Simplify.lhs 67.8 KB
Newer Older
1
%
2
% (c) The AQUA Project, Glasgow University, 1993-1998
3
4
5
6
%
\section[Simplify]{The main module of the simplifier}

\begin{code}
7
module Simplify ( simplTopBinds, simplExpr ) where
8

9
#include "HsVersions.h"
10

simonpj@microsoft.com's avatar
Wibble    
simonpj@microsoft.com committed
11
import DynFlags
12
import SimplMonad
13
import Type hiding	( substTy, extendTvSubst )
14
import SimplEnv	
15
16
import SimplUtils
import Id
17
import Var
18
19
import IdInfo
import Coercion
20
21
import DataCon		( dataConTyCon, dataConRepStrictness, dataConUnivTyVars )
import TyCon		( tyConArity )
22
import CoreSyn
23
import NewDemand	( isStrictDmd )
24
import PprCore		( pprParendExpr, pprCoreExpr )
25
import CoreUnfold	( mkUnfolding, callSiteInline )
26
import CoreUtils
27
import Rules		( lookupRule )
28
import BasicTypes	( isMarkedStrict )
29
import CostCentre	( currentCCS )
30
import TysPrim		( realWorldStatePrimTy )
31
import PrelInfo		( realWorldPrimId )
32
import BasicTypes	( TopLevelFlag(..), isTopLevel, 
33
			  RecFlag(..), isNonRuleLoopBreaker )
34
import Maybes		( orElse )
35
import Outputable
36
import Util
37
38
39
\end{code}


40
41
The guts of the simplifier is in this module, but the driver loop for
the simplifier is in SimplCore.lhs.
42
43


44
45
46
47
48
49
50
51
-----------------------------------------
	*** IMPORTANT NOTE ***
-----------------------------------------
The simplifier used to guarantee that the output had no shadowing, but
it does not do so any more.   (Actually, it never did!)  The reason is
documented with simplifyArgs.


52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
-----------------------------------------
	*** IMPORTANT NOTE ***
-----------------------------------------
Many parts of the simplifier return a bunch of "floats" as well as an
expression. This is wrapped as a datatype SimplUtils.FloatsWith.

All "floats" are let-binds, not case-binds, but some non-rec lets may
be unlifted (with RHS ok-for-speculation).



-----------------------------------------
	ORGANISATION OF FUNCTIONS
-----------------------------------------
simplTopBinds
  - simplify all top-level binders
  - for NonRec, call simplRecOrTopPair
  - for Rec,    call simplRecBind

	
	------------------------------
simplExpr (applied lambda)	==> simplNonRecBind
simplExpr (Let (NonRec ...) ..) ==> simplNonRecBind
simplExpr (Let (Rec ...)    ..) ==> simplify binders; simplRecBind

	------------------------------
simplRecBind	[binders already simplfied]
  - use simplRecOrTopPair on each pair in turn

simplRecOrTopPair [binder already simplified]
  Used for: recursive bindings (top level and nested)
	    top-level non-recursive bindings
  Returns: 
  - check for PreInlineUnconditionally
  - simplLazyBind

simplNonRecBind
  Used for: non-top-level non-recursive bindings
	    beta reductions (which amount to the same thing)
  Because it can deal with strict arts, it takes a 
	"thing-inside" and returns an expression

  - check for PreInlineUnconditionally
  - simplify binder, including its IdInfo
  - if strict binding
	simplStrictArg
	mkAtomicArgs
	completeNonRecX
    else
	simplLazyBind
	addFloats

simplNonRecX:	[given a *simplified* RHS, but an *unsimplified* binder]
  Used for: binding case-binder and constr args in a known-constructor case
  - check for PreInLineUnconditionally
  - simplify binder
  - completeNonRecX
 
	------------------------------
simplLazyBind:	[binder already simplified, RHS not]
  Used for: recursive bindings (top level and nested)
	    top-level non-recursive bindings
	    non-top-level, but *lazy* non-recursive bindings
	[must not be strict or unboxed]
  Returns floats + an augmented environment, not an expression
  - substituteIdInfo and add result to in-scope 
	[so that rules are available in rec rhs]
  - simplify rhs
  - mkAtomicArgs
  - float if exposes constructor or PAP
122
  - completeBind
123
124
125
126
127
128


completeNonRecX:	[binder and rhs both simplified]
  - if the the thing needs case binding (unlifted and not ok-for-spec)
	build a Case
   else
129
	completeBind
130
131
	addFloats

132
completeBind: 	[given a simplified RHS]
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
	[used for both rec and non-rec bindings, top level and not]
  - try PostInlineUnconditionally
  - add unfolding [this is the only place we add an unfolding]
  - add arity



Right hand sides and arguments
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In many ways we want to treat 
	(a) the right hand side of a let(rec), and 
	(b) a function argument
in the same way.  But not always!  In particular, we would
like to leave these arguments exactly as they are, so they
will match a RULE more easily.
	
	f (g x, h x)	
	g (+ x)

It's harder to make the rule match if we ANF-ise the constructor,
or eta-expand the PAP:

	f (let { a = g x; b = h x } in (a,b))
	g (\y. + x y)

On the other hand if we see the let-defns

	p = (g x, h x)
	q = + x

then we *do* want to ANF-ise and eta-expand, so that p and q
can be safely inlined.   

Even floating lets out is a bit dubious.  For let RHS's we float lets
out if that exposes a value, so that the value can be inlined more vigorously.
For example

	r = let x = e in (x,x)

Here, if we float the let out we'll expose a nice constructor. We did experiments
that showed this to be a generally good thing.  But it was a bad thing to float
lets out unconditionally, because that meant they got allocated more often.

For function arguments, there's less reason to expose a constructor (it won't
get inlined).  Just possibly it might make a rule match, but I'm pretty skeptical.
So for the moment we don't float lets out of function arguments either.


