llvm-6502

mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-01-19 04:32:19 +00:00

History

Benjamin Kramer 8611d4449a Cost model support for lowered math builtins.

We make the cost for calling libm functions extremely high as emitting the
calls is expensive and causes spills (on x86) so performance suffers. We still
vectorize important calls like ceilf and friends on SSE4.1. and fabs.

Differential Revision: http://llvm-reviews.chandlerc.com/D466

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@176287 91177308-0d34-0410-b5e6-96231b3b80d8

2013-02-28 19:09:33 +00:00

IPA

Begin fleshing out an interface in TTI for modelling the costs of

2013-01-22 11:26:02 +00:00

AliasAnalysis.cpp

Move isKnownNonNull out of AliasAnalysis.h and into ValueTracking.cpp since

2013-01-31 02:40:59 +00:00

AliasAnalysisCounter.cpp

Use the new script to sort the includes of every file under lib.

2012-12-03 16:50:05 +00:00

AliasAnalysisEvaluator.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

AliasDebugger.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

AliasSetTracker.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

Analysis.cpp

Move the initialization to the Analysis library as well as the pass.

2013-01-07 03:33:08 +00:00

BasicAliasAnalysis.cpp

Fix a problem in alias analysis. It is about the misinterpretation of "Object".

2013-02-28 00:24:45 +00:00

BlockFrequencyInfo.cpp

Use the new script to sort the includes of every file under lib.

2012-12-03 16:50:05 +00:00

BranchProbabilityInfo.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

CaptureTracking.cpp

Give CaptureTracker::shouldExplore a base implementation. Most users want to do

2012-10-08 22:12:48 +00:00

CFGPrinter.cpp

Use the new script to sort the includes of every file under lib.

2012-12-03 16:50:05 +00:00

CMakeLists.txt

Sink InlineCost.cpp into IPA -- it is now officially an interprocedural

2013-01-21 12:09:41 +00:00

CodeMetrics.cpp

Begin fleshing out an interface in TTI for modelling the costs of

2013-01-22 11:26:02 +00:00

ConstantFolding.cpp

Constant fold vector bitcasts of halves similarly to how floats and doubles are folded. Test case included.

2013-02-26 22:51:07 +00:00

CostModel.cpp

Cost model support for lowered math builtins.

2013-02-28 19:09:33 +00:00

DbgInfoPrinter.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

DependenceAnalysis.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

DominanceFrontier.cpp

Use the new script to sort the includes of every file under lib.

2012-12-03 16:50:05 +00:00

DomPrinter.cpp

…

InstCount.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

InstructionSimplify.cpp

Identify and simplify idempotent intrinsics. Test case included.

2013-02-07 19:26:05 +00:00

Interval.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

IntervalPartition.cpp

…

IVUsers.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

LazyValueInfo.cpp

Move isKnownNonNull out of AliasAnalysis.h and into ValueTracking.cpp since

2013-01-31 02:40:59 +00:00

LibCallAliasAnalysis.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

LibCallSemantics.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

Lint.cpp

Change GetPointerBaseWithConstantOffset's DataLayout argument from a

2013-01-31 02:00:45 +00:00

LLVMBuild.txt

…

Loads.cpp

Change GetPointerBaseWithConstantOffset's DataLayout argument from a

2013-01-31 02:00:45 +00:00

LoopInfo.cpp

Metadata for annotating loops as parallel. The first consumer for this

2013-02-13 18:08:57 +00:00

LoopPass.cpp

…

Makefile

…

MemDepPrinter.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

MemoryBuiltins.cpp

Reverting r171325 & r172363. This was causing a mis-compile on the self-hosted LTO build bots.

2013-01-17 21:28:46 +00:00

MemoryDependenceAnalysis.cpp

Unify clang/llvm attributes for asan/tsan/msan (LLVM part)

2013-02-26 06:58:09 +00:00

ModuleDebugInfoPrinter.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

NoAliasAnalysis.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

PathNumbering.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

PathProfileInfo.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

PathProfileVerifier.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

PHITransAddr.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

PostDominators.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

ProfileDataLoader.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

ProfileDataLoaderPass.cpp

Revert "Add LLVMContext::emitWarning methods and use them. <rdar://problem/12867368>"

2013-02-08 21:48:29 +00:00

ProfileEstimatorPass.cpp

Use the new script to sort the includes of every file under lib.

2012-12-03 16:50:05 +00:00

ProfileInfo.cpp

Use the new script to sort the includes of every file under lib.

2012-12-03 16:50:05 +00:00

ProfileInfoLoader.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

ProfileInfoLoaderPass.cpp

Revert "Add LLVMContext::emitWarning methods and use them. <rdar://problem/12867368>"

2013-02-08 21:48:29 +00:00

ProfileVerifierPass.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

PtrUseVisitor.cpp

Hoist the GEP constant address offset computation to a common home on

2012-12-11 10:29:10 +00:00

README.txt

…

RegionInfo.cpp

Use the new script to sort the includes of every file under lib.

2012-12-03 16:50:05 +00:00

RegionPass.cpp

Remove the the block_node_iterator of Region, replace it by the block_iterator.

2012-08-27 13:49:24 +00:00

RegionPrinter.cpp

Use the new script to sort the includes of every file under lib.

2012-12-03 16:50:05 +00:00

ScalarEvolution.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

ScalarEvolutionAliasAnalysis.cpp

Use the new script to sort the includes of every file under lib.

2012-12-03 16:50:05 +00:00

ScalarEvolutionExpander.cpp

SCEVExpander fix. RAUW needs to update the InsertedExpressions cache.

2013-01-14 21:00:37 +00:00

ScalarEvolutionNormalization.cpp

…

SparsePropagation.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

TargetTransformInfo.cpp

ARM cost model: Address computation in vector mem ops not free

2013-02-08 14:50:48 +00:00

Trace.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

TypeBasedAliasAnalysis.cpp

Move all of the header files which are involved in modelling the LLVM IR

2013-01-02 11:36:10 +00:00

ValueTracking.cpp

Move isKnownNonNull out of AliasAnalysis.h and into ValueTracking.cpp since

2013-01-31 02:40:59 +00:00

README.txt

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))

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