maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[ScopInfo] Remove bail out condition in buildMinMaxAccess(). 

The condition was introduced in r267142 to mitigate a long compile-time
case. In r306087, a max-computation limit was introduced that should
handle the same case while leaving the max disjuncts heuristic it
should have replaced intact.

Today, the max disjuncts bail-out causes problems in that it prematurely
stops SCoPs from being detected, e.g. in SPEC's lbm. This would hit less
like if isl_set_coalesce would be called after isl_set_remove_divs
(which makes more basic_set likely to be coalescable) instead of before.

This patch tries to remove the premature max-disjuncts bail-out
condition by using simple_hull() to reduce the computational overhead,
instead of directly invalidating that SCoP.

Differential Revision: https://reviews.llvm.org/D45066

Contributed-by: Sahil Girish Yerawar <cs15btech11044@iith.ac.in>
llvm-svn: 331891
This commit is contained in:
Michael Kruse 2018-05-09 16:23:56 +00:00
parent cb7912cc0f
commit e330071b43
2 changed files with 119 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
polly/lib/Analysis/ScopInfo.cpp
View File

@ -24,6 +24,7 @@
#include "polly/ScopDetection.h"
#include "polly/Support/GICHelper.h"
#include "polly/Support/ISLOStream.h"
#include "polly/Support/ISLTools.h"
#include "polly/Support/SCEVAffinator.h"
#include "polly/Support/SCEVValidator.h"
#include "polly/Support/ScopHelper.h"
@ -2307,12 +2308,12 @@ buildMinMaxAccess(isl::set Set, Scop::MinMaxVectorTy &MinMaxAccesses, Scop &S) {
isl::pw_aff LastDimAff;
isl::aff OneAff;
unsigned Pos;
isl::ctx Ctx = Set.get_ctx();
Set = Set.remove_divs();
polly::simplify(Set);
if (isl_set_n_basic_set(Set.get()) >= MaxDisjunctsInDomain)
return isl::stat::error;
if (isl_set_n_basic_set(Set.get()) > RunTimeChecksMaxAccessDisjuncts)
Set = Set.simple_hull();
// Restrict the number of parameters involved in the access as the lexmin/
// lexmax computation will take too long if this number is high.
@ -2338,15 +2339,9 @@ buildMinMaxAccess(isl::set Set, Scop::MinMaxVectorTy &MinMaxAccesses, Scop &S) {
return isl::stat::error;
}
if (isl_set_n_basic_set(Set.get()) > RunTimeChecksMaxAccessDisjuncts)
return isl::stat::error;
MinPMA = Set.lexmin_pw_multi_aff();
MaxPMA = Set.lexmax_pw_multi_aff();
if (isl_ctx_last_error(Ctx.get()) == isl_error_quota)
return isl::stat::error;
MinPMA = MinPMA.coalesce();
MaxPMA = MaxPMA.coalesce();
@ -2354,7 +2349,9 @@ buildMinMaxAccess(isl::set Set, Scop::MinMaxVectorTy &MinMaxAccesses, Scop &S) {
// enclose the accessed memory region by MinPMA and MaxPMA. The pointer
// we test during code generation might now point after the end of the
// allocated array but we will never dereference it anyway.
assert(MaxPMA.dim(isl::dim::out) && "Assumed at least one output dimension");
assert((!MaxPMA || MaxPMA.dim(isl::dim::out)) &&
"Assumed at least one output dimension");
Pos = MaxPMA.dim(isl::dim::out) - 1;
LastDimAff = MaxPMA.get_pw_aff(Pos);
OneAff = isl::aff(isl::local_space(LastDimAff.get_domain_space()));
@ -2362,6 +2359,9 @@ buildMinMaxAccess(isl::set Set, Scop::MinMaxVectorTy &MinMaxAccesses, Scop &S) {
LastDimAff = LastDimAff.add(OneAff);
MaxPMA = MaxPMA.set_pw_aff(Pos, LastDimAff);
if (!MinPMA || !MaxPMA)
return isl::stat::error;
MinMaxAccesses.push_back(std::make_pair(MinPMA, MaxPMA));
return isl::stat::ok;
@ -2386,8 +2386,6 @@ static bool calculateMinMaxAccess(Scop::AliasGroupTy AliasGroup, Scop &S,
Accesses = Accesses.intersect_domain(Domains);
isl::union_set Locations = Accesses.range();
Locations = Locations.coalesce();
Locations = Locations.detect_equalities();
auto Lambda = [&MinMaxAccesses, &S](isl::set Set) -> isl::stat {
return buildMinMaxAccess(Set, MinMaxAccesses, S);

