Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | [PowerPC] Use rldicr instruction for AND with an immediate if possible | Nemanja Ivanovic | 2017-02-24 | 1 | -0/+11 |
| | | | | | | | | | | | Emit clrrdi (extended mnemonic for rldicr) for AND-ing with masks that clear bits from the right hand size. Committing on behalf of Hiroshi Inoue. Differential Revision: https://reviews.llvm.org/D29388 llvm-svn: 296143 | ||||
* | Adding -verify-machineinstrs option to PowerPC tests | Ehsan Amiri | 2016-08-03 | 1 | -1/+1 |
| | | | | | | | | | | | Currently we have a number of tests that fail with -verify-machineinstrs. To detect this cases earlier we add the option to the testcases with the exception of tests that will currently fail with this option. PR 27456 keeps track of this failures. No code review, as discussed with Hal Finkel. llvm-svn: 277624 | ||||
* | PPC: Optimize rldicl generation for masked shifts | Hal Finkel | 2013-11-20 | 1 | -0/+16 |
Masking operations (where only some number of the low bits are being kept) are selected to rldicl(x, 0, mb). If x is a logical right shift (which would become rldicl(y, 64-n, n)), we might be able to fold the two instructions together: rldicl(rldicl(x, 64-n, n), 0, mb) -> rldicl(x, 64-n, mb) for n <= mb The right shift is really a left rotate followed by a mask, and if the explicit mask is a more-restrictive sub-mask of the mask implied by the shift, only one rldicl is needed. llvm-svn: 195185 |