2004-04-18 13:20:17 +08:00
|
|
|
//===-- LoopUnroll.cpp - Loop unroller pass -------------------------------===//
|
2005-04-22 07:48:37 +08:00
|
|
|
//
|
2004-04-18 13:20:17 +08:00
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
2007-12-30 04:36:04 +08:00
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
2005-04-22 07:48:37 +08:00
|
|
|
//
|
2004-04-18 13:20:17 +08:00
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This pass implements a simple loop unroller. It works best when loops have
|
|
|
|
// been canonicalized by the -indvars pass, allowing it to determine the trip
|
|
|
|
// counts of loops easily.
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
|
|
#include "llvm/Transforms/Scalar.h"
|
2015-02-13 11:57:40 +08:00
|
|
|
#include "llvm/ADT/SetVector.h"
|
2015-09-10 18:22:12 +08:00
|
|
|
#include "llvm/Analysis/GlobalsModRef.h"
|
2015-01-04 20:03:27 +08:00
|
|
|
#include "llvm/Analysis/AssumptionCache.h"
|
2011-01-02 15:35:53 +08:00
|
|
|
#include "llvm/Analysis/CodeMetrics.h"
|
2015-03-24 03:32:43 +08:00
|
|
|
#include "llvm/Analysis/InstructionSimplify.h"
|
2012-12-04 00:50:05 +08:00
|
|
|
#include "llvm/Analysis/LoopPass.h"
|
2016-02-09 07:03:59 +08:00
|
|
|
#include "llvm/Analysis/LoopUnrollAnalyzer.h"
|
2010-07-27 02:11:16 +08:00
|
|
|
#include "llvm/Analysis/ScalarEvolution.h"
|
2015-02-05 10:34:00 +08:00
|
|
|
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
|
2013-01-21 21:04:33 +08:00
|
|
|
#include "llvm/Analysis/TargetTransformInfo.h"
|
2013-01-02 19:36:10 +08:00
|
|
|
#include "llvm/IR/DataLayout.h"
|
2014-06-17 07:53:02 +08:00
|
|
|
#include "llvm/IR/DiagnosticInfo.h"
|
2014-01-13 17:26:24 +08:00
|
|
|
#include "llvm/IR/Dominators.h"
|
2015-03-24 03:32:43 +08:00
|
|
|
#include "llvm/IR/InstVisitor.h"
|
2013-01-02 19:36:10 +08:00
|
|
|
#include "llvm/IR/IntrinsicInst.h"
|
2014-06-17 07:53:02 +08:00
|
|
|
#include "llvm/IR/Metadata.h"
|
2004-09-02 06:55:40 +08:00
|
|
|
#include "llvm/Support/CommandLine.h"
|
|
|
|
#include "llvm/Support/Debug.h"
|
2009-07-25 08:23:56 +08:00
|
|
|
#include "llvm/Support/raw_ostream.h"
|
[LPM] Factor all of the loop analysis usage updates into a common helper
routine.
We were getting this wrong in small ways and generally being very
inconsistent about it across loop passes. Instead, let's have a common
place where we do this. One minor downside is that this will require
some analyses like SCEV in more places than they are strictly needed.
However, this seems benign as these analyses are complete no-ops, and
without this consistency we can in many cases end up with the legacy
pass manager scheduling deciding to split up a loop pass pipeline in
order to run the function analysis half-way through. It is very, very
annoying to fix these without just being very pedantic across the board.
The only loop passes I've not updated here are ones that use
AU.setPreservesAll() such as IVUsers (an analysis) and the pass printer.
They seemed less relevant.
With this patch, almost all of the problems in PR24804 around loop pass
pipelines are fixed. The one remaining issue is that we run simplify-cfg
and instcombine in the middle of the loop pass pipeline. We've recently
added some loop variants of these passes that would seem substantially
cleaner to use, but this at least gets us much closer to the previous
state. Notably, the seven loop pass managers is down to three.
I've not updated the loop passes using LoopAccessAnalysis because that
analysis hasn't been fully wired into LoopSimplify/LCSSA, and it isn't
clear that those transforms want to support those forms anyways. They
all run late anyways, so this is harmless. Similarly, LSR is left alone
because it already carefully manages its forms and doesn't need to get
fused into a single loop pass manager with a bunch of other loop passes.
LoopReroll didn't use loop simplified form previously, and I've updated
the test case to match the trivially different output.
Finally, I've also factored all the pass initialization for the passes
that use this technique as well, so that should be done regularly and
reliably.
Thanks to James for the help reviewing and thinking about this stuff,
and Ben for help thinking about it as well!
Differential Revision: http://reviews.llvm.org/D17435
llvm-svn: 261316
2016-02-19 18:45:18 +08:00
|
|
|
#include "llvm/Transforms/Utils/LoopUtils.h"
|
2008-05-14 08:24:14 +08:00
|
|
|
#include "llvm/Transforms/Utils/UnrollLoop.h"
|
2008-05-16 17:30:00 +08:00
|
|
|
#include <climits>
|
2004-04-18 13:20:17 +08:00
|
|
|
|
2008-05-14 08:24:14 +08:00
|
|
|
using namespace llvm;
|
2004-04-18 13:20:17 +08:00
|
|
|
|
2014-04-22 10:55:47 +08:00
|
|
|
#define DEBUG_TYPE "loop-unroll"
|
|
|
|
|
2008-05-13 08:00:25 +08:00
|
|
|
static cl::opt<unsigned>
|
2016-01-12 08:55:26 +08:00
|
|
|
UnrollThreshold("unroll-threshold", cl::Hidden,
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
cl::desc("The baseline cost threshold for loop unrolling"));
|
|
|
|
|
|
|
|
static cl::opt<unsigned> UnrollPercentDynamicCostSavedThreshold(
|
2016-01-12 08:55:26 +08:00
|
|
|
"unroll-percent-dynamic-cost-saved-threshold", cl::Hidden,
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
cl::desc("The percentage of estimated dynamic cost which must be saved by "
|
|
|
|
"unrolling to allow unrolling up to the max threshold."));
|
|
|
|
|
|
|
|
static cl::opt<unsigned> UnrollDynamicCostSavingsDiscount(
|
2016-01-12 08:55:26 +08:00
|
|
|
"unroll-dynamic-cost-savings-discount", cl::Hidden,
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
cl::desc("This is the amount discounted from the total unroll cost when "
|
|
|
|
"the unrolled form has a high dynamic cost savings (triggered by "
|
|
|
|
"the '-unroll-perecent-dynamic-cost-saved-threshold' flag)."));
|
2007-05-12 04:53:41 +08:00
|
|
|
|
2015-02-05 10:34:00 +08:00
|
|
|
static cl::opt<unsigned> UnrollMaxIterationsCountToAnalyze(
|
2015-02-13 13:31:46 +08:00
|
|
|
"unroll-max-iteration-count-to-analyze", cl::init(0), cl::Hidden,
|
2015-02-05 10:34:00 +08:00
|
|
|
cl::desc("Don't allow loop unrolling to simulate more than this number of"
|
|
|
|
"iterations when checking full unroll profitability"));
|
|
|
|
|
2008-05-13 08:00:25 +08:00
|
|
|
static cl::opt<unsigned>
|
2016-01-12 08:55:26 +08:00
|
|
|
UnrollCount("unroll-count", cl::Hidden,
|
2014-06-17 07:53:02 +08:00
|
|
|
cl::desc("Use this unroll count for all loops including those with "
|
|
|
|
"unroll_count pragma values, for testing purposes"));
|
2004-04-18 13:20:17 +08:00
|
|
|
|
2008-07-29 21:21:23 +08:00
|
|
|
static cl::opt<bool>
|
2016-01-12 08:55:26 +08:00
|
|
|
UnrollAllowPartial("unroll-allow-partial", cl::Hidden,
|
2008-07-29 21:21:23 +08:00
|
|
|
cl::desc("Allows loops to be partially unrolled until "
|
|
|
|
"-unroll-threshold loop size is reached."));
|
|
|
|
|
2011-12-09 14:19:40 +08:00
|
|
|
static cl::opt<bool>
|
2016-01-12 08:55:26 +08:00
|
|
|
UnrollRuntime("unroll-runtime", cl::ZeroOrMore, cl::Hidden,
|
2011-12-09 14:19:40 +08:00
|
|
|
cl::desc("Unroll loops with run-time trip counts"));
|
|
|
|
|
2014-06-17 07:53:02 +08:00
|
|
|
static cl::opt<unsigned>
|
|
|
|
PragmaUnrollThreshold("pragma-unroll-threshold", cl::init(16 * 1024), cl::Hidden,
|
2014-07-24 01:31:37 +08:00
|
|
|
cl::desc("Unrolled size limit for loops with an unroll(full) or "
|
2014-06-17 07:53:02 +08:00
|
|
|
"unroll_count pragma."));
|
|
|
|
|
2016-01-12 08:55:26 +08:00
|
|
|
|
|
|
|
/// A magic value for use with the Threshold parameter to indicate
|
|
|
|
/// that the loop unroll should be performed regardless of how much
|
|
|
|
/// code expansion would result.
|
|
|
|
static const unsigned NoThreshold = UINT_MAX;
|
|
|
|
|
|
|
|
/// Default unroll count for loops with run-time trip count if
|
|
|
|
/// -unroll-count is not set
|
|
|
|
static const unsigned DefaultUnrollRuntimeCount = 8;
|
|
|
|
|
|
|
|
/// Gather the various unrolling parameters based on the defaults, compiler
|
|
|
|
/// flags, TTI overrides, pragmas, and user specified parameters.