109
polly/test/ScopInfo/run-time-check-many-piecewise-aliasing.ll Normal file
View File

@ -0,0 +1,109 @@
; RUN: opt %loadPolly -polly-detect -analyze < %s \
; RUN: | FileCheck %s -check-prefix=DETECT
; RUN: opt %loadPolly -polly-scops -analyze < %s | FileCheck %s
;
; DETECT: Valid Region for Scop: for => return
;
; Check that this SCoP is allowed, even though the number of disjunct memory accesses of A
; is 11, greater than RunTimeChecksMaxAccessDisjuncts.
;
; CHECK: Function: func
; CHECK-NEXT: Region: %for---%return
define void @func(i64 %n, double* nonnull %A, double * nonnull %B, i64 %d) {
entry:
br label %for
for:
%j = phi i64 [0, %entry], [%j.inc, %inc]
%j.cmp = icmp slt i64 %j, %n
br i1 %j.cmp, label %body, label %exit
body:
%add.i.i = add nsw i64 1, %j
%sub.i.i = sub nsw i64 %add.i.i, 1
%cmp.i.i.i = icmp sgt i64 %sub.i.i, 0
%cond.i.i.i = select i1 %cmp.i.i.i, i64 %sub.i.i, i64 0
%mul.i.i = mul nsw i64 %cond.i.i.i, 7
%sub1.i.i = sub nsw i64 1, %j
%add2.i.i = add nsw i64 %sub1.i.i, 1
%cmp.i8.i.i = icmp sgt i64 %add2.i.i, 0
%cond.i11.i.i = select i1 %cmp.i8.i.i, i64 %add2.i.i, i64 0
%mul4.i.i = mul nsw i64 %cond.i11.i.i, 7
%add5.i.i = add nsw i64 %mul.i.i, %mul4.i.i
%add.i113.i = add nsw i64 1, %j
%sub.i114.i = sub nsw i64 %add.i113.i, 3
%cmp.i.i115.i = icmp sgt i64 %sub.i114.i, 0
%cond.i.i118.i = select i1 %cmp.i.i115.i, i64 %sub.i114.i, i64 0
%mul.i119.i = mul nsw i64 %cond.i.i118.i, 9
%sub1.i120.i = sub nsw i64 1, %j
%add2.i121.i = add nsw i64 %sub1.i120.i, 3
%cmp.i8.i122.i = icmp sgt i64 %add2.i121.i, 0
%cond.i11.i126.i = select i1 %cmp.i8.i122.i, i64 %add2.i121.i, i64 0
%mul4.i127.i = mul nsw i64 %cond.i11.i126.i, 9
%add5.i128.i = add nsw i64 %mul.i119.i, %mul4.i127.i
%add.i = add nsw i64 %add5.i.i, %add5.i128.i
%add.i89.i = add nsw i64 1, %j
%sub.i90.i = sub nsw i64 %add.i89.i, 4
%cmp.i.i91.i = icmp sgt i64 %sub.i90.i, 0
%cond.i.i94.i = select i1 %cmp.i.i91.i, i64 %sub.i90.i, i64 0
%mul.i95.i = mul nsw i64 %cond.i.i94.i, 11
%sub1.i96.i = sub nsw i64 1, %j
%add2.i97.i = add nsw i64 %sub1.i96.i, 4
%cmp.i8.i98.i = icmp sgt i64 %add2.i97.i, 0
