summaryrefslogtreecommitdiff
path: root/compiler/GHC/Iface/Tidy.hs
diff options
context:
space:
mode:
authorÖmer Sinan Ağacan <omeragacan@gmail.com>2019-10-14 15:44:58 +0300
committerÖmer Sinan Ağacan <omeragacan@gmail.com>2020-01-31 12:21:10 +0300
commitc846618ae0f8601515683a4c7677c20c3272a50f (patch)
tree22caa68b7c6cdf3464d078e556f7eac19400b0bf /compiler/GHC/Iface/Tidy.hs
parent01b15b835a7555c501df862b4dc8cc8eaff86afc (diff)
downloadhaskell-c846618ae0f8601515683a4c7677c20c3272a50f.tar.gz
Do CafInfo/SRT analysis in Cmm
This patch removes all CafInfo predictions and various hacks to preserve predicted CafInfos from the compiler and assigns final CafInfos to interface Ids after code generation. SRT analysis is extended to support static data, and Cmm generator is modified to allow generating static_link fields after SRT analysis. This also fixes `-fcatch-bottoms`, which introduces error calls in case expressions in CorePrep, which runs *after* CoreTidy (which is where we decide on CafInfos) and turns previously non-CAFFY things into CAFFY. Fixes #17648 Fixes #9718 Evaluation ========== NoFib ----- Boot with: `make boot mode=fast` Run: `make mode=fast EXTRA_RUNTEST_OPTS="-cachegrind" NoFibRuns=1` -------------------------------------------------------------------------------- Program Size Allocs Instrs Reads Writes -------------------------------------------------------------------------------- CS -0.0% 0.0% -0.0% -0.0% -0.0% CSD -0.0% 0.0% -0.0% -0.0% -0.0% FS -0.0% 0.0% -0.0% -0.0% -0.0% S -0.0% 0.0% -0.0% -0.0% -0.0% VS -0.0% 0.0% -0.0% -0.0% -0.0% VSD -0.0% 0.0% -0.0% -0.0% -0.5% VSM -0.0% 0.0% -0.0% -0.0% -0.0% anna -0.1% 0.0% -0.0% -0.0% -0.0% ansi -0.0% 0.0% -0.0% -0.0% -0.0% atom -0.0% 0.0% -0.0% -0.0% -0.0% awards -0.0% 0.0% -0.0% -0.0% -0.0% banner -0.0% 0.0% -0.0% -0.0% -0.0% bernouilli -0.0% 0.0% -0.0% -0.0% -0.0% binary-trees -0.0% 0.0% -0.0% -0.0% -0.0% boyer -0.0% 0.0% -0.0% -0.0% -0.0% boyer2 -0.0% 0.0% -0.0% -0.0% -0.0% bspt -0.0% 0.0% -0.0% -0.0% -0.0% cacheprof -0.0% 0.0% -0.0% -0.0% -0.0% calendar -0.0% 0.0% -0.0% -0.0% -0.0% cichelli -0.0% 0.0% -0.0% -0.0% -0.0% circsim -0.0% 0.0% -0.0% -0.0% -0.0% clausify -0.0% 0.0% -0.0% -0.0% -0.0% comp_lab_zift -0.0% 0.0% -0.0% -0.0% -0.0% compress -0.0% 0.0% -0.0% -0.0% -0.0% compress2 -0.0% 0.0% -0.0% -0.0% -0.0% constraints -0.0% 0.0% -0.0% -0.0% -0.0% cryptarithm1 -0.0% 0.0% -0.0% -0.0% -0.0% cryptarithm2 -0.0% 0.0% -0.0% -0.0% -0.0% cse -0.0% 0.0% -0.0% -0.0% -0.0% digits-of-e1 -0.0% 0.0% -0.0% -0.0% -0.0% digits-of-e2 -0.0% 0.0% -0.0% -0.0% -0.0% dom-lt -0.0% 0.0% -0.0% -0.0% -0.0% eliza -0.0% 0.0% -0.0% -0.0% -0.0% event -0.0% 0.0% -0.0% -0.0% -0.0% exact-reals -0.0% 0.0% -0.0% -0.0% -0.0% exp3_8 -0.0% 0.0% -0.0% -0.0% -0.0% expert -0.0% 0.0% -0.0% -0.0% -0.0% fannkuch-redux -0.0% 0.0% -0.0% -0.0% -0.0% fasta -0.0% 0.0% -0.0% -0.0% -0.0% fem -0.0% 0.0% -0.0% -0.0% -0.0% fft -0.0% 0.0% -0.0% -0.0% -0.0% fft2 -0.0% 0.0% -0.0% -0.0% -0.0% fibheaps -0.0% 0.0% -0.0% -0.0% -0.0% fish -0.0% 0.0% -0.0% -0.0% -0.0% fluid -0.1% 0.0% -0.0% -0.0% -0.0% fulsom -0.0% 0.0% -0.0% -0.0% -0.0% gamteb -0.0% 0.0% -0.0% -0.0% -0.0% gcd -0.0% 0.0% -0.0% -0.0% -0.0% gen_regexps -0.0% 0.0% -0.0% -0.0% -0.0% genfft -0.0% 0.0% -0.0% -0.0% -0.0% gg -0.0% 0.0% -0.0% -0.0% -0.0% grep -0.0% 0.0% -0.0% -0.0% -0.0% hidden -0.0% 0.0% -0.0% -0.0% -0.0% hpg -0.1% 0.0% -0.0% -0.0% -0.0% ida -0.0% 0.0% -0.0% -0.0% -0.0% infer -0.0% 0.0% -0.0% -0.0% -0.0% integer -0.0% 0.0% -0.0% -0.0% -0.0% integrate -0.0% 0.0% -0.0% -0.0% -0.0% k-nucleotide -0.0% 0.0% -0.0% -0.0% -0.0% kahan -0.0% 0.0% -0.0% -0.0% -0.0% knights -0.0% 0.0% -0.0% -0.0% -0.0% lambda -0.0% 0.0% -0.0% -0.0% -0.0% last-piece -0.0% 0.0% -0.0% -0.0% -0.0% lcss -0.0% 0.0% -0.0% -0.0% -0.0% life -0.0% 0.0% -0.0% -0.0% -0.0% lift -0.0% 0.0% -0.0% -0.0% -0.0% linear -0.1% 0.0% -0.0% -0.0% -0.0% listcompr -0.0% 0.0% -0.0% -0.0% -0.0% listcopy -0.0% 0.0% -0.0% -0.0% -0.0% maillist -0.0% 0.0% -0.0% -0.0% -0.0% mandel -0.0% 0.0% -0.0% -0.0% -0.0% mandel2 -0.0% 0.0% -0.0% -0.0% -0.0% mate -0.0% 0.0% -0.0% -0.0% -0.0% minimax -0.0% 0.0% -0.0% -0.0% -0.0% mkhprog -0.0% 0.0% -0.0% -0.0% -0.0% multiplier -0.0% 0.0% -0.0% -0.0% -0.0% n-body -0.0% 0.0% -0.0% -0.0% -0.0% nucleic2 -0.0% 0.0% -0.0% -0.0% -0.0% para -0.0% 0.0% -0.0% -0.0% -0.0% paraffins -0.0% 0.0% -0.0% -0.0% -0.0% parser -0.1% 0.0% -0.0% -0.0% -0.0% parstof -0.1% 0.0% -0.0% -0.0% -0.0% pic -0.0% 0.0% -0.0% -0.0% -0.0% pidigits -0.0% 0.0% -0.0% -0.0% -0.0% power -0.0% 0.0% -0.0% -0.0% -0.0% pretty -0.0% 0.0% -0.3% -0.4% -0.4% primes -0.0% 0.0% -0.0% -0.0% -0.0% primetest -0.0% 0.0% -0.0% -0.0% -0.0% prolog -0.0% 0.0% -0.0% -0.0% -0.0% puzzle -0.0% 0.0% -0.0% -0.0% -0.0% queens -0.0% 0.0% -0.0% -0.0% -0.0% reptile -0.0% 0.0% -0.0% -0.0% -0.0% reverse-complem -0.0% 0.0% -0.0% -0.0% -0.0% rewrite -0.0% 0.0% -0.0% -0.0% -0.0% rfib -0.0% 0.0% -0.0% -0.0% -0.0% rsa -0.0% 0.0% -0.0% -0.0% -0.0% scc -0.0% 0.0% -0.3% -0.5% -0.4% sched -0.0% 0.0% -0.0% -0.0% -0.0% scs -0.0% 0.0% -0.0% -0.0% -0.0% simple -0.1% 0.0% -0.0% -0.0% -0.0% solid -0.0% 0.0% -0.0% -0.0% -0.0% sorting -0.0% 0.0% -0.0% -0.0% -0.0% spectral-norm -0.0% 0.0% -0.0% -0.0% -0.0% sphere -0.0% 0.0% -0.0% -0.0% -0.0% symalg -0.0% 0.0% -0.0% -0.0% -0.0% tak -0.0% 0.0% -0.0% -0.0% -0.0% transform -0.0% 0.0% -0.0% -0.0% -0.0% treejoin -0.0% 0.0% -0.0% -0.0% -0.0% typecheck -0.0% 0.0% -0.0% -0.0% -0.0% veritas -0.0% 0.0% -0.0% -0.0% -0.0% wang -0.0% 0.0% -0.0% -0.0% -0.0% wave4main -0.0% 0.0% -0.0% -0.0% -0.0% wheel-sieve1 -0.0% 0.0% -0.0% -0.0% -0.0% wheel-sieve2 -0.0% 0.0% -0.0% -0.0% -0.0% x2n1 -0.0% 0.0% -0.0% -0.0% -0.0% -------------------------------------------------------------------------------- Min -0.1% 0.0% -0.3% -0.5% -0.5% Max -0.0% 0.0% -0.0% -0.0% -0.0% Geometric Mean -0.0% -0.0% -0.0% -0.0% -0.0% -------------------------------------------------------------------------------- Program Size Allocs Instrs Reads Writes -------------------------------------------------------------------------------- circsim -0.1% 0.0% -0.0% -0.0% -0.0% constraints -0.0% 0.0% -0.0% -0.0% -0.0% fibheaps -0.0% 0.0% -0.0% -0.0% -0.0% gc_bench -0.0% 0.0% -0.0% -0.0% -0.0% hash -0.0% 0.0% -0.0% -0.0% -0.0% lcss -0.0% 0.0% -0.0% -0.0% -0.0% power -0.0% 0.0% -0.0% -0.0% -0.0% spellcheck -0.0% 0.0% -0.0% -0.0% -0.0% -------------------------------------------------------------------------------- Min -0.1% 0.0% -0.0% -0.0% -0.0% Max -0.0% 0.0% -0.0% -0.0% -0.0% Geometric Mean -0.0% +0.0% -0.0% -0.0% -0.0% Manual inspection of programs in testsuite/tests/programs --------------------------------------------------------- I built these programs with a bunch of dump flags and `-O` and compared STG, Cmm, and Asm dumps and file sizes. (Below the numbers in parenthesis show number of modules in the program) These programs have identical compiler (same .hi and .o sizes, STG, and Cmm and Asm dumps): - Queens (1), andre_monad (1), cholewo-eval (2), cvh_unboxing (3), andy_cherry (7), fun_insts (1), hs-boot (4), fast2haskell (2), jl_defaults (1), jq_readsPrec (1), jules_xref (1), jtod_circint (4), jules_xref2 (1), lennart_range (1), lex (1), life_space_leak (1), bargon-mangler-bug (7), record_upd (1), rittri (1), sanders_array (1), strict_anns (1), thurston-module-arith (2), okeefe_neural (1), joao-circular (6), 10queens (1) Programs with different compiler outputs: - jl_defaults (1): For some reason GHC HEAD marks a lot of top-level `[Int]` closures as CAFFY for no reason. With this patch we no longer make them CAFFY and generate less SRT entries. For some reason Main.o is slightly larger with this patch (1.3%) and the executable sizes are the same. (I'd expect both to be smaller) - launchbury (1): Same as jl_defaults: top-level `[Int]` closures marked as CAFFY for no reason. Similarly `Main.o` is 1.4% larger but the executable sizes are the same. - galois_raytrace (13): Differences are in the Parse module. There are a lot, but some of the changes are caused by the fact that for some reason (I think a bug) GHC HEAD marks the dictionary for `Functor Identity` as CAFFY. Parse.o is 0.4% larger, the executable size is the same. - north_array: We now generate less SRT entries because some of array primops used in this program like `NewArrayOp` get eliminated during Stg-to-Cmm and turn some CAFFY things into non-CAFFY. Main.o gets 24% larger (9224 bytes from 9000 bytes), executable sizes are the same. - seward-space-leak: Difference in this program is better shown by this smaller example: module Lib where data CDS = Case [CDS] [(Int, CDS)] | Call CDS CDS instance Eq CDS where Case sels1 rets1 == Case sels2 rets2 = sels1 == sels2 && rets1 == rets2 Call a1 b1 == Call a2 b2 = a1 == a2 && b1 == b2 _ == _ = False In this program GHC HEAD builds a new SRT for the recursive group of `(==)`, `(/=)` and the dictionary closure. Then `/=` points to `==` in its SRT field, and `==` uses the SRT object as its SRT. With this patch we use the closure for `/=` as the SRT and add `==` there. Then `/=` gets an empty SRT field and `==` points to `/=` in its SRT field. This