|
|
|
|
static TargetTransformInfo::UnrollingPreferences gatherUnrollingPreferences(
|
|
|
|
Loop *L, const TargetTransformInfo &TTI, Optional<unsigned> UserThreshold,
|
|
|
|
Optional<unsigned> UserCount, Optional<bool> UserAllowPartial,
|
|
|
|
Optional<bool> UserRuntime, unsigned PragmaCount, bool PragmaFullUnroll,
|
|
|
|
bool PragmaEnableUnroll, unsigned TripCount) {
|
|
|
|
TargetTransformInfo::UnrollingPreferences UP;
|
|
|
|
|
|
|
|
// Set up the defaults
|
|
|
|
UP.Threshold = 150;
|
|
|
|
UP.PercentDynamicCostSavedThreshold = 20;
|
|
|
|
UP.DynamicCostSavingsDiscount = 2000;
|
|
|
|
UP.OptSizeThreshold = 50;
|
|
|
|
UP.PartialThreshold = UP.Threshold;
|
|
|
|
UP.PartialOptSizeThreshold = UP.OptSizeThreshold;
|
|
|
|
UP.Count = 0;
|
|
|
|
UP.MaxCount = UINT_MAX;
|
|
|
|
UP.Partial = false;
|
|
|
|
UP.Runtime = false;
|
|
|
|
UP.AllowExpensiveTripCount = false;
|
|
|
|
|
|
|
|
// Override with any target specific settings
|
|
|
|
TTI.getUnrollingPreferences(L, UP);
|
|
|
|
|
|
|
|
// Apply size attributes
|
|
|
|
if (L->getHeader()->getParent()->optForSize()) {
|
|
|
|
UP.Threshold = UP.OptSizeThreshold;
|
|
|
|
UP.PartialThreshold = UP.PartialOptSizeThreshold;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Apply unroll count pragmas
|
|
|
|
if (PragmaCount)
|
|
|
|
UP.Count = PragmaCount;
|
|
|
|
else if (PragmaFullUnroll)
|
|
|
|
UP.Count = TripCount;
|
|
|
|
|
|
|
|
// Apply any user values specified by cl::opt
|
|
|
|
if (UnrollThreshold.getNumOccurrences() > 0) {
|
|
|
|
UP.Threshold = UnrollThreshold;
|
|
|
|
UP.PartialThreshold = UnrollThreshold;
|
|
|
|
}
|
|
|
|
if (UnrollPercentDynamicCostSavedThreshold.getNumOccurrences() > 0)
|
|
|
|
UP.PercentDynamicCostSavedThreshold =
|
|
|
|
UnrollPercentDynamicCostSavedThreshold;
|
|
|
|
if (UnrollDynamicCostSavingsDiscount.getNumOccurrences() > 0)
|
|
|
|
UP.DynamicCostSavingsDiscount = UnrollDynamicCostSavingsDiscount;
|
|
|
|
if (UnrollCount.getNumOccurrences() > 0)
|
|
|
|
UP.Count = UnrollCount;
|
|
|
|
if (UnrollAllowPartial.getNumOccurrences() > 0)
|
|
|
|
UP.Partial = UnrollAllowPartial;
|
|
|
|
if (UnrollRuntime.getNumOccurrences() > 0)
|
|
|
|
UP.Runtime = UnrollRuntime;
|
|
|
|
|
|
|
|
// Apply user values provided by argument
|
|
|
|
if (UserThreshold.hasValue()) {
|
|
|
|
UP.Threshold = *UserThreshold;
|
|
|
|
UP.PartialThreshold = *UserThreshold;
|
|
|
|
}
|
|
|
|
if (UserCount.hasValue())
|
|
|
|
UP.Count = *UserCount;
|
|
|
|
if (UserAllowPartial.hasValue())
|
|
|
|
UP.Partial = *UserAllowPartial;
|
|
|
|
if (UserRuntime.hasValue())
|
|
|
|
UP.Runtime = *UserRuntime;
|
|
|
|
|
|
|
|
if (PragmaCount > 0 ||
|
|
|
|
((PragmaFullUnroll || PragmaEnableUnroll) && TripCount != 0)) {
|
|
|
|
// If the loop has an unrolling pragma, we want to be more aggressive with
|
|
|
|
// unrolling limits. Set thresholds to at least the PragmaTheshold value
|
|
|
|
// which is larger than the default limits.
|
|
|
|
if (UP.Threshold != NoThreshold)
|
|
|
|
UP.Threshold = std::max<unsigned>(UP.Threshold, PragmaUnrollThreshold);
|
|
|
|
if (UP.PartialThreshold != NoThreshold)
|
|
|
|
UP.PartialThreshold =
|
|
|
|
std::max<unsigned>(UP.PartialThreshold, PragmaUnrollThreshold);
|
|
|
|
}
|
|
|
|
|
|
|
|
return UP;
|
|
|
|
}
|
|
|
|
|
2015-05-23 01:41:35 +08:00
|
|
|
namespace {
|
|
|
|
struct EstimatedUnrollCost {
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
/// \brief The estimated cost after unrolling.
|
2015-08-06 02:46:21 +08:00
|
|
|
int UnrolledCost;
|
2015-02-13 10:10:56 +08:00
|
|
|
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
/// \brief The estimated dynamic cost of executing the instructions in the
|
|
|
|
/// rolled form.
|
2015-08-06 02:46:21 +08:00
|
|
|
int RolledDynamicCost;
|
2015-05-23 01:41:35 +08:00
|
|
|
};
|
|
|
|
}
|
2015-05-13 01:20:03 +08:00
|
|
|
|
2015-05-23 01:41:35 +08:00
|
|
|
/// \brief Figure out if the loop is worth full unrolling.
|
|
|
|
///
|
|
|
|
/// Complete loop unrolling can make some loads constant, and we need to know
|
|
|
|
/// if that would expose any further optimization opportunities. This routine
|
2015-06-12 06:17:39 +08:00
|
|
|
/// estimates this optimization. It computes cost of unrolled loop
|
|
|
|
/// (UnrolledCost) and dynamic cost of the original loop (RolledDynamicCost). By
|
|
|
|
/// dynamic cost we mean that we won't count costs of blocks that are known not
|
|
|
|
/// to be executed (i.e. if we have a branch in the loop and we know that at the
|
|
|
|
/// given iteration its condition would be resolved to true, we won't add up the
|
|
|
|
/// cost of the 'false'-block).
|
|
|
|
/// \returns Optional value, holding the RolledDynamicCost and UnrolledCost. If
|
|
|
|
/// the analysis failed (no benefits expected from the unrolling, or the loop is
|
|
|
|
/// too big to analyze), the returned value is None.
|
2015-08-20 17:57:22 +08:00
|
|
|
static Optional<EstimatedUnrollCost>
|
2015-08-04 04:32:27 +08:00
|
|
|
analyzeLoopUnrollCost(const Loop *L, unsigned TripCount, DominatorTree &DT,
|
|
|
|
ScalarEvolution &SE, const TargetTransformInfo &TTI,
|
2015-08-06 02:46:21 +08:00
|
|
|
int MaxUnrolledLoopSize) {
|
2015-05-23 01:41:35 +08:00
|
|
|
// We want to be able to scale offsets by the trip count and add more offsets
|
|
|
|
// to them without checking for overflows, and we already don't want to
|
|
|
|
// analyze *massive* trip counts, so we force the max to be reasonably small.
|
|
|
|
assert(UnrollMaxIterationsCountToAnalyze < (INT_MAX / 2) &&
|
|
|
|
"The unroll iterations max is too large!");
|
|
|
|
|
|
|
|
// Don't simulate loops with a big or unknown tripcount
|
|
|
|
if (!UnrollMaxIterationsCountToAnalyze || !TripCount ||
|
|
|
|
TripCount > UnrollMaxIterationsCountToAnalyze)
|
|
|
|
return None;
|
|
|
|
|
|
|
|
SmallSetVector<BasicBlock *, 16> BBWorklist;
|
|
|
|
DenseMap<Value *, Constant *> SimplifiedValues;
|
2015-08-04 04:32:27 +08:00
|
|
|
SmallVector<std::pair<Value *, Constant *>, 4> SimplifiedInputValues;
|
2015-02-13 10:17:39 +08:00
|
|
|
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
// The estimated cost of the unrolled form of the loop. We try to estimate
|
|
|
|
// this by simplifying as much as we can while computing the estimate.
|
2015-08-06 02:46:21 +08:00
|
|
|
int UnrolledCost = 0;
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
// We also track the estimated dynamic (that is, actually executed) cost in
|
|
|
|
// the rolled form. This helps identify cases when the savings from unrolling
|
|
|
|
// aren't just exposing dead control flows, but actual reduced dynamic
|
|
|
|
// instructions due to the simplifications which we expect to occur after
|
|
|
|
// unrolling.
|
2015-08-06 02:46:21 +08:00
|
|
|
int RolledDynamicCost = 0;
|
2015-05-23 01:41:35 +08:00
|
|
|
|
2015-08-04 04:32:27 +08:00
|
|
|
// Ensure that we don't violate the loop structure invariants relied on by
|
|
|
|
// this analysis.
|
|
|
|
assert(L->isLoopSimplifyForm() && "Must put loop into normal form first.");
|
|
|
|
assert(L->isLCSSAForm(DT) &&
|
|
|
|
"Must have loops in LCSSA form to track live-out values.");
|
|
|
|
|
2015-07-29 04:07:29 +08:00
|
|
|
DEBUG(dbgs() << "Starting LoopUnroll profitability analysis...\n");
|
|
|
|
|
2015-05-23 01:41:35 +08:00
|
|
|
// Simulate execution of each iteration of the loop counting instructions,
|
|
|
|
// which would be simplified.
|
|
|
|
// Since the same load will take different values on different iterations,
|
|
|
|
// we literally have to go through all loop's iterations.
|
|
|
|
for (unsigned Iteration = 0; Iteration < TripCount; ++Iteration) {
|
2015-07-29 04:07:29 +08:00
|
|
|
DEBUG(dbgs() << " Analyzing iteration " << Iteration << "\n");
|
2015-08-04 04:32:27 +08:00
|
|
|
|
|
|
|
// Prepare for the iteration by collecting any simplified entry or backedge
|
|
|
|
// inputs.
|
|
|
|
for (Instruction &I : *L->getHeader()) {
|
|
|
|
auto *PHI = dyn_cast<PHINode>(&I);
|
|
|
|
if (!PHI)
|
|
|
|
break;
|
|
|
|
|
|
|
|
// The loop header PHI nodes must have exactly two input: one from the
|
|
|
|
// loop preheader and one from the loop latch.
