llvm-project/polly/lib/Transform/DeadCodeElimination.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

201 lines
6.7 KiB
C++
Raw Normal View History

//===- DeadCodeElimination.cpp - Eliminate dead iteration ----------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// The polyhedral dead code elimination pass analyses a SCoP to eliminate
// statement instances that can be proven dead.
// As a consequence, the code generated for this SCoP may execute a statement
// less often. This means, a statement may be executed only in certain loop
// iterations or it may not even be part of the generated code at all.
//
// This code:
//
// for (i = 0; i < N; i++)
// arr[i] = 0;
// for (i = 0; i < N; i++)
// arr[i] = 10;
// for (i = 0; i < N; i++)
// arr[i] = i;
//
// is e.g. simplified to:
//
// for (i = 0; i < N; i++)
// arr[i] = i;
//
// The idea and the algorithm used was first implemented by Sven Verdoolaege in
// the 'ppcg' tool.
//
//===----------------------------------------------------------------------===//
#include "polly/DeadCodeElimination.h"
#include "polly/DependenceInfo.h"
#include "polly/LinkAllPasses.h"
#include "polly/Options.h"
#include "polly/ScopInfo.h"
#include "llvm/Support/CommandLine.h"
#include "isl/isl-noexceptions.h"
using namespace llvm;
using namespace polly;
namespace {
cl::opt<int> DCEPreciseSteps(
"polly-dce-precise-steps",
cl::desc("The number of precise steps between two approximating "
"iterations. (A value of -1 schedules another approximation stage "
"before the actual dead code elimination."),
cl::ZeroOrMore, cl::init(-1), cl::cat(PollyCategory));
class DeadCodeElimWrapperPass : public ScopPass {
public:
static char ID;
explicit DeadCodeElimWrapperPass() : ScopPass(ID) {}
/// Remove dead iterations from the schedule of @p S.
bool runOnScop(Scop &S) override;
/// Register all analyses and transformation required.
void getAnalysisUsage(AnalysisUsage &AU) const override;
};
char DeadCodeElimWrapperPass::ID = 0;
/// Return the set of live iterations.
///
/// The set of live iterations are all iterations that write to memory and for
/// which we can not prove that there will be a later write that _must_
/// overwrite the same memory location and is consequently the only one that
/// is visible after the execution of the SCoP.
///
/// To compute the live outs, we compute for the data-locations that are
/// must-written to the last statement that touches these locations. On top of
/// this we add all statements that perform may-write accesses.
///
/// We could be more precise by removing may-write accesses for which we know
/// that they are overwritten by a must-write after. However, at the moment the
/// only may-writes we introduce access the full (unbounded) array, such that
/// bounded write accesses can not overwrite all of the data-locations. As
/// this means may-writes are in the current situation always live, there is
/// no point in trying to remove them from the live-out set.
static isl::union_set getLiveOut(Scop &S) {
isl::union_map Schedule = S.getSchedule();
isl::union_map MustWrites = S.getMustWrites();
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
isl::union_map WriteIterations = MustWrites.reverse();
isl::union_map WriteTimes = WriteIterations.apply_range(Schedule);
isl::union_map LastWriteTimes = WriteTimes.lexmax();
isl::union_map LastWriteIterations =
LastWriteTimes.apply_range(Schedule.reverse());
isl::union_set Live = LastWriteIterations.range();
isl::union_map MayWrites = S.getMayWrites();
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
Live = Live.unite(MayWrites.domain());
return Live.coalesce();
}
/// Performs polyhedral dead iteration elimination by:
/// o Assuming that the last write to each location is live.
/// o Following each RAW dependency from a live iteration backwards and adding
/// that iteration to the live set.
///
/// To ensure the set of live iterations does not get too complex we always
/// combine a certain number of precise steps with one approximating step that
/// simplifies the life set with an affine hull.
