+\begin{code}
+preInlineUnconditionally :: SimplEnv -> TopLevelFlag -> InId -> InExpr -> Bool
+preInlineUnconditionally env top_lvl bndr rhs
+ | not active = False
+ | opt_SimplNoPreInlining = False
+ | otherwise = case idOccInfo bndr of
+ IAmDead -> True -- Happens in ((\x.1) v)
+ OneOcc in_lam True int_cxt -> try_once in_lam int_cxt
+ other -> False
+ where
+ phase = getMode env
+ active = case phase of
+ SimplGently -> isAlwaysActive prag
+ SimplPhase n -> isActive n prag
+ prag = idInlinePragma bndr
+
+ try_once in_lam int_cxt -- There's one textual occurrence
+ | not in_lam = isNotTopLevel top_lvl || early_phase
+ | otherwise = int_cxt && canInlineInLam rhs
+
+-- Be very careful before inlining inside a lambda, becuase (a) we must not
+-- invalidate occurrence information, and (b) we want to avoid pushing a
+-- single allocation (here) into multiple allocations (inside lambda).
+-- Inlining a *function* with a single *saturated* call would be ok, mind you.
+-- || (if is_cheap && not (canInlineInLam rhs) then pprTrace "preinline" (ppr bndr <+> ppr rhs) ok else ok)
+-- where
+-- is_cheap = exprIsCheap rhs
+-- ok = is_cheap && int_cxt
+
+ -- int_cxt The context isn't totally boring
+ -- E.g. let f = \ab.BIG in \y. map f xs
+ -- Don't want to substitute for f, because then we allocate
+ -- its closure every time the \y is called
+ -- But: let f = \ab.BIG in \y. map (f y) xs
+ -- Now we do want to substitute for f, even though it's not
+ -- saturated, because we're going to allocate a closure for
+ -- (f y) every time round the loop anyhow.
+
+ -- canInlineInLam => free vars of rhs are (Once in_lam) or Many,
+ -- so substituting rhs inside a lambda doesn't change the occ info.
+ -- Sadly, not quite the same as exprIsHNF.
+ canInlineInLam (Lit l) = True
+ canInlineInLam (Lam b e) = isRuntimeVar b || canInlineInLam e
+ canInlineInLam (Note _ e) = canInlineInLam e
+ canInlineInLam _ = False
+
+ early_phase = case phase of
+ SimplPhase 0 -> False
+ other -> True
+-- If we don't have this early_phase test, consider
+-- x = length [1,2,3]
+-- The full laziness pass carefully floats all the cons cells to
+-- top level, and preInlineUnconditionally floats them all back in.
+-- Result is (a) static allocation replaced by dynamic allocation
+-- (b) many simplifier iterations because this tickles
+-- a related problem; only one inlining per pass
+--
+-- On the other hand, I have seen cases where top-level fusion is
+-- lost if we don't inline top level thing (e.g. string constants)
+-- Hence the test for phase zero (which is the phase for all the final
+-- simplifications). Until phase zero we take no special notice of
+-- top level things, but then we become more leery about inlining
+-- them.
+
+\end{code}
+
+postInlineUnconditionally
+~~~~~~~~~~~~~~~~~~~~~~~~~
+@postInlineUnconditionally@ decides whether to unconditionally inline
+a thing based on the form of its RHS; in particular if it has a
+trivial RHS. If so, we can inline and discard the binding altogether.
+
+NB: a loop breaker has must_keep_binding = True and non-loop-breakers
+only have *forward* references Hence, it's safe to discard the binding
+
+NOTE: This isn't our last opportunity to inline. We're at the binding
+site right now, and we'll get another opportunity when we get to the
+ocurrence(s)
+
+Note that we do this unconditional inlining only for trival RHSs.
+Don't inline even WHNFs inside lambdas; doing so may simply increase
+allocation when the function is called. This isn't the last chance; see
+NOTE above.
+
+NB: Even inline pragmas (e.g. IMustBeINLINEd) are ignored here Why?
+Because we don't even want to inline them into the RHS of constructor
+arguments. See NOTE above
+
+NB: At one time even NOINLINE was ignored here: if the rhs is trivial
+it's best to inline it anyway. We often get a=E; b=a from desugaring,
+with both a and b marked NOINLINE. But that seems incompatible with
+our new view that inlining is like a RULE, so I'm sticking to the 'active'
+story for now.