Eta expansion
~~~~~~~~~~~~~~
For eta expansion, we want to catch things like

	case e of (a,b) -> \x -> case a of (p,q) -> \y -> r

If the \x was on the RHS of a let, we'd eta expand to bring the two
lambdas together.  And in general that's a good thing to do.  Perhaps
we should eta expand wherever we find a (value) lambda?  Then the eta
expansion at a let RHS can concentrate solely on the PAP case.
191
192


193
194
195
196
197
198
199
%************************************************************************
%*									*
\subsection{Bindings}
%*									*
%************************************************************************

\begin{code}
200
simplTopBinds :: SimplEnv -> [InBind] -> SimplM [OutBind]
201

202
simplTopBinds env binds
203
204
205
206
207
208
  = do	{ 	-- Put all the top-level binders into scope at the start
		-- so that if a transformation rule has unexpectedly brought
		-- anything into scope, then we don't get a complaint about that.
		-- It's rather as if the top-level binders were imported.
	; env <- simplRecBndrs env (bindersOfBinds binds)
	; dflags <- getDOptsSmpl
209
210
	; let dump_flag = dopt Opt_D_dump_inlinings dflags || 
			  dopt Opt_D_dump_rule_firings dflags
211
212
213
	; env' <- simpl_binds dump_flag env binds
	; freeTick SimplifierDone
	; return (getFloats env') }
214
  where
215
216
	-- We need to track the zapped top-level binders, because
	-- they should have their fragile IdInfo zapped (notably occurrence info)
217
	-- That's why we run down binds and bndrs' simultaneously.
218
219
220
	--
	-- The dump-flag emits a trace for each top-level binding, which
	-- helps to locate the tracing for inlining and rule firing
221
222
223
224
225
    simpl_binds :: Bool -> SimplEnv -> [InBind] -> SimplM SimplEnv
    simpl_binds dump env []	      = return env
    simpl_binds dump env (bind:binds) = do { env' <- trace dump bind $
						     simpl_bind env bind
					   ; simpl_binds dump env' binds }
226

227
228
    trace True  bind = pprTrace "SimplBind" (ppr (bindersOf bind))
    trace False bind = \x -> x
simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
229

230
231
    simpl_bind env (NonRec b r) = simplRecOrTopPair env TopLevel b r
    simpl_bind env (Rec pairs)  = simplRecBind      env TopLevel pairs
232
233
234
235
236
237
238
239
240
241
242
243
244
245
\end{code}


%************************************************************************
%*									*
\subsection{Lazy bindings}
%*									*
%************************************************************************

simplRecBind is used for
	* recursive bindings only

\begin{code}
simplRecBind :: SimplEnv -> TopLevelFlag
246
247
248
249
250
251
252
	     -> [(InId, InExpr)]
	     -> SimplM SimplEnv
simplRecBind env top_lvl pairs
  = do	{ env' <- go (zapFloats env) pairs
	; return (env `addRecFloats` env') }
	-- addFloats adds the floats from env', 
	-- *and* updates env with the in-scope set from env'
253
  where
254
    go env [] = return env
255
	
256
257
258
    go env ((bndr, rhs) : pairs)
	= do { env <- simplRecOrTopPair env top_lvl bndr rhs
	     ; go env pairs }
259
260
\end{code}

261
simplOrTopPair is used for
262
263
264
265
266
267
268
269
	* recursive bindings (whether top level or not)
	* top-level non-recursive bindings

It assumes the binder has already been simplified, but not its IdInfo.

\begin{code}
simplRecOrTopPair :: SimplEnv
	     	  -> TopLevelFlag
270
271
	     	  -> InId -> InExpr	-- Binder and rhs
	     	  -> SimplM SimplEnv	-- Returns an env that includes the binding
272

273
simplRecOrTopPair env top_lvl bndr rhs
274
  | preInlineUnconditionally env top_lvl bndr rhs  	-- Check for unconditional inline
275
276
  = do	{ tick (PreInlineUnconditionally bndr)
	; return (extendIdSubst env bndr (mkContEx env rhs)) }
277
278

  | otherwise
279
280
281
  = do	{ let bndr' = lookupRecBndr env bndr
	      (env', bndr'') = addLetIdInfo env bndr bndr'
	; simplLazyBind env' top_lvl Recursive bndr bndr'' rhs env' }
282
283
284
285
286
	-- May not actually be recursive, but it doesn't matter
\end{code}


simplLazyBind is used for
287
288
289
  * [simplRecOrTopPair] recursive bindings (whether top level or not)
  * [simplRecOrTopPair] top-level non-recursive bindings
  * [simplNonRecE]	non-top-level *lazy* non-recursive bindings
290
291
292

Nota bene:
    1. It assumes that the binder is *already* simplified, 
293
       and is in scope, and its IdInfo too, except unfolding
294
295
296
297
298
299
300
301
302
303

    2. It assumes that the binder type is lifted.

    3. It does not check for pre-inline-unconditionallly;
       that should have been done already.

\begin{code}
simplLazyBind :: SimplEnv
	      -> TopLevelFlag -> RecFlag
	      -> InId -> OutId		-- Binder, both pre-and post simpl
304
					-- The OutId has IdInfo, except arity, unfolding
305
	      -> InExpr -> SimplEnv 	-- The RHS and its environment
306
	      -> SimplM SimplEnv
307

308
simplLazyBind env top_lvl is_rec bndr bndr1 rhs rhs_se
309
310
311
  = do	{ let	rhs_env  = rhs_se `setInScope` env
		rhs_cont = mkRhsStop (idType bndr1)

312
  	-- Simplify the RHS; note the mkRhsStop, which tells 
313
	-- the simplifier that this is the RHS of a let.
314
	; (rhs_env1, rhs1) <- simplExprF rhs_env rhs rhs_cont
315
316

	-- If any of the floats can't be floated, give up now
317
318
319
320
321
	-- (The canFloat predicate says True for empty floats.)
	; if (not (canFloat top_lvl is_rec False rhs_env1))
	  then	completeBind env top_lvl bndr bndr1
				 (wrapFloats rhs_env1 rhs1)
	  else do
322
	-- ANF-ise a constructor or PAP rhs
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
	{ (rhs_env2, rhs2) <- prepareRhs rhs_env1 rhs1
	; (env', rhs3) <- chooseRhsFloats top_lvl is_rec False env rhs_env2 rhs2
	; completeBind env' top_lvl bndr bndr1 rhs3 } }

chooseRhsFloats :: TopLevelFlag -> RecFlag -> Bool
	     	-> SimplEnv	-- Env for the let
	     	-> SimplEnv	-- Env for the RHS, with RHS floats in it
	     	-> OutExpr		-- ..and the RHS itself
	     	-> SimplM (SimplEnv, OutExpr)	-- New env for let, and RHS

chooseRhsFloats top_lvl is_rec is_strict env rhs_env rhs
  | not (isEmptyFloats rhs_env) 		-- Something to float
  , canFloat top_lvl is_rec is_strict rhs_env	-- ...that can float
  , (isTopLevel top_lvl  || exprIsCheap rhs)	-- ...and we want to float	
  = do	{ tick LetFloatFromLet	-- Float
	; return (addFloats env rhs_env, rhs) }	-- Add the floats to the main env
  | otherwise			-- Don't float
  = return (env, wrapFloats rhs_env rhs)	-- Wrap the floats around the RHS
\end{code}


%************************************************************************
%*									*
\subsection{simplNonRec}
%*									*
%************************************************************************

A specialised variant of simplNonRec used when the RHS is already simplified, 
notably in knownCon.  It uses case-binding where necessary.

\begin{code}
simplNonRecX :: SimplEnv
	     -> InId 		-- Old binder
	     -> OutExpr		-- Simplified RHS
	     -> SimplM SimplEnv

simplNonRecX env bndr new_rhs
  = do	{ (env, bndr') <- simplBinder env bndr
	; completeNonRecX env NotTopLevel NonRecursive
simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
362
			  (isStrictId bndr) bndr bndr' new_rhs }
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384

completeNonRecX :: SimplEnv
		-> TopLevelFlag -> RecFlag -> Bool
	        -> InId 		-- Old binder
		-> OutId		-- New binder
	     	-> OutExpr		-- Simplified RHS
	     	-> SimplM SimplEnv

completeNonRecX env top_lvl is_rec is_strict old_bndr new_bndr new_rhs
  = do 	{ (env1, rhs1) <- prepareRhs (zapFloats env) new_rhs
	; (env2, rhs2) <- chooseRhsFloats top_lvl is_rec is_strict env env1 rhs1
	; completeBind env2 NotTopLevel old_bndr new_bndr rhs2 }
\end{code}

{- No, no, no!  Do not try preInlineUnconditionally in completeNonRecX
   Doing so risks exponential behaviour, because new_rhs has been simplified once already
   In the cases described by the folowing commment, postInlineUnconditionally will 
   catch many of the relevant cases.
  	-- This happens; for example, the case_bndr during case of
	-- known constructor:  case (a,b) of x { (p,q) -> ... }
	-- Here x isn't mentioned in the RHS, so we don't want to
	-- create the (dead) let-binding  let x = (a,b) in ...
385
	--
386
387
388
	-- Similarly, single occurrences can be inlined vigourously
	-- e.g.  case (f x, g y) of (a,b) -> ....
	-- If a,b occur once we can avoid constructing the let binding for them.
389

390
391
392
393
394
395
396
   Furthermore in the case-binding case preInlineUnconditionally risks extra thunks
	-- Consider 	case I# (quotInt# x y) of 
	--		  I# v -> let w = J# v in ...
	-- If we gaily inline (quotInt# x y) for v, we end up building an
	-- extra thunk:
	--		  let w = J# (quotInt# x y) in ...
	-- because quotInt# can fail.
397

398
399
400
401
  | preInlineUnconditionally env NotTopLevel bndr new_rhs
  = thing_inside (extendIdSubst env bndr (DoneEx new_rhs))
-}

402
----------------------------------
403
404
405
406
407
408
409
410
411
prepareRhs takes a putative RHS, checks whether it's a PAP or
constructor application and, if so, converts it to ANF, so that the 
resulting thing can be inlined more easily.  Thus
	x = (f a, g b)
becomes
	t1 = f a
	t2 = g b
	x = (t1,t2)

412
413
414
415
416
417
We also want to deal well cases like this
	v = (f e1 `cast` co) e2
Here we want to make e1,e2 trivial and get
	x1 = e1; x2 = e2; v = (f x1 `cast` co) v2
That's what the 'go' loop in prepareRhs does

418
419
420
\begin{code}
prepareRhs :: SimplEnv -> OutExpr -> SimplM (SimplEnv, OutExpr)
-- Adds new floats to the env iff that allows us to return a good RHS
simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
421
prepareRhs env (Cast rhs co)	-- Note [Float coercions]
422
423
424
425
  = do	{ (env', rhs') <- makeTrivial env rhs
	; return (env', Cast rhs' co) }

prepareRhs env rhs
426
427
  = do	{ (is_val, env', rhs') <- go 0 env rhs 
	; return (env', rhs') }
428
  where
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
    go n_val_args env (Cast rhs co)
	= do { (is_val, env', rhs') <- go n_val_args env rhs
	     ; return (is_val, env', Cast rhs' co) }
    go n_val_args env (App fun (Type ty))
	= do { (is_val, env', rhs') <- go n_val_args env fun
	     ; return (is_val, env', App rhs' (Type ty)) }
    go n_val_args env (App fun arg)
	= do { (is_val, env', fun') <- go (n_val_args+1) env fun
	     ; case is_val of
		True -> do { (env'', arg') <- makeTrivial env' arg
			   ; return (True, env'', App fun' arg') }
		False -> return (False, env, App fun arg) }
    go n_val_args env (Var fun)
	= return (is_val, env, Var fun)
	where
	  is_val = n_val_args > 0	-- There is at least one arg
					-- ...and the fun a constructor or PAP
		 && (isDataConWorkId fun || n_val_args < idArity fun)
    go n_val_args env other
	= return (False, env, other)
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
\end{code}

Note [Float coercions]
~~~~~~~~~~~~~~~~~~~~~~
When we find the binding
	x = e `cast` co
we'd like to transform it to
	x' = e
	x = x `cast` co		-- A trivial binding
There's a chance that e will be a constructor application or function, or something
like that, so moving the coerion to the usage site may well cancel the coersions
and lead to further optimisation.  Example:

