llvm-project/polly/lib/Analysis
Tobias Grosser 8d4cb1a060 ScopInfo: Do not derive assumptions from all GEP pointer instructions
... but instead rely on the assumptions that we derive for load/store
instructions.

Before we were able to delinearize arrays, we used GEP pointer instructions
to derive information about the likely range of induction variables, which
gave us more freedom during loop scheduling. Today, this is not needed
any more as we delinearize multi-dimensional memory accesses and as part
of this process also "assume" that all accesses to these arrays remain
inbounds. The old derive-assumptions-from-GEP code has consequently become
mostly redundant. We drop it both to clean up our code, but also to improve
compile time. This change reduces the scop construction time for 3mm in
no-asserts mode on my machine from 48 to 37 ms.

llvm-svn: 280601
2016-09-03 21:55:25 +00:00
..
DependenceInfo.cpp Dependences: Only create flat StmtSchedule in presence of reductions 2016-09-02 23:40:15 +00:00
PolyhedralInfo.cpp [GSoC] Add PolyhedralInfo pass - new interface to polly analysis 2016-07-25 12:48:45 +00:00
ScopBuilder.cpp Simplify AccFuncMap to vector<> AccessFunctions 2016-08-21 11:09:19 +00:00
ScopDetection.cpp Drop '@brief' from doxygen comments 2016-09-02 06:33:33 +00:00
ScopDetectionDiagnostic.cpp Drop '@brief' from doxygen comments 2016-09-02 06:33:33 +00:00
ScopGraphPrinter.cpp Migrate from NodeType * to NodeRef. 2016-08-22 22:30:27 +00:00
ScopInfo.cpp ScopInfo: Do not derive assumptions from all GEP pointer instructions 2016-09-03 21:55:25 +00:00
ScopPass.cpp Decouple SCoP building logic from pass 2016-05-31 09:41:04 +00:00