|
|
|
|
assert(
|
|
|
|
PHI->getNumIncomingValues() == 2 &&
|
|
|
|
"Must have an incoming value only for the preheader and the latch.");
|
|
|
|
|
|
|
|
Value *V = PHI->getIncomingValueForBlock(
|
|
|
|
Iteration == 0 ? L->getLoopPreheader() : L->getLoopLatch());
|
|
|
|
Constant *C = dyn_cast<Constant>(V);
|
|
|
|
if (Iteration != 0 && !C)
|
|
|
|
C = SimplifiedValues.lookup(V);
|
|
|
|
if (C)
|
|
|
|
SimplifiedInputValues.push_back({PHI, C});
|
|
|
|
}
|
|
|
|
|
|
|
|
// Now clear and re-populate the map for the next iteration.
|
2015-05-23 01:41:35 +08:00
|
|
|
SimplifiedValues.clear();
|
2015-08-04 04:32:27 +08:00
|
|
|
while (!SimplifiedInputValues.empty())
|
|
|
|
SimplifiedValues.insert(SimplifiedInputValues.pop_back_val());
|
|
|
|
|
2016-02-26 10:57:05 +08:00
|
|
|
UnrolledInstAnalyzer Analyzer(Iteration, SimplifiedValues, SE, L);
|
2015-05-23 01:41:35 +08:00
|
|
|
|
|
|
|
BBWorklist.clear();
|
|
|
|
BBWorklist.insert(L->getHeader());
|
|
|
|
// Note that we *must not* cache the size, this loop grows the worklist.
|
|
|
|
for (unsigned Idx = 0; Idx != BBWorklist.size(); ++Idx) {
|
|
|
|
BasicBlock *BB = BBWorklist[Idx];
|
|
|
|
|
|
|
|
// Visit all instructions in the given basic block and try to simplify
|
|
|
|
// it. We don't change the actual IR, just count optimization
|
|
|
|
// opportunities.
|
|
|
|
for (Instruction &I : *BB) {
|
2015-08-06 02:46:21 +08:00
|
|
|
int InstCost = TTI.getUserCost(&I);
|
2015-05-23 01:41:35 +08:00
|
|
|
|
|
|
|
// Visit the instruction to analyze its loop cost after unrolling,
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
// and if the visitor returns false, include this instruction in the
|
|
|
|
// unrolled cost.
|
|
|
|
if (!Analyzer.visit(I))
|
|
|
|
UnrolledCost += InstCost;
|
2015-07-29 04:07:29 +08:00
|
|
|
else {
|
|
|
|
DEBUG(dbgs() << " " << I
|
|
|
|
<< " would be simplified if loop is unrolled.\n");
|
|
|
|
(void)0;
|
|
|
|
}
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
|
|
|
|
// Also track this instructions expected cost when executing the rolled
|
|
|
|
// loop form.
|
|
|
|
RolledDynamicCost += InstCost;
|
2015-05-23 01:41:35 +08:00
|
|
|
|
|
|
|
// If unrolled body turns out to be too big, bail out.
|
2015-07-29 04:07:29 +08:00
|
|
|
if (UnrolledCost > MaxUnrolledLoopSize) {
|
|
|
|
DEBUG(dbgs() << " Exceeded threshold.. exiting.\n"
|
|
|
|
<< " UnrolledCost: " << UnrolledCost
|
|
|
|
<< ", MaxUnrolledLoopSize: " << MaxUnrolledLoopSize
|
|
|
|
<< "\n");
|
2015-05-23 01:41:35 +08:00
|
|
|
return None;
|
2015-07-29 04:07:29 +08:00
|
|
|
}
|
[unroll] Make the unroll cost analysis terminate deterministically and
reasonably quickly.
I don't have a reduced test case, but for a version of FFMPEG, this
makes the loop unroller start finishing at all (after over 15 minutes of
running, it hadn't terminated for me, no idea if it was a true infloop
or just exponential work).
The key thing here is to check the DeadInstructions set when pulling
things off the worklist. Without this, we would re-walk the user list of
already dead instructions again and again and again. Consider phi nodes
with many, many operands and other patterns.
The other important aspect of this is that because we would keep
re-visiting instructions that were already known dead, we kept adding
their cost savings to this! This would cause our cost savings to be
*insanely* inflated from this.
While I was here, I also rotated the operand walk out of the worklist
loop to make the code easier to read. There is still work to be done to
minimize worklist traffic because we don't de-duplicate operands. This
means we may add the same instruction onto the worklist 1000s of times
if it shows up in 1000s of operansd to a PHI node for example.
Still, with this patch, the ffmpeg testcase I have finishes quickly and
I can't measure the runtime impact of the unroll analysis any more. I'll
probably try to do a few more cleanups to this code, but not sure how
much cleanup I can justify right now.
llvm-svn: 229038
2015-02-13 11:40:58 +08:00
|
|
|
}
|
2015-05-13 01:20:03 +08:00
|
|
|
|
2015-07-24 09:53:04 +08:00
|
|
|
TerminatorInst *TI = BB->getTerminator();
|
|
|
|
|
|
|
|
// Add in the live successors by first checking whether we have terminator
|
|
|
|
// that may be simplified based on the values simplified by this call.
|
|
|
|
if (BranchInst *BI = dyn_cast<BranchInst>(TI)) {
|
|
|
|
if (BI->isConditional()) {
|
|
|
|
if (Constant *SimpleCond =
|
|
|
|
SimplifiedValues.lookup(BI->getCondition())) {
|
2015-07-30 02:10:29 +08:00
|
|
|
BasicBlock *Succ = nullptr;
|
|
|
|
// Just take the first successor if condition is undef
|
|
|
|
if (isa<UndefValue>(SimpleCond))
|
|
|
|
Succ = BI->getSuccessor(0);
|
|
|
|
else
|
|
|
|
Succ = BI->getSuccessor(
|
|
|
|
cast<ConstantInt>(SimpleCond)->isZero() ? 1 : 0);
|
2015-07-29 03:21:21 +08:00
|
|
|
if (L->contains(Succ))
|
|
|
|
BBWorklist.insert(Succ);
|
2015-07-24 09:53:04 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else if (SwitchInst *SI = dyn_cast<SwitchInst>(TI)) {
|
|
|
|
if (Constant *SimpleCond =
|
|
|
|
SimplifiedValues.lookup(SI->getCondition())) {
|
2015-07-30 02:10:29 +08:00
|
|
|
BasicBlock *Succ = nullptr;
|
|
|
|
// Just take the first successor if condition is undef
|
|
|
|
if (isa<UndefValue>(SimpleCond))
|
|
|
|
Succ = SI->getSuccessor(0);
|
|
|
|
else
|
2015-07-30 02:10:33 +08:00
|
|
|
Succ = SI->findCaseValue(cast<ConstantInt>(SimpleCond))
|
|
|
|
.getCaseSuccessor();
|
2015-07-29 03:21:21 +08:00
|
|
|
if (L->contains(Succ))
|
|
|
|
BBWorklist.insert(Succ);
|
2015-07-24 09:53:04 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-05-23 01:41:35 +08:00
|
|
|
// Add BB's successors to the worklist.
|
|
|
|
for (BasicBlock *Succ : successors(BB))
|
|
|
|
if (L->contains(Succ))
|
|
|
|
BBWorklist.insert(Succ);
|
2015-02-05 10:34:00 +08:00
|
|
|
}
|
2015-05-23 01:41:35 +08:00
|
|
|
|
|
|
|
// If we found no optimization opportunities on the first iteration, we
|
|
|
|
// won't find them on later ones too.
|
2015-07-29 04:07:29 +08:00
|
|
|
if (UnrolledCost == RolledDynamicCost) {
|
|
|
|
DEBUG(dbgs() << " No opportunities found.. exiting.\n"
|
|
|
|
<< " UnrolledCost: " << UnrolledCost << "\n");
|
2015-05-23 01:41:35 +08:00
|
|
|
return None;
|
2015-07-29 04:07:29 +08:00
|
|
|
}
|
2015-02-05 10:34:00 +08:00
|
|
|
}
|
2015-07-29 04:07:29 +08:00
|
|
|
DEBUG(dbgs() << "Analysis finished:\n"
|
|
|
|
<< "UnrolledCost: " << UnrolledCost << ", "
|
|
|
|
<< "RolledDynamicCost: " << RolledDynamicCost << "\n");
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
return {{UnrolledCost, RolledDynamicCost}};
|
2015-05-23 01:41:35 +08:00
|
|
|
}
|
2015-02-05 10:34:00 +08:00
|
|
|
|
2007-05-08 23:14:19 +08:00
|
|
|
/// ApproximateLoopSize - Approximate the size of the loop.
|
2011-10-01 09:39:05 +08:00
|
|
|
static unsigned ApproximateLoopSize(const Loop *L, unsigned &NumCalls,
|
2013-01-21 21:04:33 +08:00
|
|
|
bool &NotDuplicatable,
|
2014-09-07 21:49:57 +08:00
|
|
|
const TargetTransformInfo &TTI,
|
2015-01-04 20:03:27 +08:00
|
|
|
AssumptionCache *AC) {
|
2014-09-07 21:49:57 +08:00
|
|
|
SmallPtrSet<const Value *, 32> EphValues;
|
2015-01-04 20:03:27 +08:00
|
|
|
CodeMetrics::collectEphemeralValues(L, AC, EphValues);
|
2014-09-07 21:49:57 +08:00
|
|
|
|
2009-10-31 22:54:17 +08:00
|
|
|
CodeMetrics Metrics;
|
2016-03-09 03:06:12 +08:00
|
|
|
for (BasicBlock *BB : L->blocks())
|
|
|
|
Metrics.analyzeBasicBlock(BB, TTI, EphValues);
|
2010-09-10 04:32:23 +08:00
|
|
|
NumCalls = Metrics.NumInlineCandidates;
|
2012-12-21 00:04:27 +08:00
|
|
|
NotDuplicatable = Metrics.notDuplicatable;
|
2011-07-23 08:29:16 +08:00
|
|
|
|
2010-09-10 03:07:31 +08:00
|
|
|
unsigned LoopSize = Metrics.NumInsts;
|
2011-07-23 08:29:16 +08:00
|
|
|
|
2010-09-10 03:07:31 +08:00
|
|
|
// Don't allow an estimate of size zero. This would allows unrolling of loops
|
|
|
|
// with huge iteration counts, which is a compile time problem even if it's
|
2015-01-10 08:30:55 +08:00
|
|
|
// not a problem for code quality. Also, the code using this size may assume
|
|
|
|
// that each loop has at least three instructions (likely a conditional
|
|
|
|
// branch, a comparison feeding that branch, and some kind of loop increment
|
|
|
|
// feeding that comparison instruction).