     data family T a :: *
     data instance T Int = T Int

     foo :: Int -> Int -> Int
     foo m n = ...
        where
          x = T m
          go 0 = 0
          go n = case x of { T m -> go (n-m) }
		-- This case should optimise


\begin{code}
makeTrivial :: SimplEnv -> OutExpr -> SimplM (SimplEnv, OutExpr)
-- Binds the expression to a variable, if it's not trivial, returning the variable
makeTrivial env expr
  | exprIsTrivial expr
  = return (env, expr)
  | otherwise		-- See Note [Take care] below
  = do 	{ var <- newId FSLIT("a") (exprType expr)
	; env <- completeNonRecX env NotTopLevel NonRecursive 
				 False var var expr
	; return (env, substExpr env (Var var)) }
485
\end{code}
486
487


488
489
490
491
492
493
%************************************************************************
%*									*
\subsection{Completing a lazy binding}
%*									*
%************************************************************************

494
495
496
497
498
completeBind
  * deals only with Ids, not TyVars
  * takes an already-simplified binder and RHS
  * is used for both recursive and non-recursive bindings
  * is used for both top-level and non-top-level bindings
499
500
501
502
503
504
505
506

It does the following:
  - tries discarding a dead binding
  - tries PostInlineUnconditionally
  - add unfolding [this is the only place we add an unfolding]
  - add arity

It does *not* attempt to do let-to-case.  Why?  Because it is used for
507
508
  - top-level bindings (when let-to-case is impossible) 
  - many situations where the "rhs" is known to be a WHNF
509
510
		(so let-to-case is inappropriate).

511
512
Nor does it do the atomic-argument thing

513
\begin{code}
514
515
516
517
518
519
520
521
522
523
completeBind :: SimplEnv
	     -> TopLevelFlag		-- Flag stuck into unfolding
	     -> InId 			-- Old binder
	     -> OutId -> OutExpr	-- New binder and RHS
	     -> SimplM SimplEnv
-- completeBind may choose to do its work 
--	* by extending the substitution (e.g. let x = y in ...)
--	* or by adding to the floats in the envt

completeBind env top_lvl old_bndr new_bndr new_rhs
524
  | postInlineUnconditionally env top_lvl new_bndr occ_info new_rhs unfolding
525
526
527
528
529
530
		-- Inline and discard the binding
  = do	{ tick (PostInlineUnconditionally old_bndr)
	; -- pprTrace "postInlineUnconditionally" (ppr old_bndr <+> ppr new_bndr <+> ppr new_rhs) $
	  return (extendIdSubst env old_bndr (DoneEx new_rhs)) }
	-- Use the substitution to make quite, quite sure that the
	-- substitution will happen, since we are going to discard the binding
531
532
533

  |  otherwise
  = let
534
	-- 	Arity info
535
536
  	new_bndr_info = idInfo new_bndr `setArityInfo` exprArity new_rhs

537
	-- 	Unfolding info
538
539
540
541
542
	-- Add the unfolding *only* for non-loop-breakers
	-- Making loop breakers not have an unfolding at all 
	-- means that we can avoid tests in exprIsConApp, for example.
	-- This is important: if exprIsConApp says 'yes' for a recursive
	-- thing, then we can get into an infinite loop
543
544

	-- 	Demand info
545
546
547
548
549
550
551
552
553
554
	-- If the unfolding is a value, the demand info may
	-- go pear-shaped, so we nuke it.  Example:
	--	let x = (a,b) in
	--	case x of (p,q) -> h p q x
	-- Here x is certainly demanded. But after we've nuked
	-- the case, we'll get just
	--	let x = (a,b) in h a b x
	-- and now x is not demanded (I'm assuming h is lazy)
	-- This really happens.  Similarly
	--	let f = \x -> e in ...f..f...
555
	-- After inlining f at some of its call sites the original binding may
556
557
558
559
560
561
562
563
	-- (for example) be no longer strictly demanded.
	-- The solution here is a bit ad hoc...
 	info_w_unf = new_bndr_info `setUnfoldingInfo` unfolding
        final_info | loop_breaker		= new_bndr_info
		   | isEvaldUnfolding unfolding = zapDemandInfo info_w_unf `orElse` info_w_unf
		   | otherwise			= info_w_unf

	final_id = new_bndr `setIdInfo` final_info
564
565
566
567
    in
		-- These seqs forces the Id, and hence its IdInfo,
		-- and hence any inner substitutions
    final_id					`seq`
568
    -- pprTrace "Binding" (ppr final_id <+> ppr unfolding) $
569
    return (addNonRec env final_id new_rhs)
570
  where 
571
    unfolding    = mkUnfolding (isTopLevel top_lvl) new_rhs
572
    loop_breaker = isNonRuleLoopBreaker occ_info
573
574
    old_info     = idInfo old_bndr
    occ_info     = occInfo old_info
575
\end{code}
576
577
578



579
580
581
582
583
584
%************************************************************************
%*									*
\subsection[Simplify-simplExpr]{The main function: simplExpr}
%*									*
%************************************************************************

585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
The reason for this OutExprStuff stuff is that we want to float *after*
simplifying a RHS, not before.  If we do so naively we get quadratic
behaviour as things float out.

To see why it's important to do it after, consider this (real) example:

	let t = f x
	in fst t
==>
	let t = let a = e1
		    b = e2
		in (a,b)
	in fst t
==>
	let a = e1
	    b = e2
	    t = (a,b)
	in
	a	-- Can't inline a this round, cos it appears twice
==>
	e1

Each of the ==> steps is a round of simplification.  We'd save a
whole round if we float first.  This can cascade.  Consider

	let f = g d
	in \x -> ...f...
==>
	let f = let d1 = ..d.. in \y -> e
	in \x -> ...f...
==>
	let d1 = ..d..
	in \x -> ...(\y ->e)...

Only in this second round can the \y be applied, and it 
might do the same again.


