bcm5719-llvm/llvm/test/Transforms/SLPVectorizer/PowerPC, branch meklort-10.0.1Project Ortega BCM5719 LLVMhttps://git.raptorcs.com/git/bcm5719-llvm/atom?h=meklort-10.0.12019-04-17T04:52:47+00:00Revert "Temporarily Revert "Add basic loop fusion pass.""2019-04-17T04:52:47+00:00Eric Christopherechristo@gmail.com2019-04-17T04:52:47+00:00urn:sha1:cee313d288a4faf0355d76fb6e0e927e211d08a5
The reversion apparently deleted the test/Transforms directory.
Will be re-reverting again.
llvm-svn: 358552
Temporarily Revert "Add basic loop fusion pass."2019-04-17T02:12:23+00:00Eric Christopherechristo@gmail.com2019-04-17T02:12:23+00:00urn:sha1:a86343512845c9c1fdbac865fea88aa5fce7142a
As it's causing some bot failures (and per request from kbarton).
This reverts commit r358543/ab70da07286e618016e78247e4a24fcb84077fda.
llvm-svn: 358546
[PowerPC] Update Vector Costs for P92019-01-26T01:18:48+00:00Nemanja Ivanovicnemanja.i.ibm@gmail.com2019-01-26T01:18:48+00:00urn:sha1:7d007ddedfd6f8f3756a17e0d280c38ab2e92f41
For the power9 CPU, vector operations consume a pair of execution units rather
than one execution unit like a scalar operation. Update the target transform
cost functions to reflect the higher cost of vector operations when targeting
Power9.
Patch by RolandF.
Differential revision: https://reviews.llvm.org/D55461
llvm-svn: 352261
[SLP]Update test checks for the SPL vectorizer, NFC.2019-01-11T20:21:14+00:00Alexey Bataeva.bataev@hotmail.com2019-01-11T20:21:14+00:00urn:sha1:ce2c8b3360c2270fb95a2a98bef2bedeef476415
llvm-svn: 350967
[SLP] Update tests checks, NFC.2018-01-05T14:40:04+00:00Alexey Bataeva.bataev@hotmail.com2018-01-05T14:40:04+00:00urn:sha1:988db0bd5074b0f176557aed130445e481d6953c
llvm-svn: 321869
[SLPVectorizer] Don't ignore scalar extraction instructions of aggregate value2017-12-14T19:35:43+00:00Guozhi Weicarrot@google.com2017-12-14T19:35:43+00:00urn:sha1:d22d1b953dabb160c41ae268fffc180bdd14d9e5
In SLPVectorizer, the vector build instructions (insertvalue for aggregate type) is passed to BoUpSLP.buildTree, it is treated as UserIgnoreList, so later in cost estimation, the cost of these instructions are not counted.
For aggregate value, later usage are more likely to be done in scalar registers, either used as individual scalars or used as a whole for function call or return value. Ignore scalar extraction instructions may cause too aggressive vectorization for aggregate values, and slow down performance. So for vectorization of aggregate value, the scalar extraction instructions are required in cost estimation.
Differential Revision: https://reviews.llvm.org/D41139
llvm-svn: 320736
[SLP] Pass in correct alignment when query memory access cost2016-05-31T20:41:19+00:00Guozhi Weicarrot@google.com2016-05-31T20:41:19+00:00urn:sha1:b994f4cdbcb628f16698015d4a345744a02910c7
This patch fixes bug https://llvm.org/bugs/show_bug.cgi?id=27897.
When query memory access cost, current SLP always passes in alignment value of 1 (unaligned), so it gets a very high cost of scalar memory access, and wrongly vectorize memory loads in the test case.
It can be fixed by simply giving correct alignment.
llvm-svn: 271333