|
|
|
|
LoopSize = std::max(LoopSize, 3u);
|
2011-07-23 08:29:16 +08:00
|
|
|
|
2010-09-10 03:07:31 +08:00
|
|
|
return LoopSize;
|
2004-04-18 13:20:17 +08:00
|
|
|
}
|
|
|
|
|
2014-07-24 01:31:37 +08:00
|
|
|
// Returns the loop hint metadata node with the given name (for example,
|
|
|
|
// "llvm.loop.unroll.count"). If no such metadata node exists, then nullptr is
|
|
|
|
// returned.
|
2015-02-03 04:41:11 +08:00
|
|
|
static MDNode *GetUnrollMetadataForLoop(const Loop *L, StringRef Name) {
|
|
|
|
if (MDNode *LoopID = L->getLoopID())
|
|
|
|
return GetUnrollMetadata(LoopID, Name);
|
|
|
|
return nullptr;
|
2014-06-17 07:53:02 +08:00
|
|
|
}
|
|
|
|
|
2014-07-24 01:31:37 +08:00
|
|
|
// Returns true if the loop has an unroll(full) pragma.
|
|
|
|
static bool HasUnrollFullPragma(const Loop *L) {
|
2015-02-01 10:27:45 +08:00
|
|
|
return GetUnrollMetadataForLoop(L, "llvm.loop.unroll.full");
|
2014-06-17 07:53:02 +08:00
|
|
|
}
|
|
|
|
|
2015-08-11 01:28:08 +08:00
|
|
|
// Returns true if the loop has an unroll(enable) pragma. This metadata is used
|
|
|
|
// for both "#pragma unroll" and "#pragma clang loop unroll(enable)" directives.
|
|
|
|
static bool HasUnrollEnablePragma(const Loop *L) {
|
|
|
|
return GetUnrollMetadataForLoop(L, "llvm.loop.unroll.enable");
|
|
|
|
}
|
|
|
|
|
2014-06-17 07:53:02 +08:00
|
|
|
// Returns true if the loop has an unroll(disable) pragma.
|
|
|
|
static bool HasUnrollDisablePragma(const Loop *L) {
|
2015-02-01 10:27:45 +08:00
|
|
|
return GetUnrollMetadataForLoop(L, "llvm.loop.unroll.disable");
|
2014-06-17 07:53:02 +08:00
|
|
|
}
|
|
|
|
|
2015-03-09 14:14:18 +08:00
|
|
|
// Returns true if the loop has an runtime unroll(disable) pragma.
|
|
|
|
static bool HasRuntimeUnrollDisablePragma(const Loop *L) {
|
|
|
|
return GetUnrollMetadataForLoop(L, "llvm.loop.unroll.runtime.disable");
|
|
|
|
}
|
|
|
|
|
2014-06-17 07:53:02 +08:00
|
|
|
// If loop has an unroll_count pragma return the (necessarily
|
|
|
|
// positive) value from the pragma. Otherwise return 0.
|
|
|
|
static unsigned UnrollCountPragmaValue(const Loop *L) {
|
2015-02-03 04:41:11 +08:00
|
|
|
MDNode *MD = GetUnrollMetadataForLoop(L, "llvm.loop.unroll.count");
|
2014-07-24 01:31:37 +08:00
|
|
|
if (MD) {
|
|
|
|
assert(MD->getNumOperands() == 2 &&
|
|
|
|
"Unroll count hint metadata should have two operands.");
|
IR: Split Metadata from Value
Split `Metadata` away from the `Value` class hierarchy, as part of
PR21532. Assembly and bitcode changes are in the wings, but this is the
bulk of the change for the IR C++ API.
I have a follow-up patch prepared for `clang`. If this breaks other
sub-projects, I apologize in advance :(. Help me compile it on Darwin
I'll try to fix it. FWIW, the errors should be easy to fix, so it may
be simpler to just fix it yourself.
This breaks the build for all metadata-related code that's out-of-tree.
Rest assured the transition is mechanical and the compiler should catch
almost all of the problems.
Here's a quick guide for updating your code:
- `Metadata` is the root of a class hierarchy with three main classes:
`MDNode`, `MDString`, and `ValueAsMetadata`. It is distinct from
the `Value` class hierarchy. It is typeless -- i.e., instances do
*not* have a `Type`.
- `MDNode`'s operands are all `Metadata *` (instead of `Value *`).
- `TrackingVH<MDNode>` and `WeakVH` referring to metadata can be
replaced with `TrackingMDNodeRef` and `TrackingMDRef`, respectively.
If you're referring solely to resolved `MDNode`s -- post graph
construction -- just use `MDNode*`.
- `MDNode` (and the rest of `Metadata`) have only limited support for
`replaceAllUsesWith()`.
As long as an `MDNode` is pointing at a forward declaration -- the
result of `MDNode::getTemporary()` -- it maintains a side map of its
uses and can RAUW itself. Once the forward declarations are fully
resolved RAUW support is dropped on the ground. This means that
uniquing collisions on changing operands cause nodes to become
"distinct". (This already happened fairly commonly, whenever an
operand went to null.)
If you're constructing complex (non self-reference) `MDNode` cycles,
you need to call `MDNode::resolveCycles()` on each node (or on a
top-level node that somehow references all of the nodes). Also,
don't do that. Metadata cycles (and the RAUW machinery needed to
construct them) are expensive.
- An `MDNode` can only refer to a `Constant` through a bridge called
`ConstantAsMetadata` (one of the subclasses of `ValueAsMetadata`).
As a side effect, accessing an operand of an `MDNode` that is known
to be, e.g., `ConstantInt`, takes three steps: first, cast from
`Metadata` to `ConstantAsMetadata`; second, extract the `Constant`;
third, cast down to `ConstantInt`.
The eventual goal is to introduce `MDInt`/`MDFloat`/etc. and have
metadata schema owners transition away from using `Constant`s when
the type isn't important (and they don't care about referring to
`GlobalValue`s).
In the meantime, I've added transitional API to the `mdconst`
namespace that matches semantics with the old code, in order to
avoid adding the error-prone three-step equivalent to every call
site. If your old code was:
MDNode *N = foo();
bar(isa <ConstantInt>(N->getOperand(0)));
baz(cast <ConstantInt>(N->getOperand(1)));
bak(cast_or_null <ConstantInt>(N->getOperand(2)));
bat(dyn_cast <ConstantInt>(N->getOperand(3)));
bay(dyn_cast_or_null<ConstantInt>(N->getOperand(4)));
you can trivially match its semantics with:
MDNode *N = foo();
bar(mdconst::hasa <ConstantInt>(N->getOperand(0)));
baz(mdconst::extract <ConstantInt>(N->getOperand(1)));
bak(mdconst::extract_or_null <ConstantInt>(N->getOperand(2)));
bat(mdconst::dyn_extract <ConstantInt>(N->getOperand(3)));
bay(mdconst::dyn_extract_or_null<ConstantInt>(N->getOperand(4)));
and when you transition your metadata schema to `MDInt`:
MDNode *N = foo();
bar(isa <MDInt>(N->getOperand(0)));
baz(cast <MDInt>(N->getOperand(1)));
bak(cast_or_null <MDInt>(N->getOperand(2)));
bat(dyn_cast <MDInt>(N->getOperand(3)));
bay(dyn_cast_or_null<MDInt>(N->getOperand(4)));
- A `CallInst` -- specifically, intrinsic instructions -- can refer to
metadata through a bridge called `MetadataAsValue`. This is a
subclass of `Value` where `getType()->isMetadataTy()`.
`MetadataAsValue` is the *only* class that can legally refer to a
`LocalAsMetadata`, which is a bridged form of non-`Constant` values
like `Argument` and `Instruction`. It can also refer to any other
`Metadata` subclass.
(I'll break all your testcases in a follow-up commit, when I propagate
this change to assembly.)
llvm-svn: 223802
2014-12-10 02:38:53 +08:00
|
|
|
unsigned Count =
|
|
|
|
mdconst::extract<ConstantInt>(MD->getOperand(1))->getZExtValue();
|
2014-06-17 07:53:02 +08:00
|
|
|
assert(Count >= 1 && "Unroll count must be positive.");
|
|
|
|
return Count;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-07-19 05:04:33 +08:00
|
|
|
// Remove existing unroll metadata and add unroll disable metadata to
|
|
|
|
// indicate the loop has already been unrolled. This prevents a loop
|
|
|
|
// from being unrolled more than is directed by a pragma if the loop
|
|
|
|
// unrolling pass is run more than once (which it generally is).
|
|
|
|
static void SetLoopAlreadyUnrolled(Loop *L) {
|
|
|
|
MDNode *LoopID = L->getLoopID();
|
|
|
|
if (!LoopID) return;
|
|
|
|
|
|
|
|
// First remove any existing loop unrolling metadata.
|
IR: Split Metadata from Value
Split `Metadata` away from the `Value` class hierarchy, as part of
PR21532. Assembly and bitcode changes are in the wings, but this is the
bulk of the change for the IR C++ API.
I have a follow-up patch prepared for `clang`. If this breaks other
sub-projects, I apologize in advance :(. Help me compile it on Darwin
I'll try to fix it. FWIW, the errors should be easy to fix, so it may
be simpler to just fix it yourself.
This breaks the build for all metadata-related code that's out-of-tree.
Rest assured the transition is mechanical and the compiler should catch
almost all of the problems.
Here's a quick guide for updating your code:
- `Metadata` is the root of a class hierarchy with three main classes:
`MDNode`, `MDString`, and `ValueAsMetadata`. It is distinct from
the `Value` class hierarchy. It is typeless -- i.e., instances do
*not* have a `Type`.
- `MDNode`'s operands are all `Metadata *` (instead of `Value *`).
- `TrackingVH<MDNode>` and `WeakVH` referring to metadata can be
replaced with `TrackingMDNodeRef` and `TrackingMDRef`, respectively.
If you're referring solely to resolved `MDNode`s -- post graph
construction -- just use `MDNode*`.
- `MDNode` (and the rest of `Metadata`) have only limited support for
`replaceAllUsesWith()`.