change looks fine to me. Main.o gets 0.07% larger, executable sizes are identical. head.hackage ------------ head.hackage's CI script builds 428 packages from Hackage using this patch with no failures. Compiler performance -------------------- The compiler perf tests report that the compiler allocates slightly more (worst case observed so far is 4%). However most programs in the test suite are small, single file programs. To benchmark compiler performance on something more realistic I build Cabal (the library, 236 modules) with different optimisation levels. For the "max residency" row I run GHC with `+RTS -s -A100k -i0 -h` for more accurate numbers. Other rows are generated with just `-s`. (This is because `-i0` causes running GC much more frequently and as a result "bytes copied" gets inflated by more than 25x in some cases) * -O0 | | GHC HEAD | This MR | Diff | | --------------- | -------------- | -------------- | ------ | | Bytes allocated | 54,413,350,872 | 54,701,099,464 | +0.52% | | Bytes copied | 4,926,037,184 | 4,990,638,760 | +1.31% | | Max residency | 421,225,624 | 424,324,264 | +0.73% | * -O1 | | GHC HEAD | This MR | Diff | | --------------- | --------------- | --------------- | ------ | | Bytes allocated | 245,849,209,992 | 246,562,088,672 | +0.28% | | Bytes copied | 26,943,452,560 | 27,089,972,296 | +0.54% | | Max residency | 982,643,440 | 991,663,432 | +0.91% | * -O2 | | GHC HEAD | This MR | Diff | | --------------- | --------------- | --------------- | ------ | | Bytes allocated | 291,044,511,408 | 291,863,910,912 | +0.28% | | Bytes copied | 37,044,237,616 | 36,121,690,472 | -2.49% | | Max residency | 1,071,600,328 | 1,086,396,256 | +1.38% | Extra compiler allocations -------------------------- Runtime allocations of programs are as reported above (NoFib section). The compiler now allocates more than before. Main source of allocation in this patch compared to base commit is the new SRT algorithm (GHC.Cmm.Info.Build). Below is some of the extra work we do with this patch, numbers generated by profiled stage 2 compiler when building a pathological case (the test 'ManyConstructors') with '-O2': - We now sort the final STG for a module, which means traversing the entire program, generating free variable set for each top-level binding, doing SCC analysis, and re-ordering the program. In ManyConstructors this step allocates 97,889,952 bytes. - We now do SRT analysis on static data, which in a program like ManyConstructors causes analysing 10,000 bindings that we would previously just skip. This step allocates 70,898,352 bytes. - We now maintain an SRT map for the entire module as we compile Cmm groups: data ModuleSRTInfo = ModuleSRTInfo { ... , moduleSRTMap :: SRTMap } (SRTMap is just a strict Map from the 'containers' library) This map gets an entry for most bindings in a module (exceptions are THUNKs and CAFFY static functions). For ManyConstructors this map gets 50015 entries. - Once we're done with code generation we generate a NameSet from SRTMap for the non-CAFFY