23:42:58 +00:00
2018-02-08 07:16:29 +00:00
2017-08-29 17:24:09 +00:00
2017-08-02 20:35:29 +00:00
2018-05-09 02:40:45 +00:00
2018-05-09 02:40:45 +00:00
2017-08-02 20:35:29 +00:00
2017-08-02 20:35:29 +00:00
2017-08-02 20:35:29 +00:00
2017-07-13 13:21:23 +00:00
2017-09-15 13:29:33 +00:00
2017-08-02 20:35:29 +00:00
2017-09-15 15:56:05 +00:00
2017-10-20 10:08:47 +00:00
2017-08-02 20:35:29 +00:00
2017-09-28 02:45:42 +00:00
2017-06-28 17:01:15 +00:00
2018-03-02 16:22:32 +00:00
2017-08-02 20:35:29 +00:00