forked from OSchip/llvm-project
8699492304
We can prove that some delinearized subscripts do not wrap around to become negative by the fact that they are from inbound geps of load/store locations. This helps improve the delinearisation in cases where we can't prove that they are non-negative from SCEV alone. Differential Revision: https://reviews.llvm.org/D48481 llvm-svn: 335481 |
||
|---|---|---|
| .. | ||
| AA.ll | ||
| Banerjee.ll | ||
| BasePtrBug.ll | ||
| Constraints.ll | ||
| Coupled.ll | ||
| DADelin.ll | ||
| ExactRDIV.ll | ||
| ExactSIV.ll | ||
| GCD.ll | ||
| Invariant.ll | ||
| MIVCheckConst.ll | ||
| NonAffineExpr.ll | ||
| NonCanonicalizedSubscript.ll | ||
| PR21585.ll | ||
| Preliminary.ll | ||
| Propagating.ll | ||
| Separability.ll | ||
| StrongSIV.ll | ||
| SymbolicRDIV.ll | ||
| SymbolicSIV.ll | ||
| UsefulGEP.ll | ||
| WeakCrossingSIV.ll | ||
| WeakZeroDstSIV.ll | ||
| WeakZeroSrcSIV.ll | ||
| ZIV.ll | ||