names in the current module. This set gets the same number of entries as the SRTMap. - Finally we update CafInfos in ModDetails for the non-CAFFY Ids, using the NameSet generated in the previous step. This usually does the least amount of allocation among the work listed here. Only place with this patch where we do less work in the CAF analysis in the tidying pass (CoreTidy). However that doesn't save us much, as the pass still needs to traverse the whole program and update IdInfos for other reasons. Only thing we don't here do is the `hasCafRefs` pass over the RHS of bindings, which is a stateless pass that returns a boolean value, so it doesn't allocate much. (Metric changes blow are all increased allocations) Metric changes -------------- Metric Increase: ManyAlternatives ManyConstructors T13035 T14683 T1969 T9961
Diffstat (limited to 'compiler/GHC/Iface/Tidy.hs')
-rw-r--r--compiler/GHC/Iface/Tidy.hs200
1 files changed, 15 insertions, 185 deletions
diff --git a/compiler/GHC/Iface/Tidy.hs b/compiler/GHC/Iface/Tidy.hs
index 6f3a104925..8da7700e0e 100644
--- a/compiler/GHC/Iface/Tidy.hs
+++ b/compiler/GHC/Iface/Tidy.hs
@@ -23,12 +23,9 @@ import CoreUnfold
import CoreFVs
import CoreTidy
import CoreMonad
-import GHC.CoreToStg.Prep
-import CoreUtils (rhsIsStatic)
import CoreStats (coreBindsStats, CoreStats(..))
import CoreSeq (seqBinds)
import CoreLint
-import Literal
import Rules
import PatSyn
import ConLike
@@ -55,7 +52,6 @@ import DataCon
import TyCon
import Class
import Module
-import Packages( isDllName )
import HscTypes
import Maybes
import UniqSupply
@@ -119,7 +115,7 @@ Plan A: mkBootModDetails: omit pragmas, make interfaces small
* Drop rules altogether
-* Tidy the bindings, to ensure that the Caf and Arity
+* Tidy the bindings, to ensure that the Arity
information is correct for each top-level binder; the
code generator needs it. And to ensure that local names have
distinct OccNames in case of object-file splitting
@@ -217,7 +213,7 @@ globaliseAndTidyBootId :: Id -> Id
-- makes it into a GlobalId
-- * unchanged Name (might be Internal or External)
-- * unchanged details
--- * VanillaIdInfo (makes a conservative assumption about Caf-hood and arity)
+-- * VanillaIdInfo (makes a conservative assumption about arity)
-- * BootUnfolding (see Note [Inlining and hs-boot files] in GHC.CoreToIface)
globaliseAndTidyBootId id
= globaliseId id `setIdType` tidyTopType (idType id)
@@ -316,8 +312,6 @@ binder
* its arity, computed from the number of visible lambdas
- * its CAF info, computed from what is free in its RHS
-
Finally, substitute these new top-level binders consistently
throughout, including in unfoldings. We also tidy binders in
@@ -359,7 +353,7 @@ tidyProgram hsc_env (ModGuts { mg_module = mod
= findExternalRules omit_prags binds imp_rules unfold_env }
; (tidy_env, tidy_binds)
- <- tidyTopBinds hsc_env mod unfold_env tidy_occ_env trimmed_binds
+ <- tidyTopBinds hsc_env unfold_env tidy_occ_env trimmed_binds
-- See Note [Grand plan for static forms] in StaticPtrTable.
