mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-19 19:12:56 +02:00
9c88c96b3f
allows us to compile the example in readme.txt into: LBB1_1: ## %bb movl 4(%rdx,%rax), %ecx movl %ecx, %esi imull (%rdx,%rax), %esi imull %esi, %ecx movl %esi, 8(%rdx,%rax) imull %ecx, %esi movl %ecx, 12(%rdx,%rax) movl %esi, 16(%rdx,%rax) imull %ecx, %esi movl %esi, 20(%rdx,%rax) addq $16, %rax cmpq $4000, %rax jne LBB1_1 instead of: LBB1_1: movl (%rdx,%rax), %ecx imull 4(%rdx,%rax), %ecx movl %ecx, 8(%rdx,%rax) imull 4(%rdx,%rax), %ecx movl %ecx, 12(%rdx,%rax) imull 8(%rdx,%rax), %ecx movl %ecx, 16(%rdx,%rax) imull 12(%rdx,%rax), %ecx movl %ecx, 20(%rdx,%rax) addq $16, %rax cmpq $4000, %rax jne LBB1_1 GCC (4.2) doesn't seem to be able to eliminate the loads in this testcase either, it generates: L2: movl (%rdx), %eax imull 4(%rdx), %eax movl %eax, 8(%rdx) imull 4(%rdx), %eax movl %eax, 12(%rdx) imull 8(%rdx), %eax movl %eax, 16(%rdx) imull 12(%rdx), %eax movl %eax, 20(%rdx) addl $4, %ecx addq $16, %rdx cmpl $1002, %ecx jne L2 llvm-svn: 89952 |
||
|---|---|---|
| .. | ||
| IPA | ||
| AliasAnalysis.cpp | ||
| AliasAnalysisCounter.cpp | ||
| AliasAnalysisEvaluator.cpp | ||
| AliasDebugger.cpp | ||
| AliasSetTracker.cpp | ||
| Analysis.cpp | ||
| BasicAliasAnalysis.cpp | ||
| CaptureTracking.cpp | ||
| CFGPrinter.cpp | ||
| CMakeLists.txt | ||
| ConstantFolding.cpp | ||
| DbgInfoPrinter.cpp | ||
| DebugInfo.cpp | ||
| DomPrinter.cpp | ||
| InlineCost.cpp | ||
| InstCount.cpp | ||
| InstructionSimplify.cpp | ||
| Interval.cpp | ||
| IntervalPartition.cpp | ||
| IVUsers.cpp | ||
| LazyValueInfo.cpp | ||
| LibCallAliasAnalysis.cpp | ||
| LibCallSemantics.cpp | ||
| LiveValues.cpp | ||
| LoopDependenceAnalysis.cpp | ||
| LoopInfo.cpp | ||
| LoopPass.cpp | ||
| Makefile | ||
| MemoryBuiltins.cpp | ||
| MemoryDependenceAnalysis.cpp | ||
| PointerTracking.cpp | ||
| PostDominators.cpp | ||
| ProfileEstimatorPass.cpp | ||
| ProfileInfo.cpp | ||
| ProfileInfoLoader.cpp | ||
| ProfileInfoLoaderPass.cpp | ||
| ProfileVerifierPass.cpp | ||
| README.txt | ||
| ScalarEvolution.cpp | ||
| ScalarEvolutionAliasAnalysis.cpp | ||
| ScalarEvolutionExpander.cpp | ||
| SparsePropagation.cpp | ||
| Trace.cpp | ||
| ValueTracking.cpp | ||
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.
//===---------------------------------------------------------------------===//