llvm-6502/lib/Analysis
Juergen Ributzka d3cf783ed1 [Constant Hoisting] Make the constant materialization cost operand dependent
Extend the target hook to take also the operand index into account when
calculating the cost of the constant materialization.

Related to <rdar://problem/16381500>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@204435 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-21 06:04:45 +00:00
..
IPA Consistent use of the noduplicate attribute. 2014-03-17 16:19:07 +00:00
AliasAnalysis.cpp IR: add a second ordering operand to cmpxhg for failure 2014-03-11 10:48:52 +00:00
AliasAnalysisCounter.cpp
AliasAnalysisEvaluator.cpp
AliasDebugger.cpp
AliasSetTracker.cpp
Analysis.cpp
BasicAliasAnalysis.cpp
BlockFrequencyInfo.cpp
BranchProbabilityInfo.cpp
CaptureTracking.cpp [C++11] Add range based accessors for the Use-Def chain of a Value. 2014-03-09 03:16:01 +00:00
CFG.cpp
CFGPrinter.cpp
CMakeLists.txt
CodeMetrics.cpp Consistent use of the noduplicate attribute. 2014-03-17 16:19:07 +00:00
ConstantFolding.cpp
CostModel.cpp
Delinearization.cpp
DependenceAnalysis.cpp
DominanceFrontier.cpp
DomPrinter.cpp
InstCount.cpp
InstructionSimplify.cpp [C++11] Add range based accessors for the Use-Def chain of a Value. 2014-03-09 03:16:01 +00:00
Interval.cpp
IntervalPartition.cpp
IVUsers.cpp PR17473: 2014-03-12 21:31:05 +00:00
LazyCallGraph.cpp [LCG] Ran clang-format over this too and it pointed out some fixes. 2014-03-10 02:14:14 +00:00
LazyValueInfo.cpp
LibCallAliasAnalysis.cpp
LibCallSemantics.cpp
Lint.cpp
LLVMBuild.txt
Loads.cpp
LoopInfo.cpp Consistent use of the noduplicate attribute. 2014-03-17 16:19:07 +00:00
LoopPass.cpp
Makefile
MemDepPrinter.cpp
MemoryBuiltins.cpp [C++11] Add range based accessors for the Use-Def chain of a Value. 2014-03-09 03:16:01 +00:00
MemoryDependenceAnalysis.cpp
ModuleDebugInfoPrinter.cpp [C++11] Change DebugInfoFinder to use range-based loops 2014-03-18 09:41:07 +00:00
NoAliasAnalysis.cpp
PHITransAddr.cpp [C++11] Add range based accessors for the Use-Def chain of a Value. 2014-03-09 03:16:01 +00:00
PostDominators.cpp
PtrUseVisitor.cpp [C++11] Add range based accessors for the Use-Def chain of a Value. 2014-03-09 03:16:01 +00:00
README.txt
RegionInfo.cpp
RegionPass.cpp
RegionPrinter.cpp
ScalarEvolution.cpp Remove some dead assignements found by scan-build 2014-03-15 22:13:15 +00:00
ScalarEvolutionAliasAnalysis.cpp
ScalarEvolutionExpander.cpp [C++11] Add range based accessors for the Use-Def chain of a Value. 2014-03-09 03:16:01 +00:00
ScalarEvolutionNormalization.cpp Add stride normalization to SCEV Normalize/Denormalize transformation. 2014-03-18 17:34:03 +00:00
SparsePropagation.cpp [C++11] Add range based accessors for the Use-Def chain of a Value. 2014-03-09 03:16:01 +00:00
TargetTransformInfo.cpp [Constant Hoisting] Make the constant materialization cost operand dependent 2014-03-21 06:04:45 +00:00
Trace.cpp
TypeBasedAliasAnalysis.cpp
ValueTracking.cpp [C++11] Add range based accessors for the Use-Def chain of a Value. 2014-03-09 03:16:01 +00:00

Analysis Opportunities:

//===---------------------------------------------------------------------===//

In test/Transforms/LoopStrengthReduce/quadradic-exit-value.ll, the
ScalarEvolution expression for %r is this:

  {1,+,3,+,2}<loop>

Outside the loop, this could be evaluated simply as (%n * %n), however
ScalarEvolution currently evaluates it as

  (-2 + (2 * (trunc i65 (((zext i64 (-2 + %n) to i65) * (zext i64 (-1 + %n) to i65)) /u 2) to i64)) + (3 * %n))

In addition to being much more complicated, it involves i65 arithmetic,
which is very inefficient when expanded into code.

//===---------------------------------------------------------------------===//

In formatValue in test/CodeGen/X86/lsr-delayed-fold.ll,

ScalarEvolution is forming this expression:

((trunc i64 (-1 * %arg5) to i32) + (trunc i64 %arg5 to i32) + (-1 * (trunc i64 undef to i32)))

This could be folded to

(-1 * (trunc i64 undef to i32))

//===---------------------------------------------------------------------===//