As long as an `MDNode` is pointing at a forward declaration -- the
result of `MDNode::getTemporary()` -- it maintains a side map of its
uses and can RAUW itself. Once the forward declarations are fully
resolved RAUW support is dropped on the ground. This means that
uniquing collisions on changing operands cause nodes to become
"distinct". (This already happened fairly commonly, whenever an
operand went to null.)
If you're constructing complex (non self-reference) `MDNode` cycles,
you need to call `MDNode::resolveCycles()` on each node (or on a
top-level node that somehow references all of the nodes). Also,
don't do that. Metadata cycles (and the RAUW machinery needed to
construct them) are expensive.
- An `MDNode` can only refer to a `Constant` through a bridge called
`ConstantAsMetadata` (one of the subclasses of `ValueAsMetadata`).
As a side effect, accessing an operand of an `MDNode` that is known
to be, e.g., `ConstantInt`, takes three steps: first, cast from
`Metadata` to `ConstantAsMetadata`; second, extract the `Constant`;
third, cast down to `ConstantInt`.
The eventual goal is to introduce `MDInt`/`MDFloat`/etc. and have
metadata schema owners transition away from using `Constant`s when
the type isn't important (and they don't care about referring to
`GlobalValue`s).
In the meantime, I've added transitional API to the `mdconst`
namespace that matches semantics with the old code, in order to
avoid adding the error-prone three-step equivalent to every call
site. If your old code was:
MDNode *N = foo();
bar(isa <ConstantInt>(N->getOperand(0)));
baz(cast <ConstantInt>(N->getOperand(1)));
bak(cast_or_null <ConstantInt>(N->getOperand(2)));
bat(dyn_cast <ConstantInt>(N->getOperand(3)));
bay(dyn_cast_or_null<ConstantInt>(N->getOperand(4)));
you can trivially match its semantics with:
MDNode *N = foo();
bar(mdconst::hasa <ConstantInt>(N->getOperand(0)));
baz(mdconst::extract <ConstantInt>(N->getOperand(1)));
bak(mdconst::extract_or_null <ConstantInt>(N->getOperand(2)));
bat(mdconst::dyn_extract <ConstantInt>(N->getOperand(3)));
bay(mdconst::dyn_extract_or_null<ConstantInt>(N->getOperand(4)));
and when you transition your metadata schema to `MDInt`:
MDNode *N = foo();
bar(isa <MDInt>(N->getOperand(0)));
baz(cast <MDInt>(N->getOperand(1)));
bak(cast_or_null <MDInt>(N->getOperand(2)));
bat(dyn_cast <MDInt>(N->getOperand(3)));
bay(dyn_cast_or_null<MDInt>(N->getOperand(4)));
- A `CallInst` -- specifically, intrinsic instructions -- can refer to
metadata through a bridge called `MetadataAsValue`. This is a
subclass of `Value` where `getType()->isMetadataTy()`.
`MetadataAsValue` is the *only* class that can legally refer to a
`LocalAsMetadata`, which is a bridged form of non-`Constant` values
like `Argument` and `Instruction`. It can also refer to any other
`Metadata` subclass.
(I'll break all your testcases in a follow-up commit, when I propagate
this change to assembly.)
llvm-svn: 223802
2014-12-10 02:38:53 +08:00
|
|
|
SmallVector<Metadata *, 4> MDs;
|
2014-07-19 05:04:33 +08:00
|
|
|
// Reserve first location for self reference to the LoopID metadata node.
|
IR: Split Metadata from Value
Split `Metadata` away from the `Value` class hierarchy, as part of
PR21532. Assembly and bitcode changes are in the wings, but this is the
bulk of the change for the IR C++ API.
I have a follow-up patch prepared for `clang`. If this breaks other
sub-projects, I apologize in advance :(. Help me compile it on Darwin
I'll try to fix it. FWIW, the errors should be easy to fix, so it may
be simpler to just fix it yourself.
This breaks the build for all metadata-related code that's out-of-tree.
Rest assured the transition is mechanical and the compiler should catch
almost all of the problems.
Here's a quick guide for updating your code:
- `Metadata` is the root of a class hierarchy with three main classes:
`MDNode`, `MDString`, and `ValueAsMetadata`. It is distinct from
the `Value` class hierarchy. It is typeless -- i.e., instances do
*not* have a `Type`.
- `MDNode`'s operands are all `Metadata *` (instead of `Value *`).
- `TrackingVH<MDNode>` and `WeakVH` referring to metadata can be
replaced with `TrackingMDNodeRef` and `TrackingMDRef`, respectively.
If you're referring solely to resolved `MDNode`s -- post graph
construction -- just use `MDNode*`.
- `MDNode` (and the rest of `Metadata`) have only limited support for
`replaceAllUsesWith()`.
As long as an `MDNode` is pointing at a forward declaration -- the
result of `MDNode::getTemporary()` -- it maintains a side map of its
uses and can RAUW itself. Once the forward declarations are fully
resolved RAUW support is dropped on the ground. This means that
uniquing collisions on changing operands cause nodes to become
"distinct". (This already happened fairly commonly, whenever an
operand went to null.)
If you're constructing complex (non self-reference) `MDNode` cycles,
you need to call `MDNode::resolveCycles()` on each node (or on a
top-level node that somehow references all of the nodes). Also,
don't do that. Metadata cycles (and the RAUW machinery needed to
construct them) are expensive.
- An `MDNode` can only refer to a `Constant` through a bridge called
`ConstantAsMetadata` (one of the subclasses of `ValueAsMetadata`).
As a side effect, accessing an operand of an `MDNode` that is known
to be, e.g., `ConstantInt`, takes three steps: first, cast from
`Metadata` to `ConstantAsMetadata`; second, extract the `Constant`;
third, cast down to `ConstantInt`.
The eventual goal is to introduce `MDInt`/`MDFloat`/etc. and have
metadata schema owners transition away from using `Constant`s when
the type isn't important (and they don't care about referring to
`GlobalValue`s).
In the meantime, I've added transitional API to the `mdconst`
namespace that matches semantics with the old code, in order to
avoid adding the error-prone three-step equivalent to every call
site. If your old code was:
MDNode *N = foo();
bar(isa <ConstantInt>(N->getOperand(0)));
baz(cast <ConstantInt>(N->getOperand(1)));
bak(cast_or_null <ConstantInt>(N->getOperand(2)));
bat(dyn_cast <ConstantInt>(N->getOperand(3)));
bay(dyn_cast_or_null<ConstantInt>(N->getOperand(4)));
you can trivially match its semantics with:
MDNode *N = foo();
bar(mdconst::hasa <ConstantInt>(N->getOperand(0)));
baz(mdconst::extract <ConstantInt>(N->getOperand(1)));
bak(mdconst::extract_or_null <ConstantInt>(N->getOperand(2)));
bat(mdconst::dyn_extract <ConstantInt>(N->getOperand(3)));
bay(mdconst::dyn_extract_or_null<ConstantInt>(N->getOperand(4)));
and when you transition your metadata schema to `MDInt`:
MDNode *N = foo();
bar(isa <MDInt>(N->getOperand(0)));
baz(cast <MDInt>(N->getOperand(1)));
bak(cast_or_null <MDInt>(N->getOperand(2)));
bat(dyn_cast <MDInt>(N->getOperand(3)));
bay(dyn_cast_or_null<MDInt>(N->getOperand(4)));
- A `CallInst` -- specifically, intrinsic instructions -- can refer to
metadata through a bridge called `MetadataAsValue`. This is a
subclass of `Value` where `getType()->isMetadataTy()`.
`MetadataAsValue` is the *only* class that can legally refer to a
`LocalAsMetadata`, which is a bridged form of non-`Constant` values
like `Argument` and `Instruction`. It can also refer to any other
`Metadata` subclass.
(I'll break all your testcases in a follow-up commit, when I propagate
this change to assembly.)
llvm-svn: 223802
2014-12-10 02:38:53 +08:00
|
|
|
MDs.push_back(nullptr);
|
2014-07-19 05:04:33 +08:00
|
|
|
for (unsigned i = 1, ie = LoopID->getNumOperands(); i < ie; ++i) {
|
|
|
|
bool IsUnrollMetadata = false;
|
|
|
|
MDNode *MD = dyn_cast<MDNode>(LoopID->getOperand(i));
|
|
|
|
if (MD) {
|
|
|
|
const MDString *S = dyn_cast<MDString>(MD->getOperand(0));
|
|
|
|
IsUnrollMetadata = S && S->getString().startswith("llvm.loop.unroll.");
|
|
|
|
}
|
IR: Split Metadata from Value
Split `Metadata` away from the `Value` class hierarchy, as part of
PR21532. Assembly and bitcode changes are in the wings, but this is the
bulk of the change for the IR C++ API.
I have a follow-up patch prepared for `clang`. If this breaks other
sub-projects, I apologize in advance :(. Help me compile it on Darwin
I'll try to fix it. FWIW, the errors should be easy to fix, so it may
be simpler to just fix it yourself.
This breaks the build for all metadata-related code that's out-of-tree.
Rest assured the transition is mechanical and the compiler should catch
almost all of the problems.
Here's a quick guide for updating your code:
- `Metadata` is the root of a class hierarchy with three main classes:
`MDNode`, `MDString`, and `ValueAsMetadata`. It is distinct from
the `Value` class hierarchy. It is typeless -- i.e., instances do
*not* have a `Type`.
- `MDNode`'s operands are all `Metadata *` (instead of `Value *`).
- `TrackingVH<MDNode>` and `WeakVH` referring to metadata can be
replaced with `TrackingMDNodeRef` and `TrackingMDRef`, respectively.
If you're referring solely to resolved `MDNode`s -- post graph
construction -- just use `MDNode*`.
- `MDNode` (and the rest of `Metadata`) have only limited support for
`replaceAllUsesWith()`.
As long as an `MDNode` is pointing at a forward declaration -- the
result of `MDNode::getTemporary()` -- it maintains a side map of its
uses and can RAUW itself. Once the forward declarations are fully
resolved RAUW support is dropped on the ground. This means that
uniquing collisions on changing operands cause nodes to become
"distinct". (This already happened fairly commonly, whenever an
operand went to null.)