623
\begin{code}
624
simplExpr :: SimplEnv -> CoreExpr -> SimplM CoreExpr
625
simplExpr env expr = simplExprC env expr (mkBoringStop expr_ty')
626
		   where
627
		     expr_ty' = substTy env (exprType expr)
628
	-- The type in the Stop continuation, expr_ty', is usually not used
629
	-- It's only needed when discarding continuations after finding
630
631
	-- a function that returns bottom.
	-- Hence the lazy substitution
632

633

634
635
636
simplExprC :: SimplEnv -> CoreExpr -> SimplCont -> SimplM CoreExpr
	-- Simplify an expression, given a continuation
simplExprC env expr cont 
637
638
639
640
641
642
643
644
645
646
647
  = -- pprTrace "simplExprC" (ppr expr $$ ppr cont {- $$ ppr (seIdSubst env) -} $$ ppr (seFloats env) ) $
    do	{ (env', expr') <- simplExprF (zapFloats env) expr cont
	; -- pprTrace "simplExprC ret" (ppr expr $$ ppr expr') $
	  -- pprTrace "simplExprC ret3" (ppr (seInScope env')) $
	  -- pprTrace "simplExprC ret4" (ppr (seFloats env')) $
          return (wrapFloats env' expr') }

--------------------------------------------------
simplExprF :: SimplEnv -> InExpr -> SimplCont
	   -> SimplM (SimplEnv, OutExpr)

648
649
650
simplExprF env e cont 
  = -- pprTrace "simplExprF" (ppr e $$ ppr cont $$ ppr (seTvSubst env) $$ ppr (seIdSubst env) {- $$ ppr (seFloats env) -} ) $
    simplExprF' env e cont
651
    				     
652
simplExprF' env (Var v)	       cont = simplVar env v cont
653
654
655
656
simplExprF' env (Lit lit)      cont = rebuild env (Lit lit) cont
simplExprF' env (Note n expr)  cont = simplNote env n expr cont
simplExprF' env (Cast body co) cont = simplCast env body co cont
simplExprF' env (App fun arg)  cont = simplExprF env fun $
657
				      ApplyTo NoDup arg env cont
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675

simplExprF' env expr@(Lam _ _) cont 
  = simplLam env (map zap bndrs) body cont
	-- The main issue here is under-saturated lambdas
	--   (\x1. \x2. e) arg1
	-- Here x1 might have "occurs-once" occ-info, because occ-info
	-- is computed assuming that a group of lambdas is applied
	-- all at once.  If there are too few args, we must zap the 
	-- occ-info.
  where
    n_args   = countArgs cont
    n_params = length bndrs
    (bndrs, body) = collectBinders expr
    zap | n_args >= n_params = \b -> b	
	| otherwise	     = \b -> if isTyVar b then b
				     else zapLamIdInfo b
	-- NB: we count all the args incl type args
	-- so we must count all the binders (incl type lambdas)
676

677
simplExprF' env (Type ty) cont
678
  = ASSERT( contIsRhsOrArg cont )
679
680
    do	{ ty' <- simplType env ty
	; rebuild env (Type ty') cont }
681

682
simplExprF' env (Case scrut bndr case_ty alts) cont
683
684
685
  | not (switchIsOn (getSwitchChecker env) NoCaseOfCase)
  = 	-- Simplify the scrutinee with a Select continuation
    simplExprF env scrut (Select NoDup bndr alts env cont)
686

687
688
  | otherwise
  = 	-- If case-of-case is off, simply simplify the case expression
689
	-- in a vanilla Stop context, and rebuild the result around it
690
691
    do	{ case_expr' <- simplExprC env scrut case_cont
	; rebuild env case_expr' cont }
692
  where
693
    case_cont = Select NoDup bndr alts env (mkBoringStop case_ty')
694
    case_ty'  = substTy env case_ty	-- c.f. defn of simplExpr
695

696
697
698
699
simplExprF' env (Let (Rec pairs) body) cont
  = do	{ env <- simplRecBndrs env (map fst pairs)
		-- NB: bndrs' don't have unfoldings or rules
		-- We add them as we go down
700

701
702
	; env <- simplRecBind env NotTopLevel pairs
	; simplExprF env body cont }
703

704
705
simplExprF' env (Let (NonRec bndr rhs) body) cont
  = simplNonRecE env bndr (rhs, env) ([], body) cont
706
707

---------------------------------
708
709
710
simplType :: SimplEnv -> InType -> SimplM OutType
	-- Kept monadic just so we can do the seqType
simplType env ty
711
712
  = -- pprTrace "simplType" (ppr ty $$ ppr (seTvSubst env)) $
    seqType new_ty   `seq`   returnSmpl new_ty
713
  where
714
    new_ty = substTy env ty
715
716
717
\end{code}


718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
%************************************************************************
%*									*
\subsection{The main rebuilder}
%*									*
%************************************************************************

\begin{code}
rebuild :: SimplEnv -> OutExpr -> SimplCont -> SimplM (SimplEnv, OutExpr)
-- At this point the substitution in the SimplEnv should be irrelevant
-- only the in-scope set and floats should matter
rebuild env expr cont
  = -- pprTrace "rebuild" (ppr expr $$ ppr cont $$ ppr (seFloats env)) $
    case cont of
      Stop {}		      	   -> return (env, expr)
      CoerceIt co cont	      	   -> rebuild env (mkCoerce co expr) cont
      Select _ bndr alts se cont   -> rebuildCase (se `setFloats` env) expr bndr alts cont
      StrictArg fun ty info cont   -> rebuildCall env (fun `App` expr) (funResultTy ty) info cont
      StrictBind b bs body se cont -> do { env' <- simplNonRecX (se `setFloats` env) b expr
					 ; simplLam env' bs body cont }
      ApplyTo _ arg se cont	   -> do { arg' <- simplExpr (se `setInScope` env) arg
				         ; rebuild env (App expr arg') cont }
\end{code}


742
743
744
745
746
747
748
%************************************************************************
%*									*
\subsection{Lambdas}
%*									*
%************************************************************************

\begin{code}
749
750
simplCast :: SimplEnv -> InExpr -> Coercion -> SimplCont
	  -> SimplM (SimplEnv, OutExpr)
751
simplCast env body co cont
752
753
754
  = do	{ co' <- simplType env co
	; simplExprF env body (addCoerce co' cont) }
  where
755
756
       addCoerce co cont = add_coerce co (coercionKind co) cont

simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
757
758
759
       add_coerce co (s1, k1) cont 	-- co :: ty~ty
         | s1 `coreEqType` k1 = cont	-- is a no-op

760
761
       add_coerce co1 (s1, k2) (CoerceIt co2 cont)
         | (l1, t1) <- coercionKind co2
762
763
764
765
766
767
768
769
770
771
772
773
                -- 	coerce T1 S1 (coerce S1 K1 e)
		-- ==>
		--	e, 			if T1=K1
		--	coerce T1 K1 e,		otherwise
		--
		-- For example, in the initial form of a worker
		-- we may find 	(coerce T (coerce S (\x.e))) y
		-- and we'd like it to simplify to e[y/x] in one round 
		-- of simplification
         , s1 `coreEqType` t1  = cont		 -- The coerces cancel out  
         | otherwise           = CoerceIt (mkTransCoercion co1 co2) cont
    
774
775
776
777
778
779
780
781
782
783
784
       add_coerce co (s1s2, t1t2) (ApplyTo dup (Type arg_ty) arg_se cont)
		-- (f `cast` g) ty  --->   (f ty) `cast` (g @ ty)
		-- This implements the PushT rule from the paper
	 | Just (tyvar,_) <- splitForAllTy_maybe s1s2
	 , not (isCoVar tyvar)
	 = ApplyTo dup (Type ty') (zapSubstEnv env) (addCoerce (mkInstCoercion co ty') cont)
	 where
	   ty' = substTy arg_se arg_ty