+
+\begin{code}
+postInlineUnconditionally :: SimplEnv -> TopLevelFlag -> OutId -> OccInfo -> OutExpr -> Unfolding -> Bool
+postInlineUnconditionally env top_lvl bndr occ_info rhs unfolding
+ | not active = False
+ | isLoopBreaker occ_info = False
+ | isExportedId bndr = False
+ | exprIsTrivial rhs = True
+ | otherwise
+ = case occ_info of
+ OneOcc in_lam one_br int_cxt
+ -> (one_br || smallEnoughToInline unfolding) -- Small enough to dup
+ -- ToDo: consider discount on smallEnoughToInline if int_cxt is true
+ --
+ -- NB: Do we want to inline arbitrarily big things becuase
+ -- one_br is True? that can lead to inline cascades. But
+ -- preInlineUnconditionlly has dealt with all the common cases
+ -- so perhaps it's worth the risk. Here's an example
+ -- let f = if b then Left (\x.BIG) else Right (\y.BIG)
+ -- in \y. ....f....
+ -- We can't preInlineUnconditionally because that woud invalidate
+ -- the occ info for b. Yet f is used just once, and duplicating
+ -- the case work is fine (exprIsCheap).
+
+ && ((isNotTopLevel top_lvl && not in_lam) ||
+ -- But outside a lambda, we want to be reasonably aggressive
+ -- about inlining into multiple branches of case
+ -- e.g. let x = <non-value>
+ -- in case y of { C1 -> ..x..; C2 -> ..x..; C3 -> ... }
+ -- Inlining can be a big win if C3 is the hot-spot, even if
+ -- the uses in C1, C2 are not 'interesting'
+ -- An example that gets worse if you add int_cxt here is 'clausify'
+
+ (isCheapUnfolding unfolding && int_cxt))
+ -- isCheap => acceptable work duplication; in_lam may be true
+ -- int_cxt to prevent us inlining inside a lambda without some
+ -- good reason. See the notes on int_cxt in preInlineUnconditionally
+
+ other -> False
+ -- The point here is that for *non-values* that occur
+ -- outside a lambda, the call-site inliner won't have
+ -- a chance (becuase it doesn't know that the thing
+ -- only occurs once). The pre-inliner won't have gotten
+ -- it either, if the thing occurs in more than one branch
+ -- So the main target is things like
+ -- let x = f y in
+ -- case v of
+ -- True -> case x of ...
+ -- False -> case x of ...
+ -- I'm not sure how important this is in practice
+ where
+ active = case getMode env of
+ SimplGently -> isAlwaysActive prag
+ SimplPhase n -> isActive n prag
+ prag = idInlinePragma bndr
+
+activeInline :: SimplEnv -> OutId -> OccInfo -> Bool
+activeInline env id occ
+ = case getMode env of
+ SimplGently -> isOneOcc occ && isAlwaysActive prag
+ -- No inlining at all when doing gentle stuff,
+ -- except for local things that occur once
+ -- The reason is that too little clean-up happens if you
+ -- don't inline use-once things. Also a bit of inlining is *good* for
+ -- full laziness; it can expose constant sub-expressions.
+ -- Example in spectral/mandel/Mandel.hs, where the mandelset
+ -- function gets a useful let-float if you inline windowToViewport
+
+ -- NB: we used to have a second exception, for data con wrappers.
+ -- On the grounds that we use gentle mode for rule LHSs, and
+ -- they match better when data con wrappers are inlined.
+ -- But that only really applies to the trivial wrappers (like (:)),
+ -- and they are now constructed as Compulsory unfoldings (in MkId)
+ -- so they'll happen anyway.
+
+ SimplPhase n -> isActive n prag
+ where
+ prag = idInlinePragma id
+
+activeRule :: SimplEnv -> Maybe (Activation -> Bool)
+-- Nothing => No rules at all
+activeRule env
+ | opt_RulesOff = Nothing
+ | otherwise
+ = case getMode env of
+ SimplGently -> Just isAlwaysActive
+ -- Used to be Nothing (no rules in gentle mode)
+ -- Main motivation for changing is that I wanted
+ -- lift String ===> ...