If you're constructing complex (non self-reference) `MDNode` cycles,
you need to call `MDNode::resolveCycles()` on each node (or on a
top-level node that somehow references all of the nodes). Also,
don't do that. Metadata cycles (and the RAUW machinery needed to
construct them) are expensive.
- An `MDNode` can only refer to a `Constant` through a bridge called
`ConstantAsMetadata` (one of the subclasses of `ValueAsMetadata`).
As a side effect, accessing an operand of an `MDNode` that is known
to be, e.g., `ConstantInt`, takes three steps: first, cast from
`Metadata` to `ConstantAsMetadata`; second, extract the `Constant`;
third, cast down to `ConstantInt`.
The eventual goal is to introduce `MDInt`/`MDFloat`/etc. and have
metadata schema owners transition away from using `Constant`s when
the type isn't important (and they don't care about referring to
`GlobalValue`s).
In the meantime, I've added transitional API to the `mdconst`
namespace that matches semantics with the old code, in order to
avoid adding the error-prone three-step equivalent to every call
site. If your old code was:
MDNode *N = foo();
bar(isa <ConstantInt>(N->getOperand(0)));
baz(cast <ConstantInt>(N->getOperand(1)));
bak(cast_or_null <ConstantInt>(N->getOperand(2)));
bat(dyn_cast <ConstantInt>(N->getOperand(3)));
bay(dyn_cast_or_null<ConstantInt>(N->getOperand(4)));
you can trivially match its semantics with:
MDNode *N = foo();
bar(mdconst::hasa <ConstantInt>(N->getOperand(0)));
baz(mdconst::extract <ConstantInt>(N->getOperand(1)));
bak(mdconst::extract_or_null <ConstantInt>(N->getOperand(2)));
bat(mdconst::dyn_extract <ConstantInt>(N->getOperand(3)));
bay(mdconst::dyn_extract_or_null<ConstantInt>(N->getOperand(4)));
and when you transition your metadata schema to `MDInt`:
MDNode *N = foo();
bar(isa <MDInt>(N->getOperand(0)));
baz(cast <MDInt>(N->getOperand(1)));
bak(cast_or_null <MDInt>(N->getOperand(2)));
bat(dyn_cast <MDInt>(N->getOperand(3)));
bay(dyn_cast_or_null<MDInt>(N->getOperand(4)));
- A `CallInst` -- specifically, intrinsic instructions -- can refer to
metadata through a bridge called `MetadataAsValue`. This is a
subclass of `Value` where `getType()->isMetadataTy()`.
`MetadataAsValue` is the *only* class that can legally refer to a
`LocalAsMetadata`, which is a bridged form of non-`Constant` values
like `Argument` and `Instruction`. It can also refer to any other
`Metadata` subclass.
(I'll break all your testcases in a follow-up commit, when I propagate
this change to assembly.)
llvm-svn: 223802
2014-12-10 02:38:53 +08:00
|
|
|
if (!IsUnrollMetadata)
|
|
|
|
MDs.push_back(LoopID->getOperand(i));
|
2014-07-19 05:04:33 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// Add unroll(disable) metadata to disable future unrolling.
|
|
|
|
LLVMContext &Context = L->getHeader()->getContext();
|
IR: Split Metadata from Value
Split `Metadata` away from the `Value` class hierarchy, as part of
PR21532. Assembly and bitcode changes are in the wings, but this is the
bulk of the change for the IR C++ API.
I have a follow-up patch prepared for `clang`. If this breaks other
sub-projects, I apologize in advance :(. Help me compile it on Darwin
I'll try to fix it. FWIW, the errors should be easy to fix, so it may
be simpler to just fix it yourself.
This breaks the build for all metadata-related code that's out-of-tree.
Rest assured the transition is mechanical and the compiler should catch
almost all of the problems.
Here's a quick guide for updating your code:
- `Metadata` is the root of a class hierarchy with three main classes:
`MDNode`, `MDString`, and `ValueAsMetadata`. It is distinct from
the `Value` class hierarchy. It is typeless -- i.e., instances do
*not* have a `Type`.
- `MDNode`'s operands are all `Metadata *` (instead of `Value *`).
- `TrackingVH<MDNode>` and `WeakVH` referring to metadata can be
replaced with `TrackingMDNodeRef` and `TrackingMDRef`, respectively.
If you're referring solely to resolved `MDNode`s -- post graph
construction -- just use `MDNode*`.
- `MDNode` (and the rest of `Metadata`) have only limited support for
`replaceAllUsesWith()`.
As long as an `MDNode` is pointing at a forward declaration -- the
result of `MDNode::getTemporary()` -- it maintains a side map of its
uses and can RAUW itself. Once the forward declarations are fully
resolved RAUW support is dropped on the ground. This means that
uniquing collisions on changing operands cause nodes to become
"distinct". (This already happened fairly commonly, whenever an
operand went to null.)
If you're constructing complex (non self-reference) `MDNode` cycles,
you need to call `MDNode::resolveCycles()` on each node (or on a
top-level node that somehow references all of the nodes). Also,
don't do that. Metadata cycles (and the RAUW machinery needed to
construct them) are expensive.
- An `MDNode` can only refer to a `Constant` through a bridge called
`ConstantAsMetadata` (one of the subclasses of `ValueAsMetadata`).
As a side effect, accessing an operand of an `MDNode` that is known
to be, e.g., `ConstantInt`, takes three steps: first, cast from
`Metadata` to `ConstantAsMetadata`; second, extract the `Constant`;
third, cast down to `ConstantInt`.
The eventual goal is to introduce `MDInt`/`MDFloat`/etc. and have
metadata schema owners transition away from using `Constant`s when
the type isn't important (and they don't care about referring to
`GlobalValue`s).
In the meantime, I've added transitional API to the `mdconst`
namespace that matches semantics with the old code, in order to
avoid adding the error-prone three-step equivalent to every call
site. If your old code was:
MDNode *N = foo();
bar(isa <ConstantInt>(N->getOperand(0)));
baz(cast <ConstantInt>(N->getOperand(1)));
bak(cast_or_null <ConstantInt>(N->getOperand(2)));
bat(dyn_cast <ConstantInt>(N->getOperand(3)));
bay(dyn_cast_or_null<ConstantInt>(N->getOperand(4)));
you can trivially match its semantics with:
MDNode *N = foo();
bar(mdconst::hasa <ConstantInt>(N->getOperand(0)));
baz(mdconst::extract <ConstantInt>(N->getOperand(1)));
bak(mdconst::extract_or_null <ConstantInt>(N->getOperand(2)));
bat(mdconst::dyn_extract <ConstantInt>(N->getOperand(3)));
bay(mdconst::dyn_extract_or_null<ConstantInt>(N->getOperand(4)));
and when you transition your metadata schema to `MDInt`:
MDNode *N = foo();
bar(isa <MDInt>(N->getOperand(0)));
baz(cast <MDInt>(N->getOperand(1)));
bak(cast_or_null <MDInt>(N->getOperand(2)));
bat(dyn_cast <MDInt>(N->getOperand(3)));
bay(dyn_cast_or_null<MDInt>(N->getOperand(4)));
- A `CallInst` -- specifically, intrinsic instructions -- can refer to
metadata through a bridge called `MetadataAsValue`. This is a
subclass of `Value` where `getType()->isMetadataTy()`.
`MetadataAsValue` is the *only* class that can legally refer to a
`LocalAsMetadata`, which is a bridged form of non-`Constant` values
like `Argument` and `Instruction`. It can also refer to any other
`Metadata` subclass.
(I'll break all your testcases in a follow-up commit, when I propagate
this change to assembly.)
llvm-svn: 223802
2014-12-10 02:38:53 +08:00
|
|
|
SmallVector<Metadata *, 1> DisableOperands;
|
2014-07-24 01:31:37 +08:00
|
|
|
DisableOperands.push_back(MDString::get(Context, "llvm.loop.unroll.disable"));
|
2014-07-19 05:29:41 +08:00
|
|
|
MDNode *DisableNode = MDNode::get(Context, DisableOperands);
|
IR: Split Metadata from Value
Split `Metadata` away from the `Value` class hierarchy, as part of
PR21532. Assembly and bitcode changes are in the wings, but this is the
bulk of the change for the IR C++ API.
I have a follow-up patch prepared for `clang`. If this breaks other
sub-projects, I apologize in advance :(. Help me compile it on Darwin
I'll try to fix it. FWIW, the errors should be easy to fix, so it may
be simpler to just fix it yourself.
This breaks the build for all metadata-related code that's out-of-tree.
Rest assured the transition is mechanical and the compiler should catch
almost all of the problems.
Here's a quick guide for updating your code:
- `Metadata` is the root of a class hierarchy with three main classes:
`MDNode`, `MDString`, and `ValueAsMetadata`. It is distinct from
the `Value` class hierarchy. It is typeless -- i.e., instances do
*not* have a `Type`.
- `MDNode`'s operands are all `Metadata *` (instead of `Value *`).
- `TrackingVH<MDNode>` and `WeakVH` referring to metadata can be
replaced with `TrackingMDNodeRef` and `TrackingMDRef`, respectively.
If you're referring solely to resolved `MDNode`s -- post graph
construction -- just use `MDNode*`.
- `MDNode` (and the rest of `Metadata`) have only limited support for
`replaceAllUsesWith()`.
As long as an `MDNode` is pointing at a forward declaration -- the
result of `MDNode::getTemporary()` -- it maintains a side map of its
uses and can RAUW itself. Once the forward declarations are fully
resolved RAUW support is dropped on the ground. This means that
uniquing collisions on changing operands cause nodes to become
"distinct". (This already happened fairly commonly, whenever an
operand went to null.)
If you're constructing complex (non self-reference) `MDNode` cycles,
you need to call `MDNode::resolveCycles()` on each node (or on a
top-level node that somehow references all of the nodes). Also,
don't do that. Metadata cycles (and the RAUW machinery needed to
construct them) are expensive.
- An `MDNode` can only refer to a `Constant` through a bridge called
`ConstantAsMetadata` (one of the subclasses of `ValueAsMetadata`).
As a side effect, accessing an operand of an `MDNode` that is known
to be, e.g., `ConstantInt`, takes three steps: first, cast from
`Metadata` to `ConstantAsMetadata`; second, extract the `Constant`;
third, cast down to `ConstantInt`.