	-- ToDo: the PushC rule is not implemented at all

785
       add_coerce co (s1s2, t1t2) (ApplyTo dup arg arg_se cont)
786
         | not (isTypeArg arg)  -- This implements the Push rule from the paper
787
         , isFunTy s1s2	  -- t1t2 must be a function type, becuase it's applied
788
789
790
791
792
793
794
795
796
797
798
799
                -- co : s1s2 :=: t1t2
		--	(coerce (T1->T2) (S1->S2) F) E
		-- ===> 
		--	coerce T2 S2 (F (coerce S1 T1 E))
		--
		-- t1t2 must be a function type, T1->T2, because it's applied
		-- to something but s1s2 might conceivably not be
		--
		-- When we build the ApplyTo we can't mix the out-types
		-- with the InExpr in the argument, so we simply substitute
		-- to make it all consistent.  It's a bit messy.
		-- But it isn't a common case.
800
801
		--
		-- Example of use: Trac #995
802
         = ApplyTo dup new_arg (zapSubstEnv env) (addCoerce co2 cont)
803
804
805
806
807
         where
           -- we split coercion t1->t2 :=: s1->s2 into t1 :=: s1 and 
           -- t2 :=: s2 with left and right on the curried form: 
           --    (->) t1 t2 :=: (->) s1 s2
           [co1, co2] = decomposeCo 2 co
808
           new_arg    = mkCoerce (mkSymCoercion co1) arg'
809
810
	   arg'       = substExpr arg_se arg

811
       add_coerce co _ cont = CoerceIt co cont
812
813
\end{code}

814

815
816
817
818
819
%************************************************************************
%*									*
\subsection{Lambdas}
%*									*
%************************************************************************
820
821

\begin{code}
822
823
824
825
simplLam :: SimplEnv -> [InId] -> InExpr -> SimplCont
	 -> SimplM (SimplEnv, OutExpr)

simplLam env [] body cont = simplExprF env body cont
826
827

      	-- Type-beta reduction
828
829
830
831
832
simplLam env (bndr:bndrs) body (ApplyTo _ (Type ty_arg) arg_se cont)
  = ASSERT( isTyVar bndr )
    do	{ tick (BetaReduction bndr)
	; ty_arg' <- simplType (arg_se `setInScope` env) ty_arg
	; simplLam (extendTvSubst env bndr ty_arg') bndrs body cont }
833
834

	-- Ordinary beta reduction
835
836
837
simplLam env (bndr:bndrs) body (ApplyTo _ arg arg_se cont)
  = do	{ tick (BetaReduction bndr)	
	; simplNonRecE env bndr (arg, arg_se) (bndrs, body) cont }
838

839
	-- Not enough args, so there are real lambdas left to put in the result
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
simplLam env bndrs body cont
  = do	{ (env, bndrs') <- simplLamBndrs env bndrs
	; body' <- simplExpr env body
	; new_lam <- mkLam bndrs' body'
	; rebuild env new_lam cont }

------------------
simplNonRecE :: SimplEnv 
	     -> InId 			-- The binder
	     -> (InExpr, SimplEnv)	-- Rhs of binding (or arg of lambda)
	     -> ([InId], InExpr)	-- Body of the let/lambda
					--	\xs.e
	     -> SimplCont
	     -> SimplM (SimplEnv, OutExpr)

-- simplNonRecE is used for
--  * non-top-level non-recursive lets in expressions
--  * beta reduction
--
-- It deals with strict bindings, via the StrictBind continuation,
-- which may abort the whole process
--
-- The "body" of the binding comes as a pair of ([InId],InExpr)
-- representing a lambda; so we recurse back to simplLam
-- Why?  Because of the binder-occ-info-zapping done before 
-- 	 the call to simplLam in simplExprF (Lam ...)

simplNonRecE env bndr (rhs, rhs_se) (bndrs, body) cont
  | preInlineUnconditionally env NotTopLevel bndr rhs
  = do	{ tick (PreInlineUnconditionally bndr)
	; simplLam (extendIdSubst env bndr (mkContEx rhs_se rhs)) bndrs body cont }

simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
872
  | isStrictId bndr
873
874
875
876
877
878
879
  = do	{ simplExprF (rhs_se `setFloats` env) rhs 
		     (StrictBind bndr bndrs body env cont) }

  | otherwise
  = do	{ (env, bndr') <- simplBinder env bndr
	; env <- simplLazyBind env NotTopLevel NonRecursive bndr bndr' rhs rhs_se
	; simplLam env bndrs body cont }
880
881
\end{code}

882

883
884
885
886
887
888
%************************************************************************
%*									*
\subsection{Notes}
%*									*
%************************************************************************

sof's avatar
sof committed
889
\begin{code}
890
891
-- Hack alert: we only distinguish subsumed cost centre stacks for the 
-- purposes of inlining.  All other CCCSs are mapped to currentCCS.
892
simplNote env (SCC cc) e cont
893
894
  = do 	{ e' <- simplExpr (setEnclosingCC env currentCCS) e
	; rebuild env (mkSCC cc e') cont }
895
896
897
898

-- See notes with SimplMonad.inlineMode
simplNote env InlineMe e cont
  | contIsRhsOrArg cont		-- Totally boring continuation; see notes above
899
900
901
  = do	{ 			-- Don't inline inside an INLINE expression
	  e' <- simplExpr (setMode inlineMode env) e
	; rebuild env (mkInlineMe e') cont }
902
903
904
905

  | otherwise  	-- Dissolve the InlineMe note if there's
		-- an interesting context of any kind to combine with
		-- (even a type application -- anything except Stop)
906
  = simplExprF env e cont
907
908

simplNote env (CoreNote s) e cont
909
910
  = simplExpr env e    `thenSmpl` \ e' ->
    rebuild env (Note (CoreNote s) e') cont
911
912
913
\end{code}


914
915
%************************************************************************
%*									*
916
\subsection{Dealing with calls}
917
918
%*									*
%************************************************************************
919

920
\begin{code}
921
simplVar env var cont
922
923
924
  = case substId env var of
	DoneEx e	 -> simplExprF (zapSubstEnv env) e cont
	ContEx tvs ids e -> simplExprF (setSubstEnv env tvs ids) e cont
925
	DoneId var1      -> completeCall (zapSubstEnv env) var1 cont
926
		-- Note [zapSubstEnv]
927
928
929
930
931
932
933
934
		-- The template is already simplified, so don't re-substitute.
		-- This is VITAL.  Consider
		--	let x = e in
		--	let y = \z -> ...x... in
		--	\ x -> ...y...
		-- We'll clone the inner \x, adding x->x' in the id_subst
		-- Then when we inline y, we must *not* replace x by x' in
		-- the inlined copy!!
935

936
---------------------------------------------------------
937
--	Dealing with a call site
938

939
completeCall env var cont
940
941
942
943
944
945
946
947
948
949
950
951
  = do	{ dflags <- getDOptsSmpl
	; let	(args,call_cont) = contArgs cont
		-- The args are OutExprs, obtained by *lazily* substituting
		-- in the args found in cont.  These args are only examined
		-- to limited depth (unless a rule fires).  But we must do
		-- the substitution; rule matching on un-simplified args would
		-- be bogus

	------------- First try rules ----------------
	-- Do this before trying inlining.  Some functions have 
	-- rules *and* are strict; in this case, we don't want to 
	-- inline the wrapper of the non-specialised thing; better
952
	-- to call the specialised thing instead.
953
	--
954
955
956
	-- We used to use the black-listing mechanism to ensure that inlining of 
	-- the wrapper didn't occur for things that have specialisations till a 
	-- later phase, so but now we just try RULES first
957
	--
958
959
960
961
962
963
964
965
966
967
968
	-- You might think that we shouldn't apply rules for a loop breaker: 
	-- doing so might give rise to an infinite loop, because a RULE is
	-- rather like an extra equation for the function:
	--	RULE:		f (g x) y = x+y
	--	Eqn:		f a     y = a-y
	--
	-- But it's too drastic to disable rules for loop breakers.  
	-- Even the foldr/build rule would be disabled, because foldr 
	-- is recursive, and hence a loop breaker:
	--	foldr k z (build g) = g k z
	-- So it's up to the programmer: rules can cause divergence
969
970
971
972
973
974
975
976
977
	; let	in_scope   = getInScope env
		rules	   = getRules env
		maybe_rule = case activeRule env of
				Nothing     -> Nothing	-- No rules apply
				Just act_fn -> lookupRule act_fn in_scope 
							  rules var args 
	; case maybe_rule of {
	    Just (rule, rule_rhs) -> 
		tick (RuleFired (ru_name rule))			`thenSmpl_`
978
		(if dopt Opt_D_dump_rule_firings dflags then
979
		   pprTrace "Rule fired" (vcat [
980
			text "Rule:" <+> ftext (ru_name rule),
981
			text "Before:" <+> ppr var <+> sep (map pprParendExpr args),
982
983
			text "After: " <+> pprCoreExpr rule_rhs,
			text "Cont:  " <+> ppr call_cont])
984
985
		 else
			id)		$
986
987
		simplExprF env rule_rhs (dropArgs (ruleArity rule) cont)
		-- The ruleArity says how many args the rule consumed
988
	
