summaryrefslogtreecommitdiffstats
path: root/llvm/test/Transforms/AtomicExpand
Commit message (Expand)AuthorAgeFilesLines
* Revert "Temporarily Revert "Add basic loop fusion pass.""Eric Christopher2019-04-1727-0/+2509
* Temporarily Revert "Add basic loop fusion pass."Eric Christopher2019-04-1727-2509/+0
* [AtomicExpand] Allow libcall expansion for non-zero address spaces (try 2)Philip Reames2019-03-061-0/+34
* Revert "[AtomicExpand] Allow libcall expansion for non-zero address spaces" f...Mitch Phillips2019-03-061-36/+0
* [AtomicExpand] Allow libcall expansion for non-zero address spacesPhilip Reames2019-03-051-0/+36
* Codegen support for atomicrmw fadd/fsubMatt Arsenault2019-01-223-0/+577
* Reapply "IR: Add fp operations to atomicrmw"Matt Arsenault2019-01-228-0/+264
* Revert r351778: IR: Add fp operations to atomicrmwChandler Carruth2019-01-228-252/+0
* IR: Add fp operations to atomicrmwMatt Arsenault2019-01-228-0/+252
* Allow FP types for atomicrmw xchgMatt Arsenault2019-01-173-0/+102
* AMDGPU: Expand atomicrmw nand in IRMatt Arsenault2018-10-022-0/+62
* [AtomicExpandPass] Widen partword atomicrmw or/xor/and before tryExpandAtomicRMWAlex Bradbury2018-08-171-0/+25
* Add address space mangling to lifetime intrinsicsMatt Arsenault2017-04-101-22/+22
* Support expanding partial-word cmpxchg to full-word cmpxchg in AtomicExpandPass.James Y Knight2016-06-171-0/+166
* ARM: use a pseudo-instruction for cmpxchg at -O0.Tim Northover2016-04-183-3/+3
* Add __atomic_* lowering to AtomicExpandPass.James Y Knight2016-04-122-0/+259
* This reverts commit r266002, r266011 and r266016.Rafael Espindola2016-04-122-259/+0
* Add __atomic_* lowering to AtomicExpandPass.James Y Knight2016-04-112-0/+259
* ARM: sink atomic release barrier as far as possible into cmpxchg.Tim Northover2016-02-222-17/+122
* [IR] Extend cmpxchg to allow pointer type operandsPhilip Reames2016-02-191-0/+85
* [IR] Add support for floating pointer atomic loads and storesPhilip Reames2015-12-161-0/+82
* [ARM] Emit clrex in the expanded cmpxchg fail block.Ahmed Bougacha2015-09-223-12/+56
* Fix an alignment error in `llvm::expandAtomicRMWToCmpXchg` without breaking t...Richard Diamond2015-08-062-0/+13
* Revert "Divide the primitive size in bits by eight so the initial load's alig...Renato Golin2015-08-061-8/+0
* Divide the primitive size in bits by eight so the initial load's alignment is inRichard Diamond2015-08-051-0/+8
* Use target-dependent emitLeading/TrailingFence instead of the target-independ...Robin Morisset2014-09-032-43/+44
* Rename AtomicExpandLoadLinked into AtomicExpandRobin Morisset2014-08-214-0/+690
OpenPOWER on IntegriCloud