The eventual goal is to introduce `MDInt`/`MDFloat`/etc. and have
metadata schema owners transition away from using `Constant`s when
the type isn't important (and they don't care about referring to
`GlobalValue`s).
In the meantime, I've added transitional API to the `mdconst`
namespace that matches semantics with the old code, in order to
avoid adding the error-prone three-step equivalent to every call
site. If your old code was:
MDNode *N = foo();
bar(isa <ConstantInt>(N->getOperand(0)));
baz(cast <ConstantInt>(N->getOperand(1)));
bak(cast_or_null <ConstantInt>(N->getOperand(2)));
bat(dyn_cast <ConstantInt>(N->getOperand(3)));
bay(dyn_cast_or_null<ConstantInt>(N->getOperand(4)));
you can trivially match its semantics with:
MDNode *N = foo();
bar(mdconst::hasa <ConstantInt>(N->getOperand(0)));
baz(mdconst::extract <ConstantInt>(N->getOperand(1)));
bak(mdconst::extract_or_null <ConstantInt>(N->getOperand(2)));
bat(mdconst::dyn_extract <ConstantInt>(N->getOperand(3)));
bay(mdconst::dyn_extract_or_null<ConstantInt>(N->getOperand(4)));
and when you transition your metadata schema to `MDInt`:
MDNode *N = foo();
bar(isa <MDInt>(N->getOperand(0)));
baz(cast <MDInt>(N->getOperand(1)));
bak(cast_or_null <MDInt>(N->getOperand(2)));
bat(dyn_cast <MDInt>(N->getOperand(3)));
bay(dyn_cast_or_null<MDInt>(N->getOperand(4)));
- A `CallInst` -- specifically, intrinsic instructions -- can refer to
metadata through a bridge called `MetadataAsValue`. This is a
subclass of `Value` where `getType()->isMetadataTy()`.
`MetadataAsValue` is the *only* class that can legally refer to a
`LocalAsMetadata`, which is a bridged form of non-`Constant` values
like `Argument` and `Instruction`. It can also refer to any other
`Metadata` subclass.
(I'll break all your testcases in a follow-up commit, when I propagate
this change to assembly.)
llvm-svn: 223802
2014-12-10 02:38:53 +08:00
|
|
|
MDs.push_back(DisableNode);
|
2014-07-19 05:04:33 +08:00
|
|
|
|
IR: Split Metadata from Value
Split `Metadata` away from the `Value` class hierarchy, as part of
PR21532. Assembly and bitcode changes are in the wings, but this is the
bulk of the change for the IR C++ API.
I have a follow-up patch prepared for `clang`. If this breaks other
sub-projects, I apologize in advance :(. Help me compile it on Darwin
I'll try to fix it. FWIW, the errors should be easy to fix, so it may
be simpler to just fix it yourself.
This breaks the build for all metadata-related code that's out-of-tree.
Rest assured the transition is mechanical and the compiler should catch
almost all of the problems.
Here's a quick guide for updating your code:
- `Metadata` is the root of a class hierarchy with three main classes:
`MDNode`, `MDString`, and `ValueAsMetadata`. It is distinct from
the `Value` class hierarchy. It is typeless -- i.e., instances do
*not* have a `Type`.
- `MDNode`'s operands are all `Metadata *` (instead of `Value *`).
- `TrackingVH<MDNode>` and `WeakVH` referring to metadata can be
replaced with `TrackingMDNodeRef` and `TrackingMDRef`, respectively.
If you're referring solely to resolved `MDNode`s -- post graph
construction -- just use `MDNode*`.
- `MDNode` (and the rest of `Metadata`) have only limited support for
`replaceAllUsesWith()`.
As long as an `MDNode` is pointing at a forward declaration -- the
result of `MDNode::getTemporary()` -- it maintains a side map of its
uses and can RAUW itself. Once the forward declarations are fully
resolved RAUW support is dropped on the ground. This means that
uniquing collisions on changing operands cause nodes to become
"distinct". (This already happened fairly commonly, whenever an
operand went to null.)
If you're constructing complex (non self-reference) `MDNode` cycles,
you need to call `MDNode::resolveCycles()` on each node (or on a
top-level node that somehow references all of the nodes). Also,
don't do that. Metadata cycles (and the RAUW machinery needed to
construct them) are expensive.
- An `MDNode` can only refer to a `Constant` through a bridge called
`ConstantAsMetadata` (one of the subclasses of `ValueAsMetadata`).
As a side effect, accessing an operand of an `MDNode` that is known
to be, e.g., `ConstantInt`, takes three steps: first, cast from
`Metadata` to `ConstantAsMetadata`; second, extract the `Constant`;
third, cast down to `ConstantInt`.
The eventual goal is to introduce `MDInt`/`MDFloat`/etc. and have
metadata schema owners transition away from using `Constant`s when
the type isn't important (and they don't care about referring to
`GlobalValue`s).
In the meantime, I've added transitional API to the `mdconst`
namespace that matches semantics with the old code, in order to
avoid adding the error-prone three-step equivalent to every call
site. If your old code was:
MDNode *N = foo();
bar(isa <ConstantInt>(N->getOperand(0)));
baz(cast <ConstantInt>(N->getOperand(1)));
bak(cast_or_null <ConstantInt>(N->getOperand(2)));
bat(dyn_cast <ConstantInt>(N->getOperand(3)));
bay(dyn_cast_or_null<ConstantInt>(N->getOperand(4)));
you can trivially match its semantics with:
MDNode *N = foo();
bar(mdconst::hasa <ConstantInt>(N->getOperand(0)));
baz(mdconst::extract <ConstantInt>(N->getOperand(1)));
bak(mdconst::extract_or_null <ConstantInt>(N->getOperand(2)));
bat(mdconst::dyn_extract <ConstantInt>(N->getOperand(3)));
bay(mdconst::dyn_extract_or_null<ConstantInt>(N->getOperand(4)));
and when you transition your metadata schema to `MDInt`:
MDNode *N = foo();
bar(isa <MDInt>(N->getOperand(0)));
baz(cast <MDInt>(N->getOperand(1)));
bak(cast_or_null <MDInt>(N->getOperand(2)));
bat(dyn_cast <MDInt>(N->getOperand(3)));
bay(dyn_cast_or_null<MDInt>(N->getOperand(4)));
- A `CallInst` -- specifically, intrinsic instructions -- can refer to
metadata through a bridge called `MetadataAsValue`. This is a
subclass of `Value` where `getType()->isMetadataTy()`.
`MetadataAsValue` is the *only* class that can legally refer to a
`LocalAsMetadata`, which is a bridged form of non-`Constant` values
like `Argument` and `Instruction`. It can also refer to any other
`Metadata` subclass.
(I'll break all your testcases in a follow-up commit, when I propagate
this change to assembly.)
llvm-svn: 223802
2014-12-10 02:38:53 +08:00
|
|
|
MDNode *NewLoopID = MDNode::get(Context, MDs);
|
2014-07-19 05:04:33 +08:00
|
|
|
// Set operand 0 to refer to the loop id itself.
|
|
|
|
NewLoopID->replaceOperandWith(0, NewLoopID);
|
|
|
|
L->setLoopID(NewLoopID);
|
|
|
|
}
|
|
|
|
|
2016-01-12 09:06:32 +08:00
|
|
|
static bool canUnrollCompletely(Loop *L, unsigned Threshold,
|
|
|
|
unsigned PercentDynamicCostSavedThreshold,
|
|
|
|
unsigned DynamicCostSavingsDiscount,
|
|
|
|
uint64_t UnrolledCost,
|
|
|
|
uint64_t RolledDynamicCost) {
|
2015-05-13 01:20:03 +08:00
|
|
|
if (Threshold == NoThreshold) {
|
|
|
|
DEBUG(dbgs() << " Can fully unroll, because no threshold is set.\n");
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
if (UnrolledCost <= Threshold) {
|
|
|
|
DEBUG(dbgs() << " Can fully unroll, because unrolled cost: "
|
|
|
|
<< UnrolledCost << "<" << Threshold << "\n");
|
2015-05-13 01:20:03 +08:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
assert(UnrolledCost && "UnrolledCost can't be 0 at this point.");
|
|
|
|
assert(RolledDynamicCost >= UnrolledCost &&
|
|
|
|
"Cannot have a higher unrolled cost than a rolled cost!");
|
|
|
|
|
|
|
|
// Compute the percentage of the dynamic cost in the rolled form that is
|
|
|
|
// saved when unrolled. If unrolling dramatically reduces the estimated
|
|
|
|
// dynamic cost of the loop, we use a higher threshold to allow more
|
|
|
|
// unrolling.