989
990
991
992
993
994
995
996
997
998
	  ; Nothing -> do	-- No rules

	------------- Next try inlining ----------------
	{ let	arg_infos = [interestingArg arg | arg <- args, isValArg arg]
		n_val_args = length arg_infos
	      	interesting_cont = interestingCallContext (notNull args)
						  	  (notNull arg_infos)
						  	  call_cont
	 	active_inline = activeInline env var
		maybe_inline  = callSiteInline dflags active_inline
999
				       var arg_infos interesting_cont
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
	; case maybe_inline of {
	    Just unfolding  	-- There is an inlining!
	      ->  do { tick (UnfoldingDone var)
		     ; (if dopt Opt_D_dump_inlinings dflags then
			   pprTrace "Inlining done" (vcat [
				text "Before:" <+> ppr var <+> sep (map pprParendExpr args),
				text "Inlined fn: " <+> nest 2 (ppr unfolding),
				text "Cont:  " <+> ppr call_cont])
			 else
				id)
		       simplExprF env unfolding cont }

	    ; Nothing -> 		-- No inlining!

	------------- No inlining! ----------------
	-- Next, look for rules or specialisations that match
	--
	rebuildCall env (Var var) (idType var) 
		    (mkArgInfo var n_val_args call_cont) cont
    }}}}
1020

1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
rebuildCall :: SimplEnv
	    -> OutExpr -> OutType	-- Function and its type
	    -> (Bool, [Bool])		-- See SimplUtils.mkArgInfo
	    -> SimplCont
	    -> SimplM (SimplEnv, OutExpr)
rebuildCall env fun fun_ty (has_rules, []) cont
  -- When we run out of strictness args, it means
  -- that the call is definitely bottom; see SimplUtils.mkArgInfo
  -- Then we want to discard the entire strict continuation.  E.g.
  --	* case (error "hello") of { ... }
  --	* (error "Hello") arg
  --	* f (error "Hello") where f is strict
  --	etc
  -- Then, especially in the first of these cases, we'd like to discard
  -- the continuation, leaving just the bottoming expression.  But the
  -- type might not be right, so we may have to add a coerce.
  | not (contIsTrivial cont)	 -- Only do thia if there is a non-trivial
  = return (env, mk_coerce fun)  -- contination to discard, else we do it
  where				 -- again and again!
    cont_ty = contResultType cont
    co      = mkUnsafeCoercion fun_ty cont_ty
    mk_coerce expr | cont_ty `coreEqType` fun_ty = fun
		   | otherwise = mkCoerce co fun

rebuildCall env fun fun_ty info (ApplyTo _ (Type arg_ty) se cont)
  = do	{ ty' <- simplType (se `setInScope` env) arg_ty
	; rebuildCall env (fun `App` Type ty') (applyTy fun_ty ty') info cont }

rebuildCall env fun fun_ty (has_rules, str:strs) (ApplyTo _ arg arg_se cont)
  | str || isStrictType arg_ty		-- Strict argument
  = -- pprTrace "Strict Arg" (ppr arg $$ ppr (seIdSubst env) $$ ppr (seInScope env)) $
    simplExprF (arg_se `setFloats` env) arg
	       (StrictArg fun fun_ty (has_rules, strs) cont)
		-- Note [Shadowing]

  | otherwise				-- Lazy argument
	-- DO NOT float anything outside, hence simplExprC
	-- There is no benefit (unlike in a let-binding), and we'd
	-- have to be very careful about bogus strictness through 
	-- floating a demanded let.
  = do	{ arg' <- simplExprC (arg_se `setInScope` env) arg
			     (mkLazyArgStop arg_ty has_rules)
	; rebuildCall env (fun `App` arg') res_ty (has_rules, strs) cont }
1064
  where
1065
    (arg_ty, res_ty) = splitFunTy fun_ty
1066

1067
1068
rebuildCall env fun fun_ty info cont
  = rebuild env fun cont
1069
\end{code}
1070

1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
Note [Shadowing]
~~~~~~~~~~~~~~~~
This part of the simplifier may break the no-shadowing invariant
Consider
	f (...(\a -> e)...) (case y of (a,b) -> e')
where f is strict in its second arg
If we simplify the innermost one first we get (...(\a -> e)...)
Simplifying the second arg makes us float the case out, so we end up with
	case y of (a,b) -> f (...(\a -> e)...) e'
So the output does not have the no-shadowing invariant.  However, there is
no danger of getting name-capture, because when the first arg was simplified
we used an in-scope set that at least mentioned all the variables free in its
static environment, and that is enough.

We can't just do innermost first, or we'd end up with a dual problem:
	case x of (a,b) -> f e (...(\a -> e')...)

I spent hours trying to recover the no-shadowing invariant, but I just could
not think of an elegant way to do it.  The simplifier is already knee-deep in
continuations.  We have to keep the right in-scope set around; AND we have
to get the effect that finding (error "foo") in a strict arg position will
discard the entire application and replace it with (error "foo").  Getting
all this at once is TOO HARD!
1094

1095
1096
%************************************************************************
%*									*
1097
		Rebuilding a cse expression
1098
1099
%*									*
%************************************************************************
1100

1101
1102
1103
Blob of helper functions for the "case-of-something-else" situation.

\begin{code}
1104
---------------------------------------------------------
1105
-- 	Eliminate the case if possible
1106

1107
1108
1109
rebuildCase :: SimplEnv
	    -> OutExpr		-- Scrutinee
	    -> InId		-- Case binder
1110
	    -> [InAlt]		-- Alternatives (inceasing order)
1111
	    -> SimplCont
1112
	    -> SimplM (SimplEnv, OutExpr)
1113

1114
1115
1116
1117
--------------------------------------------------
--	1. Eliminate the case if there's a known constructor
--------------------------------------------------

1118
1119
1120
1121
rebuildCase env scrut case_bndr alts cont
  | Just (con,args) <- exprIsConApp_maybe scrut	
	-- Works when the scrutinee is a variable with a known unfolding
	-- as well as when it's an explicit constructor application
1122
  = knownCon env scrut (DataAlt con) args case_bndr alts cont
1123

1124
1125
  | Lit lit <- scrut	-- No need for same treatment as constructors
			-- because literals are inlined more vigorously
1126
  = knownCon env scrut (LitAlt lit) [] case_bndr alts cont
1127

1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167

--------------------------------------------------
--	2. Eliminate the case if scrutinee is evaluated
--------------------------------------------------

rebuildCase env scrut case_bndr [(con,bndrs,rhs)] cont
  -- See if we can get rid of the case altogether
  -- See the extensive notes on case-elimination above
  -- mkCase made sure that if all the alternatives are equal, 
  -- then there is now only one (DEFAULT) rhs
 | all isDeadBinder bndrs	-- bndrs are [InId]

	-- Check that the scrutinee can be let-bound instead of case-bound
 , exprOkForSpeculation scrut
		-- OK not to evaluate it
		-- This includes things like (==# a# b#)::Bool
		-- so that we simplify 
		-- 	case ==# a# b# of { True -> x; False -> x }
		-- to just
		--	x
		-- This particular example shows up in default methods for
		-- comparision operations (e.g. in (>=) for Int.Int32)
	|| exprIsHNF scrut			-- It's already evaluated
	|| var_demanded_later scrut		-- It'll be demanded later

--      || not opt_SimplPedanticBottoms)	-- Or we don't care!
--	We used to allow improving termination by discarding cases, unless -fpedantic-bottoms was on,
-- 	but that breaks badly for the dataToTag# primop, which relies on a case to evaluate
-- 	its argument:  case x of { y -> dataToTag# y }
--	Here we must *not* discard the case, because dataToTag# just fetches the tag from
--	the info pointer.  So we'll be pedantic all the time, and see if that gives any
-- 	other problems
--	Also we don't want to discard 'seq's
  = do	{ tick (CaseElim case_bndr)
	; env <- simplNonRecX env case_bndr scrut
	; simplExprF env rhs cont }
  where
	-- The case binder is going to be evaluated later, 
	-- and the scrutinee is a simple variable
    var_demanded_later (Var v) = isStrictDmd (idNewDemandInfo case_bndr)
1168
1169
1170
    		       	         && not (isTickBoxOp v)	
				    -- ugly hack; covering this case is what 
				    -- exprOkForSpeculation was intended for.
1171
1172
1173
1174
1175
1176
1177
1178
    var_demanded_later other   = False


--------------------------------------------------
--	3. Catch-all case
--------------------------------------------------

rebuildCase env scrut case_bndr alts cont
1179
1180
1181
  = do	{ 	-- Prepare the continuation;
		-- The new subst_env is in place
	  (env, dup_cont, nodup_cont) <- prepareCaseCont env alts cont
1182

1183
1184
1185
1186
	-- Simplify the alternatives
	; (case_bndr', alts') <- simplAlts env scrut case_bndr alts dup_cont
	; let res_ty' = contResultType dup_cont
	; case_expr <- mkCase scrut case_bndr' res_ty' alts'
sof's avatar
sof committed
1187

1188
1189
	-- Notice that rebuildDone returns the in-scope set from env, not alt_env
	-- The case binder *not* scope over the whole returned case-expression
1190
	; rebuild env case_expr nodup_cont }
1191
\end{code}
1192

1193
1194
1195
1196
1197
simplCaseBinder checks whether the scrutinee is a variable, v.  If so,
try to eliminate uses of v in the RHSs in favour of case_bndr; that
way, there's a chance that v will now only be used once, and hence
inlined.

simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1198
1199
Note [no-case-of-case]
~~~~~~~~~~~~~~~~~~~~~~
1200
1201
1202
There is a time we *don't* want to do that, namely when
-fno-case-of-case is on.  This happens in the first simplifier pass,
and enhances full laziness.  Here's the bad case:
1203
1204
1205
1206
1207
	f = \ y -> ...(case x of I# v -> ...(case x of ...) ... )
If we eliminate the inner case, we trap it inside the I# v -> arm,
which might prevent some full laziness happening.  I've seen this
in action in spectral/cichelli/Prog.hs:
	 [(m,n) | m <- [1..max], n <- [1..max]]
1208
1209
Hence the check for NoCaseOfCase.

simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1210
1211
1212
1213
Note [Suppressing the case binder-swap]
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
There is another situation when it might make sense to suppress the
case-expression binde-swap. If we have
1214
1215
1216
1217
1218
1219
1220
1221
1222

    case x of w1 { DEFAULT -> case x of w2 { A -> e1; B -> e2 }
	           ...other cases .... }

We'll perform the binder-swap for the outer case, giving

    case x of w1 { DEFAULT -> case w1 of w2 { A -> e1; B -> e2 } 
	           ...other cases .... }

1223
1224
1225
1226
But there is no point in doing it for the inner case, because w1 can't
be inlined anyway.  Furthermore, doing the case-swapping involves
zapping w2's occurrence info (see paragraphs that follow), and that
forces us to bind w2 when doing case merging.  So we get
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238

    case x of w1 { A -> let w2 = w1 in e1
		   B -> let w2 = w1 in e2
	           ...other cases .... }

This is plain silly in the common case where w2 is dead.

Even so, I can't see a good way to implement this idea.  I tried
not doing the binder-swap if the scrutinee was already evaluated
but that failed big-time:

	data T = MkT !Int
1239

1240
1241
1242
	case v of w  { MkT x ->
	case x of x1 { I# y1 ->
	case x of x2 { I# y2 -> ...
1243

1244
1245
1246
1247
1248
Notice that because MkT is strict, x is marked "evaluated".  But to
eliminate the last case, we must either make sure that x (as well as
x1) has unfolding MkT y1.  THe straightforward thing to do is to do
the binder-swap.  So this whole note is a no-op.

simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1249
1250
Note [zapOccInfo]
~~~~~~~~~~~~~~~~~
1251
1252
1253
1254
If we replace the scrutinee, v, by tbe case binder, then we have to nuke
any occurrence info (eg IAmDead) in the case binder, because the
case-binder now effectively occurs whenever v does.  AND we have to do
the same for the pattern-bound variables!  Example:
1255

1256
	(case x of { (a,b) -> a }) (case x of { (p,q) -> q })
1257

1258
1259
Here, b and p are dead.  But when we move the argment inside the first
case RHS, and eliminate the second case, we get
1260

1261
	case x of { (a,b) -> a b }
1262

1263
Urk! b is alive!  Reason: the scrutinee was a variable, and case elimination
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
happened.  

Indeed, this can happen anytime the case binder isn't dead:
	case <any> of x { (a,b) -> 
        case x of { (p,q) -> p } }
Here (a,b) both look dead, but come alive after the inner case is eliminated.
The point is that we bring into the envt a binding
	let x = (a,b) 
after the outer case, and that makes (a,b) alive.  At least we do unless
the case binder is guaranteed dead.
1274

simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1275
1276
1277
1278
1279
1280
1281
1282
1283
Note [Case of cast]
~~~~~~~~~~~~~~~~~~~
Consider 	case (v `cast` co) of x { I# ->
		... (case (v `cast` co) of {...}) ...
We'd like to eliminate the inner case.  We can get this neatly by 
arranging that inside the outer case we add the unfolding
	v |-> x `cast` (sym co)
to v.  Then we should inline v at the inner case, cancel the casts, and away we go
	