%cond.i11.i102.i = select i1 %cmp.i8.i98.i, i64 %add2.i97.i, i64 0
%mul4.i103.i = mul nsw i64 %cond.i11.i102.i, 11
%add5.i104.i = add nsw i64 %mul.i95.i, %mul4.i103.i
%add3.i = add nsw i64 %add.i, %add5.i104.i
%add.i65.i = add nsw i64 1, %j
%sub.i66.i = sub nsw i64 %add.i65.i, 6
%cmp.i.i67.i = icmp sgt i64 %sub.i66.i, 0
%cond.i.i70.i = select i1 %cmp.i.i67.i, i64 %sub.i66.i, i64 0
%mul.i71.i = mul nsw i64 %cond.i.i70.i, 13
%sub1.i72.i = sub nsw i64 1, %j
%add2.i73.i = add nsw i64 %sub1.i72.i, 6
%cmp.i8.i74.i = icmp sgt i64 %add2.i73.i, 0
%cond.i11.i78.i = select i1 %cmp.i8.i74.i, i64 %add2.i73.i, i64 0
%mul4.i79.i = mul nsw i64 %cond.i11.i78.i, 13
%add5.i80.i = add nsw i64 %mul.i71.i, %mul4.i79.i
%add5.i = add nsw i64 %add3.i, %add5.i80.i
%add.i41.i = add nsw i64 1, %j
%sub.i42.i = sub nsw i64 %add.i41.i, 8
%cmp.i.i43.i = icmp sgt i64 %sub.i42.i, 0
%cond.i.i46.i = select i1 %cmp.i.i43.i, i64 %sub.i42.i, i64 0
%mul.i47.i = mul nsw i64 %cond.i.i46.i, 17
%sub1.i48.i = sub nsw i64 1, %j
%add2.i49.i = add nsw i64 %sub1.i48.i, 8
%cmp.i8.i50.i = icmp sgt i64 %add2.i49.i, 0
%cond.i11.i54.i = select i1 %cmp.i8.i50.i, i64 %add2.i49.i, i64 0
%mul4.i55.i = mul nsw i64 %cond.i11.i54.i, 17
%add5.i56.i = add nsw i64 %mul.i47.i, %mul4.i55.i
%add7.i = add nsw i64 %add5.i, %add5.i56.i
%add.i17.i = add nsw i64 1, %j
%sub.i18.i = sub nsw i64 %add.i17.i, 10
%cmp.i.i19.i = icmp sgt i64 %sub.i18.i, 0
%cond.i.i22.i = select i1 %cmp.i.i19.i, i64 %sub.i18.i, i64 0
%mul.i23.i = mul nsw i64 %cond.i.i22.i, 19
%sub1.i24.i = sub nsw i64 1, %j
%add2.i25.i = add nsw i64 %sub1.i24.i, 10
%cmp.i8.i26.i = icmp sgt i64 %add2.i25.i, 0
%cond.i11.i30.i = select i1 %cmp.i8.i26.i, i64 %add2.i25.i, i64 0
%mul4.i31.i = mul nsw i64 %cond.i11.i30.i, 19
%add5.i32.i = add nsw i64 %mul.i23.i, %mul4.i31.i
%idxprom = add nsw i64 %add7.i, %add5.i32.i
%A_idx = getelementptr inbounds double, double* %A, i64 %idxprom
%val = load double, double* %A_idx
%B_idx = getelementptr inbounds double, double* %B, i64 %j
store double %val, double* %B_idx
br label %inc
inc:
%j.inc = add nuw nsw i64 %j, 1
br label %for
exit:
br label %return
return:
ret void
}