static bool runDeadCodeElimination(Scop &S, int PreciseSteps,
const Dependences &D) {
if (!D.hasValidDependences())
return false;
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
isl::union_set Live = getLiveOut(S);
isl::union_map Dep =
D.getDependences(Dependences::TYPE_RAW | Dependences::TYPE_RED);
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
Dep = Dep.reverse();
if (PreciseSteps == -1)
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
Live = Live.affine_hull();
isl::union_set OriginalDomain = S.getDomains();
int Steps = 0;
2014-02-22 05:06:08 +08:00
while (true) {
Steps++;
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
isl::union_set Extra = Live.apply(Dep);
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
if (Extra.is_subset(Live))
break;
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
Live = Live.unite(Extra);
if (Steps > PreciseSteps) {
Steps = 0;
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
Live = Live.affine_hull();
}
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
Live = Live.intersect(OriginalDomain);
}
[DeadCodeElimination] Translate to C++ bindings This pass is a small and self-contained example of a piece of code that was written with the isl C interface. The diff of this change nicely shows how the C++ bindings can improve the readability of the code by avoiding the long C function names and by avoiding any need for memory management. As you will see, no calls to isl_*_copy or isl_*_free are needed anymore. Instead the C++ interface takes care of automatically managing the objects. This may introduce internally additional copies, but due to the isl reference counting, such copies are expected to be cheap. For performance critical operations, we will later exploit move semantics to eliminate unnecessary copies that have shown to be costly. Below we give a set of examples that shows the benefit of the C++ interface vs. the pure C interface. Check properties ---------------- Before: if (isl_aff_is_zero(aff) || isl_aff_is_one(aff)) return true; After: if (Aff.is_zero() || Aff.is_one()) return true; Type conversion --------------- Before: isl_union_pw_multi_aff *UPMA = isl_union_pw_multi_aff_from_union_map(umap); After: isl::union_pw_multi_aff UPMA = UMap; Type construction ----------------- Before: auto *Empty = isl_union_map_empty(space); After: auto Empty = isl::union_map::empty(Space); Operations ---------- Before: set = isl_union_set_intersect(set, set2); After: Set = Set.intersect(Set2); The use of isl::boolean in return types also adds an increases the robustness of Polly, as on conversion to true or false, we verify that no isl_bool_error has been returned and assert in case an error was returned. Before this change we would have just ignored the error and proceeded with (some) exection path. Tags: #polly Reviewed By: Meinersbur Differential Revision: https://reviews.llvm.org/D30619 llvm-svn: 297466
2017-03-10 23:05:38 +08:00
Live = Live.coalesce();
return S.restrictDomains(Live);
}
bool DeadCodeElimWrapperPass::runOnScop(Scop &S) {
auto &DI = getAnalysis<DependenceInfo>();
const Dependences &Deps = DI.getDependences(Dependences::AL_Statement);
bool Changed = runDeadCodeElimination(S, DCEPreciseSteps, Deps);
// FIXME: We can probably avoid the recomputation of all dependences by
// updating them explicitly.
if (Changed)
DI.recomputeDependences(Dependences::AL_Statement);
return false;
}
void DeadCodeElimWrapperPass::getAnalysisUsage(AnalysisUsage &AU) const {
ScopPass::getAnalysisUsage(AU);
AU.addRequired<DependenceInfo>();
}
} // namespace
Pass *polly::createDeadCodeElimWrapperPass() {
return new DeadCodeElimWrapperPass();
}
llvm::PreservedAnalyses DeadCodeElimPass::run(Scop &S, ScopAnalysisManager &SAM,
ScopStandardAnalysisResults &SAR,
SPMUpdater &U) {
DependenceAnalysis::Result &DA = SAM.getResult<DependenceAnalysis>(S, SAR);
const Dependences &Deps = DA.getDependences(Dependences::AL_Statement);
bool Changed = runDeadCodeElimination(S, DCEPreciseSteps, Deps);
// FIXME: We can probably avoid the recomputation of all dependences by
// updating them explicitly.
if (Changed)
DA.recomputeDependences(Dependences::AL_Statement);
if (!Changed)
return PreservedAnalyses::all();
PreservedAnalyses PA;
PA.preserveSet<AllAnalysesOn<Module>>();
PA.preserveSet<AllAnalysesOn<Function>>();
PA.preserveSet<AllAnalysesOn<Loop>>();
return PA;
}
INITIALIZE_PASS_BEGIN(DeadCodeElimWrapperPass, "polly-dce",
"Polly - Remove dead iterations", false, false)
INITIALIZE_PASS_DEPENDENCY(DependenceInfo)
INITIALIZE_PASS_DEPENDENCY(ScopInfoRegionPass)
INITIALIZE_PASS_END(DeadCodeElimWrapperPass, "polly-dce",
"Polly - Remove dead iterations", false, false)