; (spt_entries, tidy_binds') <-
@@ -1070,22 +1064,13 @@ tidyTopName mod nc_var maybe_ref occ_env id
-- * subst_env: A Var->Var mapping that substitutes the new Var for the old
tidyTopBinds :: HscEnv
- -> Module
-> UnfoldEnv
-> TidyOccEnv
-> CoreProgram
-> IO (TidyEnv, CoreProgram)
-tidyTopBinds hsc_env this_mod unfold_env init_occ_env binds
- = do mkIntegerId <- lookupMkIntegerName dflags hsc_env
- mkNaturalId <- lookupMkNaturalName dflags hsc_env
- integerSDataCon <- lookupIntegerSDataConName dflags hsc_env
- naturalSDataCon <- lookupNaturalSDataConName dflags hsc_env
- let cvt_literal nt i = case nt of
- LitNumInteger -> Just (cvtLitInteger dflags mkIntegerId integerSDataCon i)
- LitNumNatural -> Just (cvtLitNatural dflags mkNaturalId naturalSDataCon i)
- _ -> Nothing
- result = tidy cvt_literal init_env binds
+tidyTopBinds hsc_env unfold_env init_occ_env binds
+ = do let result = tidy init_env binds
seqBinds (snd result) `seq` return result
-- This seqBinds avoids a spike in space usage (see #13564)
where
@@ -1093,35 +1078,28 @@ tidyTopBinds hsc_env this_mod unfold_env init_occ_env binds
init_env = (init_occ_env, emptyVarEnv)
- tidy cvt_literal = mapAccumL (tidyTopBind dflags this_mod cvt_literal unfold_env)
+ tidy = mapAccumL (tidyTopBind dflags unfold_env)
------------------------
tidyTopBind :: DynFlags
- -> Module
- -> (LitNumType -> Integer -> Maybe CoreExpr)
-> UnfoldEnv
-> TidyEnv
-> CoreBind
-> (TidyEnv, CoreBind)
-tidyTopBind dflags this_mod cvt_literal unfold_env
+tidyTopBind dflags unfold_env
(occ_env,subst1) (NonRec bndr rhs)
= (tidy_env2, NonRec bndr' rhs')
where
Just (name',show_unfold) = lookupVarEnv unfold_env bndr
- caf_info = hasCafRefs dflags this_mod
- (subst1, cvt_literal)
- (idArity bndr) rhs
- (bndr', rhs') = tidyTopPair dflags show_unfold tidy_env2 caf_info name'
- (bndr, rhs)
+ (bndr', rhs') = tidyTopPair dflags show_unfold tidy_env2 name' (bndr, rhs)
subst2 = extendVarEnv subst1 bndr bndr'
tidy_env2 = (occ_env, subst2)
-tidyTopBind dflags this_mod cvt_literal unfold_env
- (occ_env, subst1) (Rec prs)
+tidyTopBind dflags unfold_env (occ_env, subst1) (Rec prs)
= (tidy_env2, Rec prs')
where
- prs' = [ tidyTopPair dflags show_unfold tidy_env2 caf_info name' (id,rhs)
+ prs' = [ tidyTopPair dflags show_unfold tidy_env2 name' (id,rhs)
| (id,rhs) <- prs,
let (name',show_unfold) =
expectJust "tidyTopBind" $ lookupVarEnv unfold_env id
@@ -1132,21 +1110,11 @@ tidyTopBind dflags this_mod cvt_literal unfold_env
bndrs = map fst prs
- -- the CafInfo for a recursive group says whether *any* rhs in
- -- the group may refer indirectly to a CAF (because then, they all do).
- caf_info
- | or [ mayHaveCafRefs (hasCafRefs dflags this_mod
- (subst1, cvt_literal)
- (idArity bndr) rhs)
- | (bndr,rhs) <- prs ] = MayHaveCafRefs
- | otherwise = NoCafRefs
-
-----------------------------------------------------------
tidyTopPair :: DynFlags
-> Bool -- show unfolding
-> TidyEnv -- The TidyEnv is used to tidy the IdInfo
-- It is knot-tied: don't look at it!
