dotp-vectorize

Test.hs

import Control.Monad.Error

import LLVM.General.Context
import LLVM.General.Module
import LLVM.General.Target
import LLVM.General.Target.Options
import LLVM.General.PassManager
import LLVM.General.Transforms
import LLVM.General.Diagnostic
import LLVM.General.CommandLine

{-- The standard compiler passes:
 --
 -- $ opt -O3 -disable-output -debug-pass=Arguments dotp.ll
 
Pass Arguments:
  -datalayout -notti -basictti -x86tti -no-aa -tbaa -targetlibinfo -basicaa
  -preverify -domtree -verify -simplifycfg -domtree -sroa -early-cse
  -lower-expect

Pass Arguments:
  -targetlibinfo -datalayout -notti -basictti -x86tti -no-aa -tbaa -basicaa
  -globalopt -ipsccp -deadargelim -instcombine -simplifycfg -basiccg -prune-eh
  -inline-cost -inline -functionattrs -argpromotion -sroa -domtree -early-cse
  -lazy-value-info -jump-threading -correlated-propagation -simplifycfg
  -instcombine -tailcallelim -simplifycfg -reassociate -domtree -loops
  -loop-simplify -lcssa -loop-rotate -licm -lcssa -loop-unswitch -instcombine
  -scalar-evolution -loop-simplify -lcssa -indvars -loop-idiom -loop-deletion
  -loop-unroll -memdep -gvn -memdep -memcpyopt -sccp -instcombine
  -lazy-value-info -jump-threading -correlated-propagation -domtree -memdep -dse
  -loops -scalar-evolution -slp-vectorizer -adce -simplifycfg -instcombine
  -barrier -domtree -loops -loop-simplify -lcssa -scalar-evolution
  -loop-simplify -lcssa -loop-vectorize -instcombine -simplifycfg
  -strip-dead-prototypes -globaldce -constmerge -preverify -domtree -verify
--}

main :: IO ()
main = do
  parseCommandLineOptions
    [ "-debug"
--    , "-force-vector-width=2"
--    , "-mtriple=x86_64-apple-macosx10.9.0"
--    , "-mcpu=corei7-avx"
    , "-debug-pass=Arguments"
    , "-debug-only=loop-vectorize"
    ]
    Nothing

  mt <- readFile "dotp.ll"
  r  <- withContext $ \cx ->
    runErrorT $ withModuleFromLLVMAssembly cx mt $ \mdl -> do
    runErrorT $ withDefaultTargetMachine $ \machine -> do
      triple <- getProcessTargetTriple
      withTargetLibraryInfo triple $ \libinfo -> do

        datalayout  <- getTargetMachineDataLayout machine

        let p1 = PassSetSpec prepass (Just datalayout) (Just libinfo) (Just machine)
            p2 = PassSetSpec optpass (Just datalayout) (Just libinfo) (Just machine)
--            p3 = defaultCuratedPassSetSpec { optLevel = Just 3 }

        _b1 <- withPassManager p1 $ \pm -> runPassManager pm mdl
        _b2 <- withPassManager p2 $ \pm -> runPassManager pm mdl
--      _b3 <- withPassManager p3 $ \pm -> runPassManager pm mdl

        moduleLLVMAssembly mdl >>= putStrLn

  either (either error (putStrLn . diagnosticDisplay))
         (either error return)
         r


prepass :: [Pass]
prepass =
  [ SimplifyControlFlowGraph
  , ScalarReplacementOfAggregates { requiresDominatorTree = True }
  , EarlyCommonSubexpressionElimination
  , LowerExpectIntrinsic
  ]

optpass :: [Pass]
optpass =
  [
  -- -targetlibinfo
  -- -datalayout
  -- -notti
  -- -basictti
  -- -x86tti
  -- -no-aa
  -- -tbaa
  -- -basicaa
  -- -globalopt
    InterproceduralSparseConditionalConstantPropagation                 -- ipsccp
  -- -deadargelim
  , InstructionCombining
  , SimplifyControlFlowGraph
  -- -basiccg
  , PruneExceptionHandling
  -- -inline-cost
  -- , FunctionInlining { functionInliningThreshold = 0 }               -- threshold??
  , FunctionAttributes
  -- , ArgumentPromotion                                                -- not needed?
  , ScalarReplacementOfAggregates { requiresDominatorTree = True }      -- false?
  -- -domtree
  , EarlyCommonSubexpressionElimination
  -- -lazy-value-info
  , JumpThreading
  , CorrelatedValuePropagation
  , SimplifyControlFlowGraph
  , InstructionCombining
  , TailCallElimination
  , SimplifyControlFlowGraph
  , Reassociate
  -- -domtree
  -- -loops
  -- -loop-simplify
  , LoopClosedSingleStaticAssignment
  , LoopRotate
  , LoopInvariantCodeMotion
  , LoopClosedSingleStaticAssignment
  , LoopUnswitch { optimizeForSize = False }
  , LoopInstructionSimplify
  , InstructionCombining
  -- -scalar-evolution
  -- -loop-simplify
  , LoopClosedSingleStaticAssignment
  , InductionVariableSimplify
  , LoopIdiom
  , LoopDeletion
  , LoopUnroll { loopUnrollThreshold = Nothing
               , count               = Nothing
               , allowPartial        = Nothing }
  -- -memdep
  , GlobalValueNumbering { noLoads = False }                             -- loads??
  -- -memdep
  -- -memcpyopt
  , SparseConditionalConstantPropagation
  , InstructionCombining
  -- -lazy-value-info
  , JumpThreading
  , CorrelatedValuePropagation
  -- -domtree
  -- -memdep
  , DeadStoreElimination
  -- -loops
  -- -scalar-evolution
  -- -slp-vectorizer
  -- , defaultVectorizeBasicBlocks      -- instead of slp-vectorizer?
  , AggressiveDeadCodeElimination
  , SimplifyControlFlowGraph
  , InstructionCombining
  -- -barrier
  -- -domtree
  -- -loops
  -- -loop-simplify
  , LoopClosedSingleStaticAssignment
  -- -scalar-evolution
  -- -loop-simplify
  -- LoopClosedSingleStaticAssignment
  , LoopVectorize
  , InstructionCombining
  , SimplifyControlFlowGraph
  -- -strip-dead-prototypes
  , GlobalDeadCodeElimination
  , ConstantMerge
  -- -preverify
  -- -domtree
  -- -verify
  ]