+ -- to work in Template Haskell when simplifying
+ -- splices, so we get simpler code for literal strings
+ SimplPhase n -> Just (isActive n)
+\end{code}
+
+
+%************************************************************************
+%* *
+\subsection{Rebuilding a lambda}
+%* *
+%************************************************************************
+
+\begin{code}
+mkLam :: SimplEnv -> [OutBinder] -> OutExpr -> SimplCont -> SimplM FloatsWithExpr
+\end{code}
+
+Try three things
+ a) eta reduction, if that gives a trivial expression
+ b) eta expansion [only if there are some value lambdas]
+ c) floating lets out through big lambdas
+ [only if all tyvar lambdas, and only if this lambda
+ is the RHS of a let]
+
+\begin{code}
+mkLam env bndrs body cont
+ = getDOptsSmpl `thenSmpl` \dflags ->
+ mkLam' dflags env bndrs body cont
+ where
+ mkLam' dflags env bndrs body cont
+ | dopt Opt_DoEtaReduction dflags,
+ Just etad_lam <- tryEtaReduce bndrs body
+ = tick (EtaReduction (head bndrs)) `thenSmpl_`
+ returnSmpl (emptyFloats env, etad_lam)
+
+ | dopt Opt_DoLambdaEtaExpansion dflags,
+ any isRuntimeVar bndrs
+ = tryEtaExpansion body `thenSmpl` \ body' ->
+ returnSmpl (emptyFloats env, mkLams bndrs body')
+
+{- Sept 01: I'm experimenting with getting the
+ full laziness pass to float out past big lambdsa
+ | all isTyVar bndrs, -- Only for big lambdas
+ contIsRhs cont -- Only try the rhs type-lambda floating
+ -- if this is indeed a right-hand side; otherwise
+ -- we end up floating the thing out, only for float-in
+ -- to float it right back in again!
+ = tryRhsTyLam env bndrs body `thenSmpl` \ (floats, body') ->
+ returnSmpl (floats, mkLams bndrs body')
+-}
+
+ | otherwise
+ = returnSmpl (emptyFloats env, mkLams bndrs body)
+\end{code}
+
+
+%************************************************************************
+%* *
+\subsection{Eta expansion and reduction}
+%* *
+%************************************************************************
+
+We try for eta reduction here, but *only* if we get all the
+way to an exprIsTrivial expression.
+We don't want to remove extra lambdas unless we are going
+to avoid allocating this thing altogether
+
+\begin{code}
+tryEtaReduce :: [OutBinder] -> OutExpr -> Maybe OutExpr
+tryEtaReduce bndrs body
+ -- We don't use CoreUtils.etaReduce, because we can be more
+ -- efficient here:
+ -- (a) we already have the binders
+ -- (b) we can do the triviality test before computing the free vars
+ = go (reverse bndrs) body
+ where
+ go (b : bs) (App fun arg) | ok_arg b arg = go bs fun -- Loop round
+ go [] fun | ok_fun fun = Just fun -- Success!
+ go _ _ = Nothing -- Failure!
+
+ ok_fun fun = exprIsTrivial fun
+ && not (any (`elemVarSet` (exprFreeVars fun)) bndrs)
+ && (exprIsHNF fun || all ok_lam bndrs)
+ ok_lam v = isTyVar v || isDictId v
+ -- The exprIsHNF is because eta reduction is not
+ -- valid in general: \x. bot /= bot
+ -- So we need to be sure that the "fun" is a value.
+ --
+ -- However, we always want to reduce (/\a -> f a) to f
+ -- This came up in a RULE: foldr (build (/\a -> g a))
+ -- did not match foldr (build (/\b -> ...something complex...))
+ -- The type checker can insert these eta-expanded versions,
+ -- with both type and dictionary lambdas; hence the slightly
+ -- ad-hoc isDictTy
+
+ ok_arg b arg = varToCoreExpr b `cheapEqExpr` arg
+\end{code}
+
+
+ Try eta expansion for RHSs
+
+We go for:
+ f = \x1..xn -> N ==> f = \x1..xn y1..ym -> N y1..ym
+ (n >= 0)
+
+where (in both cases)
+
+ * The xi can include type variables
+
+ * The yi are all value variables
+
+ * N is a NORMAL FORM (i.e. no redexes anywhere)
+ wanting a suitable number of extra args.
+
+We may have to sandwich some coerces between the lambdas
+to make the types work. exprEtaExpandArity looks through coerces
+when computing arity; and etaExpand adds the coerces as necessary when
+actually computing the expansion.
+
+\begin{code}
+tryEtaExpansion :: OutExpr -> SimplM OutExpr
+-- There is at least one runtime binder in the binders
+tryEtaExpansion body
+ = getUniquesSmpl `thenSmpl` \ us ->
+ returnSmpl (etaExpand fun_arity us body (exprType body))
+ where
+ fun_arity = exprEtaExpandArity body