- -> CafInfo
-> Name -- New name
-> (Id, CoreExpr) -- Binder and RHS before tidying
-> (Id, CoreExpr)
@@ -1156,7 +1124,7 @@ tidyTopPair :: DynFlags
-- group, a variable late in the group might be mentioned
-- in the IdInfo of one early in the group
-tidyTopPair dflags show_unfold rhs_tidy_env caf_info name' (bndr, rhs)
+tidyTopPair dflags show_unfold rhs_tidy_env name' (bndr, rhs)
= (bndr1, rhs1)
where
bndr1 = mkGlobalId details name' ty' idinfo'
@@ -1164,28 +1132,22 @@ tidyTopPair dflags show_unfold rhs_tidy_env caf_info name' (bndr, rhs)
ty' = tidyTopType (idType bndr)
rhs1 = tidyExpr rhs_tidy_env rhs
idinfo' = tidyTopIdInfo dflags rhs_tidy_env name' rhs rhs1 (idInfo bndr)
- show_unfold caf_info
+ show_unfold
-- tidyTopIdInfo creates the final IdInfo for top-level
--- binders. There are two delicate pieces:
+-- binders. The delicate piece:
--
-- * Arity. After CoreTidy, this arity must not change any more.
-- Indeed, CorePrep must eta expand where necessary to make
-- the manifest arity equal to the claimed arity.
--
--- * CAF info. This must also remain valid through to code generation.
--- We add the info here so that it propagates to all
--- occurrences of the binders in RHSs, and hence to occurrences in
--- unfoldings, which are inside Ids imported by GHCi. Ditto RULES.
--- CoreToStg makes use of this when constructing SRTs.
tidyTopIdInfo :: DynFlags -> TidyEnv -> Name -> CoreExpr -> CoreExpr
- -> IdInfo -> Bool -> CafInfo -> IdInfo
-tidyTopIdInfo dflags rhs_tidy_env name orig_rhs tidy_rhs idinfo show_unfold caf_info
+ -> IdInfo -> Bool -> IdInfo
+tidyTopIdInfo dflags rhs_tidy_env name orig_rhs tidy_rhs idinfo show_unfold
| not is_external -- For internal Ids (not externally visible)
= vanillaIdInfo -- we only need enough info for code generation
-- Arity and strictness info are enough;
-- c.f. CoreTidy.tidyLetBndr
- `setCafInfo` caf_info
`setArityInfo` arity
`setStrictnessInfo` final_sig
`setUnfoldingInfo` minimal_unfold_info -- See note [Preserve evaluatedness]
@@ -1193,7 +1155,6 @@ tidyTopIdInfo dflags rhs_tidy_env name orig_rhs tidy_rhs idinfo show_unfold caf_
| otherwise -- Externally-visible Ids get the whole lot
= vanillaIdInfo
- `setCafInfo` caf_info
`setArityInfo` arity
`setStrictnessInfo` final_sig
`setOccInfo` robust_occ_info
@@ -1257,137 +1218,6 @@ tidyTopIdInfo dflags rhs_tidy_env name orig_rhs tidy_rhs idinfo show_unfold caf_
{-
************************************************************************
* *
- Figuring out CafInfo for an expression
-* *
-************************************************************************
-
-hasCafRefs decides whether a top-level closure can point into the dynamic heap.
-We mark such things as `MayHaveCafRefs' because this information is
-used to decide whether a particular closure needs to be referenced
-in an SRT or not.
-
-There are two reasons for setting MayHaveCafRefs:
- a) The RHS is a CAF: a top-level updatable thunk.
- b) The RHS refers to something that MayHaveCafRefs
-
-Possible improvement: In an effort to keep the number of CAFs (and
-hence the size of the SRTs) down, we could also look at the expression and
-decide whether it requires a small bounded amount of heap, so we can ignore
-it as a CAF. In these cases however, we would need to use an additional
-CAF list to keep track of non-collectable CAFs.
-
-Note [Disgusting computation of CafRefs]
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-We compute hasCafRefs here, because IdInfo is supposed to be finalised
-after tidying. But CorePrep does some transformations that affect CAF-hood.
-So we have to *predict* the result here, which is revolting.
-
-In particular CorePrep expands Integer and Natural literals. So in the
-prediction code here we resort to applying the same expansion (cvt_literal).
-There are also numerous other ways in which we can introduce inconsistencies
-between CorePrep and GHC.Iface.Tidy. See Note [CAFfyness inconsistencies due to
-eta expansion in TidyPgm] for one such example.
-
-Ugh! What ugliness we hath wrought.