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371

Note [Case elimination]
~~~~~~~~~~~~~~~~~~~~~~~
The case-elimination transformation discards redundant case expressions.
Start with a simple situation:

	case x# of	===>   e[x#/y#]
	  y# -> e

(when x#, y# are of primitive type, of course).  We can't (in general)
do this for algebraic cases, because we might turn bottom into
non-bottom!

The code in SimplUtils.prepareAlts has the effect of generalise this
idea to look for a case where we're scrutinising a variable, and we
know that only the default case can match.  For example:

	case x of
	  0#      -> ...
	  DEFAULT -> ...(case x of
			 0#      -> ...
			 DEFAULT -> ...) ...

Here the inner case is first trimmed to have only one alternative, the
DEFAULT, after which it's an instance of the previous case.  This
really only shows up in eliminating error-checking code.

We also make sure that we deal with this very common case:

 	case e of 
	  x -> ...x...

Here we are using the case as a strict let; if x is used only once
then we want to inline it.  We have to be careful that this doesn't 
make the program terminate when it would have diverged before, so we
check that 
	- e is already evaluated (it may so if e is a variable)
	- x is used strictly, or

Lastly, the code in SimplUtils.mkCase combines identical RHSs.  So

	case e of	===> case e of DEFAULT -> r
	   True  -> r
	   False -> r

Now again the case may be elminated by the CaseElim transformation.


Further notes about case elimination
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Consider:	test :: Integer -> IO ()
		test = print

Turns out that this compiles to:
    Print.test
      = \ eta :: Integer
	  eta1 :: State# RealWorld ->
	  case PrelNum.< eta PrelNum.zeroInteger of wild { __DEFAULT ->
	  case hPutStr stdout
		 (PrelNum.jtos eta ($w[] @ Char))
		 eta1
	  of wild1 { (# new_s, a4 #) -> PrelIO.lvl23 new_s  }}

Notice the strange '<' which has no effect at all. This is a funny one.  
It started like this:

f x y = if x < 0 then jtos x
          else if y==0 then "" else jtos x

At a particular call site we have (f v 1).  So we inline to get

	if v < 0 then jtos x 
	else if 1==0 then "" else jtos x

Now simplify the 1==0 conditional:

	if v<0 then jtos v else jtos v

Now common-up the two branches of the case:

	case (v<0) of DEFAULT -> jtos v

Why don't we drop the case?  Because it's strict in v.  It's technically
wrong to drop even unnecessary evaluations, and in practice they
may be a result of 'seq' so we *definitely* don't want to drop those.
I don't really know how to improve this situation.


1372
\begin{code}
1373
simplCaseBinder :: SimplEnv -> OutExpr -> InId -> SimplM (SimplEnv, OutId)
simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1374
1375
1376
1377
1378
simplCaseBinder env scrut case_bndr
  | switchIsOn (getSwitchChecker env) NoCaseOfCase
	-- See Note [no-case-of-case]
  = do	{ (env, case_bndr') <- simplBinder env case_bndr
	; return (env, case_bndr') }
1379

simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1380
simplCaseBinder env (Var v) case_bndr
1381
1382
-- Failed try [see Note 2 above]
--     not (isEvaldUnfolding (idUnfolding v))
simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1383
1384
  = do	{ (env, case_bndr') <- simplBinder env (zapOccInfo case_bndr)
	; return (modifyInScope env v case_bndr', case_bndr') }
1385
1386
	-- We could extend the substitution instead, but it would be
	-- a hack because then the substitution wouldn't be idempotent
1387
	-- any more (v is an OutId).  And this does just as well.
1388
	    
simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1389
1390
1391
1392
1393
simplCaseBinder env (Cast (Var v) co) case_bndr		-- Note [Case of cast]
  = do	{ (env, case_bndr') <- simplBinder env (zapOccInfo case_bndr)
  	; let rhs = Cast (Var case_bndr') (mkSymCoercion co)
	; return (addBinderUnfolding env v rhs, case_bndr') }

1394
simplCaseBinder env other_scrut case_bndr 
simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1395
1396
  = do	{ (env, case_bndr') <- simplBinder env case_bndr
	; return (env, case_bndr') }
1397

simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1398
zapOccInfo :: InId -> InId	-- See Note [zapOccInfo]
1399
zapOccInfo b = b `setIdOccInfo` NoOccInfo
1400
\end{code}
1401
1402


1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
simplAlts does two things:

1.  Eliminate alternatives that cannot match, including the
    DEFAULT alternative.

2.  If the DEFAULT alternative can match only one possible constructor,
    then make that constructor explicit.
    e.g.
	case e of x { DEFAULT -> rhs }
     ===>
	case e of x { (a,b) -> rhs }
    where the type is a single constructor type.  This gives better code
    when rhs also scrutinises x or e.

Here "cannot match" includes knowledge from GADTs

It's a good idea do do this stuff before simplifying the alternatives, to
avoid simplifying alternatives we know can't happen, and to come up with
the list of constructors that are handled, to put into the IdInfo of the
case binder, for use when simplifying the alternatives.

Eliminating the default alternative in (1) isn't so obvious, but it can
happen:

data Colour = Red | Green | Blue

f x = case x of
	Red -> ..
	Green -> ..
	DEFAULT -> h x

h y = case y of
	Blue -> ..
	DEFAULT -> [ case y of ... ]

If we inline h into f, the default case of the inlined h can't happen.
If we don't notice this, we may end up filtering out *all* the cases
of the inner case y, which give us nowhere to go!

sof's avatar
sof committed
1442

1443
\begin{code}
1444
simplAlts :: SimplEnv 
1445
	  -> OutExpr
1446
	  -> InId			-- Case binder
1447
	  -> [InAlt] -> SimplCont
1448
1449
1450
1451
1452
1453
1454
1455
1456
	  -> SimplM (OutId, [OutAlt])	-- Includes the continuation
-- Like simplExpr, this just returns the simplified alternatives;
-- it not return an environment

simplAlts env scrut case_bndr alts cont'
  = -- pprTrace "simplAlts" (ppr alts $$ ppr (seIdSubst env)) $
    do	{ let alt_env = zapFloats env
	; (alt_env, case_bndr') <- simplCaseBinder alt_env scrut case_bndr

1457
	; (imposs_deflt_cons, in_alts) <- prepareAlts scrut case_bndr' alts
1458

1459
	; alts' <- mapM (simplAlt alt_env imposs_deflt_cons case_bndr' cont') in_alts
1460
	; return (case_bndr', alts') }
1461

1462
------------------------------------
1463
1464
simplAlt :: SimplEnv
	 -> [AltCon]	-- These constructors can't be present when
1465
			-- matching the DEFAULT alternative
1466
1467
1468
	 -> OutId	-- The case binder
	 -> SimplCont
	 -> InAlt
1469
	 -> SimplM OutAlt
1470

1471
simplAlt env imposs_deflt_cons case_bndr' cont' (DEFAULT, bndrs, rhs)
1472
  = ASSERT( null bndrs )
1473
    do	{ let env' = addBinderOtherCon env case_bndr' imposs_deflt_cons
1474
1475
1476
		-- Record the constructors that the case-binder *can't* be.
	; rhs' <- simplExprC env' rhs cont'
	; return (DEFAULT, [], rhs') }
1477

1478
simplAlt env imposs_deflt_cons case_bndr' cont' (LitAlt lit, bndrs, rhs)
1479
  = ASSERT( null bndrs )
1480
1481
1482
    do	{ let env' = addBinderUnfolding env case_bndr' (Lit lit)
	; rhs' <- simplExprC env' rhs cont'
	; return (LitAlt lit, [], rhs') }
1483

1484
simplAlt env imposs_deflt_cons case_bndr' cont' (DataAlt con, vs, rhs)
1485
1486
  = do	{	-- Deal with the pattern-bound variables
	  (env, vs') <- simplBinders env (add_evals con vs)
1487

1488
1489
1490
1491
		-- Mark the ones that are in ! positions in the
		-- data constructor as certainly-evaluated.
	; let vs'' = add_evals con vs'

1492
		-- Bind the case-binder to (con args)
1493
	; let inst_tys' = tyConAppArgs (idType case_bndr')
1494
	      con_args  = map Type inst_tys' ++ varsToCoreExprs vs'' 
1495
1496
1497
	      env'      = addBinderUnfolding env case_bndr' (mkConApp con con_args)

	; rhs' <- simplExprC env' rhs cont'
1498
	; return (DataAlt con, vs'', rhs') }
1499
  where
1500
1501
1502
1503
1504
1505
1506
	-- add_evals records the evaluated-ness of the bound variables of
	-- a case pattern.  This is *important*.  Consider
	--	data T = T !Int !Int
	--
	--	case x of { T a b -> T (a+1) b }
	--
	-- We really must record that b is already evaluated so that we don't
1507
	-- go and re-evaluate it when constructing the result.
1508
	-- See Note [Data-con worker strictness] in MkId.lhs
1509
    add_evals dc vs = cat_evals dc vs (dataConRepStrictness dc)
sof's avatar
sof committed
1510

1511
1512
    cat_evals dc vs strs
	= go vs strs
1513
	where
1514
	  go [] [] = []
1515
	  go (v:vs) strs | isTyVar v = v : go vs strs
1516
1517
1518
1519
1520
	  go (v:vs) (str:strs)
	    | isMarkedStrict str = evald_v  : go vs strs
	    | otherwise          = zapped_v : go vs strs
	    where
	      zapped_v = zap_occ_info v
1521
	      evald_v  = zapped_v `setIdUnfolding` evaldUnfolding
1522
	  go _ _ = pprPanic "cat_evals" (ppr dc $$ ppr vs $$ ppr strs)
1523
1524
1525
1526

	-- If the case binder is alive, then we add the unfolding
	--	case_bndr = C vs
	-- to the envt; so vs are now very much alive
1527
	-- Note [Aug06] I can't see why this actually matters
1528
    zap_occ_info | isDeadBinder case_bndr' = \id -> id
1529
		 | otherwise		   = zapOccInfo
1530

simonpj@microsoft.com's avatar
simonpj@microsoft.com committed
1531
1532
1533
1534
1535
1536
1537
addBinderUnfolding :: SimplEnv -> Id -> CoreExpr -> SimplEnv
addBinderUnfolding env bndr rhs
  = modifyInScope env bndr (bndr `setIdUnfolding` mkUnfolding False rhs)

addBinderOtherCon :: SimplEnv -> Id -> [AltCon] -> SimplEnv
addBinderOtherCon env bndr cons
  = modifyInScope env bndr (bndr `setIdUnfolding` mkOtherCon cons)
1538
\end{code}
sof's avatar
sof committed
1539
1540