-
-
-Note [CAFfyness inconsistencies due to eta expansion in TidyPgm]
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-Eta expansion during CorePrep can have non-obvious negative consequences on
-the CAFfyness computation done by tidying (see Note [Disgusting computation of
-CafRefs] in GHC.Iface.Tidy). This late expansion happens/happened for a few
-reasons:
-
- * CorePrep previously eta expanded unsaturated primop applications, as
- described in Note [Primop wrappers]).
-
- * CorePrep still does eta expand unsaturated data constructor applications.
-
-In particular, consider the program:
-
- data Ty = Ty (RealWorld# -> (# RealWorld#, Int #))
-
- -- Is this CAFfy?
- x :: STM Int
- x = Ty (retry# @Int)
-
-Consider whether x is CAFfy. One might be tempted to answer "no".
-Afterall, f obviously has no CAF references and the application (retry#
-@Int) is essentially just a variable reference at runtime.
-
-However, when CorePrep expanded the unsaturated application of 'retry#'
-it would rewrite this to
-
- x = \u []
- let sat = retry# @Int
- in Ty sat
-
-This is now a CAF. Failing to handle this properly was the cause of
-#16846. We fixed this by eliminating the need to eta expand primops, as
-described in Note [Primop wrappers]), However we have not yet done the same for
-data constructor applications.
-
--}
-
-type CafRefEnv = (VarEnv Id, LitNumType -> Integer -> Maybe CoreExpr)
- -- The env finds the Caf-ness of the Id
- -- The LitNumType -> Integer -> CoreExpr is the desugaring functions for
- -- Integer and Natural literals
- -- See Note [Disgusting computation of CafRefs]
-
-hasCafRefs :: DynFlags -> Module
- -> CafRefEnv -> Arity -> CoreExpr
- -> CafInfo
-hasCafRefs dflags this_mod (subst, cvt_literal) arity expr
- | is_caf || mentions_cafs = MayHaveCafRefs
- | otherwise = NoCafRefs
- where
- mentions_cafs = cafRefsE expr
- is_dynamic_name = isDllName dflags this_mod
- is_caf = not (arity > 0 || rhsIsStatic (targetPlatform dflags) is_dynamic_name
- cvt_literal expr)
-
- -- NB. we pass in the arity of the expression, which is expected
- -- to be calculated by exprArity. This is because exprArity
- -- knows how much eta expansion is going to be done by
- -- CorePrep later on, and we don't want to duplicate that
- -- knowledge in rhsIsStatic below.
-
- cafRefsE :: Expr a -> Bool
- cafRefsE (Var id) = cafRefsV id
- cafRefsE (Lit lit) = cafRefsL lit
- cafRefsE (App f a) = cafRefsE f || cafRefsE a
- cafRefsE (Lam _ e) = cafRefsE e
- cafRefsE (Let b e) = cafRefsEs (rhssOfBind b) || cafRefsE e
- cafRefsE (Case e _ _ alts) = cafRefsE e || cafRefsEs (rhssOfAlts alts)
- cafRefsE (Tick _n e) = cafRefsE e
- cafRefsE (Cast e _co) = cafRefsE e
- cafRefsE (Type _) = False
- cafRefsE (Coercion _) = False
-
- cafRefsEs :: [Expr a] -> Bool
- cafRefsEs [] = False
- cafRefsEs (e:es) = cafRefsE e || cafRefsEs es
-
- cafRefsL :: Literal -> Bool
- -- Don't forget that mk_integer id might have Caf refs!
- -- We first need to convert the Integer into its final form, to
- -- see whether mkInteger is used. Same for LitNatural.
- cafRefsL (LitNumber nt i _) = case cvt_literal nt i of
- Just e -> cafRefsE e
- Nothing -> False
- cafRefsL _ = False
-
- cafRefsV :: Id -> Bool
- cafRefsV id
- | not (isLocalId id) = mayHaveCafRefs (idCafInfo id)
- | Just id' <- lookupVarEnv subst id = mayHaveCafRefs (idCafInfo id')
- | otherwise = False
-
-
-{-
-************************************************************************
-* *
Old, dead, type-trimming code
* *
************************************************************************
View Lorry Controller Status