|
|
|
|
unsigned PercentDynamicCostSaved =
|
|
|
|
(uint64_t)(RolledDynamicCost - UnrolledCost) * 100ull / RolledDynamicCost;
|
|
|
|
|
|
|
|
if (PercentDynamicCostSaved >= PercentDynamicCostSavedThreshold &&
|
|
|
|
(int64_t)UnrolledCost - (int64_t)DynamicCostSavingsDiscount <=
|
|
|
|
(int64_t)Threshold) {
|
|
|
|
DEBUG(dbgs() << " Can fully unroll, because unrolling will reduce the "
|
|
|
|
"expected dynamic cost by " << PercentDynamicCostSaved
|
|
|
|
<< "% (threshold: " << PercentDynamicCostSavedThreshold
|
|
|
|
<< "%)\n"
|
|
|
|
<< " and the unrolled cost (" << UnrolledCost
|
|
|
|
<< ") is less than the max threshold ("
|
|
|
|
<< DynamicCostSavingsDiscount << ").\n");
|
2015-05-13 01:20:03 +08:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
DEBUG(dbgs() << " Too large to fully unroll:\n");
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
DEBUG(dbgs() << " Threshold: " << Threshold << "\n");
|
|
|
|
DEBUG(dbgs() << " Max threshold: " << DynamicCostSavingsDiscount << "\n");
|
|
|
|
DEBUG(dbgs() << " Percent cost saved threshold: "
|
|
|
|
<< PercentDynamicCostSavedThreshold << "%\n");
|
|
|
|
DEBUG(dbgs() << " Unrolled cost: " << UnrolledCost << "\n");
|
|
|
|
DEBUG(dbgs() << " Rolled dynamic cost: " << RolledDynamicCost << "\n");
|
|
|
|
DEBUG(dbgs() << " Percent cost saved: " << PercentDynamicCostSaved
|
|
|
|
<< "\n");
|
2015-05-13 01:20:03 +08:00
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2016-01-12 13:21:37 +08:00
|
|
|
static bool tryToUnrollLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
|
|
|
|
ScalarEvolution *SE, const TargetTransformInfo &TTI,
|
|
|
|
AssumptionCache &AC, bool PreserveLCSSA,
|
|
|
|
Optional<unsigned> ProvidedCount,
|
|
|
|
Optional<unsigned> ProvidedThreshold,
|
|
|
|
Optional<bool> ProvidedAllowPartial,
|
|
|
|
Optional<bool> ProvidedRuntime) {
|
2007-05-08 23:19:19 +08:00
|
|
|
BasicBlock *Header = L->getHeader();
|
2010-01-05 09:27:44 +08:00
|
|
|
DEBUG(dbgs() << "Loop Unroll: F[" << Header->getParent()->getName()
|
2009-07-25 08:23:56 +08:00
|
|
|
<< "] Loop %" << Header->getName() << "\n");
|
2011-07-23 08:29:16 +08:00
|
|
|
|
2014-06-17 07:53:02 +08:00
|
|
|
if (HasUnrollDisablePragma(L)) {
|
|
|
|
return false;
|
2014-04-02 02:50:30 +08:00
|
|
|
}
|
2014-07-24 01:31:37 +08:00
|
|
|
bool PragmaFullUnroll = HasUnrollFullPragma(L);
|
2015-08-11 01:28:08 +08:00
|
|
|
bool PragmaEnableUnroll = HasUnrollEnablePragma(L);
|
2014-06-17 07:53:02 +08:00
|
|
|
unsigned PragmaCount = UnrollCountPragmaValue(L);
|
2015-08-11 01:28:08 +08:00
|
|
|
bool HasPragma = PragmaFullUnroll || PragmaEnableUnroll || PragmaCount > 0;
|
2014-06-17 07:53:02 +08:00
|
|
|
|
2011-08-12 07:36:16 +08:00
|
|
|
// Find trip count and trip multiple if count is not available
|
|
|
|
unsigned TripCount = 0;
|
2011-07-23 08:33:05 +08:00
|
|
|
unsigned TripMultiple = 1;
|
2014-10-11 08:12:11 +08:00
|
|
|
// If there are multiple exiting blocks but one of them is the latch, use the
|
|
|
|
// latch for the trip count estimation. Otherwise insist on a single exiting
|
|
|
|
// block for the trip count estimation.
|
|
|
|
BasicBlock *ExitingBlock = L->getLoopLatch();
|
|
|
|
if (!ExitingBlock || !L->isLoopExiting(ExitingBlock))
|
|
|
|
ExitingBlock = L->getExitingBlock();
|
|
|
|
if (ExitingBlock) {
|
|
|
|
TripCount = SE->getSmallConstantTripCount(L, ExitingBlock);
|
|
|
|
TripMultiple = SE->getSmallConstantTripMultiple(L, ExitingBlock);
|
2011-08-12 07:36:16 +08:00
|
|
|
}
|
2013-09-12 03:25:43 +08:00
|
|
|
|
2016-01-12 08:55:26 +08:00
|
|
|
TargetTransformInfo::UnrollingPreferences UP = gatherUnrollingPreferences(
|
|
|
|
L, TTI, ProvidedThreshold, ProvidedCount, ProvidedAllowPartial,
|
|
|
|
ProvidedRuntime, PragmaCount, PragmaFullUnroll, PragmaEnableUnroll,
|
|
|
|
TripCount);
|
|
|
|
|
|
|
|
unsigned Count = UP.Count;
|
|
|
|
bool CountSetExplicitly = Count != 0;
|
|
|
|
// Use a heuristic count if we didn't set anything explicitly.
|
|
|
|
if (!CountSetExplicitly)
|
|
|
|
Count = TripCount == 0 ? DefaultUnrollRuntimeCount : TripCount;
|
|
|
|
if (TripCount && Count > TripCount)
|
|
|
|
Count = TripCount;
|
2014-06-17 07:53:02 +08:00
|
|
|
|
|
|
|
unsigned NumInlineCandidates;
|
|
|
|
bool notDuplicatable;
|
|
|
|
unsigned LoopSize =
|
2015-01-04 20:03:27 +08:00
|
|
|
ApproximateLoopSize(L, NumInlineCandidates, notDuplicatable, TTI, &AC);
|
2014-06-17 07:53:02 +08:00
|
|
|
DEBUG(dbgs() << " Loop Size = " << LoopSize << "\n");
|
2015-01-10 08:30:55 +08:00
|
|
|
|
|
|
|
// When computing the unrolled size, note that the conditional branch on the
|
|
|
|
// backedge and the comparison feeding it are not replicated like the rest of
|
|
|
|
// the loop body (which is why 2 is subtracted).
|
|
|
|
uint64_t UnrolledSize = (uint64_t)(LoopSize-2) * Count + 2;
|
2014-06-17 07:53:02 +08:00
|
|
|
if (notDuplicatable) {
|
|
|
|
DEBUG(dbgs() << " Not unrolling loop which contains non-duplicatable"
|
|
|
|
<< " instructions.\n");
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
if (NumInlineCandidates != 0) {
|
|
|
|
DEBUG(dbgs() << " Not unrolling loop with inlinable calls.\n");
|
|
|
|
return false;
|
|
|
|
}
|
2011-12-09 14:19:40 +08:00
|
|
|
|
2014-06-17 07:53:02 +08:00
|
|
|
// Given Count, TripCount and thresholds determine the type of
|
|
|
|
// unrolling which is to be performed.
|
|
|
|
enum { Full = 0, Partial = 1, Runtime = 2 };
|
|
|
|
int Unrolling;
|
|
|
|
if (TripCount && Count == TripCount) {
|
2015-05-13 01:20:03 +08:00
|
|
|
Unrolling = Partial;
|
|
|
|
// If the loop is really small, we don't need to run an expensive analysis.
|
2016-01-12 08:55:26 +08:00
|
|
|
if (canUnrollCompletely(L, UP.Threshold, 100, UP.DynamicCostSavingsDiscount,
|
[Unroll] Rework the naming and structure of the new unroll heuristics.
The new naming is (to me) much easier to understand. Here is a summary
of the new state of the world:
- '*Threshold' is the threshold for full unrolling. It is measured
against the estimated unrolled cost as computed by getUserCost in TTI
(or CodeMetrics, etc). We will exceed this threshold when unrolling
loops where unrolling exposes a significant degree of simplification
of the logic within the loop.
- '*PercentDynamicCostSavedThreshold' is the percentage of the loop's
estimated dynamic execution cost which needs to be saved by unrolling
to apply a discount to the estimated unrolled cost.
- '*DynamicCostSavingsDiscount' is the discount applied to the estimated
unrolling cost when the dynamic savings are expected to be high.
When actually analyzing the loop, we now produce both an estimated
unrolled cost, and an estimated rolled cost. The rolled cost is notably
a dynamic estimate based on our analysis of the expected execution of
each iteration.
While we're still working to build up the infrastructure for making
these estimates, to me it is much more clear *how* to make them better
when they have reasonably descriptive names. For example, we may want to
apply estimated (from heuristics or profiles) dynamic execution weights
to the *dynamic* cost estimates. If we start doing that, we would also
need to track the static unrolled cost and the dynamic unrolled cost, as
only the latter could reasonably be weighted by profile information.
This patch is sadly not without functionality change for the new unroll
analysis logic. Buried in the heuristic management were several things
that surprised me. For example, we never subtracted the optimized
instruction count off when comparing against the unroll heursistics!
I don't know if this just got lost somewhere along the way or what, but
with the new accounting of things, this is much easier to keep track of
and we use the post-simplification cost estimate to compare to the
thresholds, and use the dynamic cost reduction ratio to select whether
we can exceed the baseline threshold.
The old values of these flags also don't necessarily make sense. My
impression is that none of these thresholds or discounts have been tuned
yet, and so they're just arbitrary placehold numbers. As such, I've not
bothered to adjust for the fact that this is now a discount and not
a tow-tier threshold model. We need to tune all these values once the
logic is ready to be enabled.
Differential Revision: http://reviews.llvm.org/D9966
llvm-svn: 239164
2015-06-06 01:01:43 +08:00
|
|
|
UnrolledSize, UnrolledSize)) {
|
2014-06-17 07:53:02 +08:00
|
|
|
Unrolling = Full;
|
2015-05-13 01:20:03 +08:00
|
|
|
} else {
|
|
|
|
// The loop isn't that small, but we still can fully unroll it if that
|
|
|
|
// helps to remove a significant number of instructions.
|
|
|
|
// To check that, run additional analysis on the loop.
|
2016-01-12 08:55:26 +08:00
|
|
|
if (Optional<EstimatedUnrollCost> Cost = analyzeLoopUnrollCost(
|
|
|
|
L, TripCount, DT, *SE, TTI,
|
|
|
|
UP.Threshold + UP.DynamicCostSavingsDiscount))
|
|
|
|
if (canUnrollCompletely(L, UP.Threshold,
|
|
|
|
UP.PercentDynamicCostSavedThreshold,
|
|
|
|
UP.DynamicCostSavingsDiscount,
|
|
|
|
Cost->UnrolledCost, Cost->RolledDynamicCost)) {
|
2015-05-23 01:41:35 +08:00
|
|
|
Unrolling = Full;
|
|
|
|
}
|
2014-06-17 07:53:02 +08:00
|
|
|
}
|
|
|
|
} else if (TripCount && Count < TripCount) {
|
|
|
|
Unrolling = Partial;
|
|
|
|
} else {
|
|
|
|
Unrolling = Runtime;
|
2007-05-12 04:53:41 +08:00
|
|
|
}
|
2007-03-03 07:31:34 +08:00
|
|
|
|
2014-06-17 07:53:02 +08:00
|
|
|
// Reduce count based on the type of unrolling and the threshold values.
|
|
|
|
unsigned OriginalCount = Count;
|
2016-01-12 08:55:26 +08:00
|
|
|
bool AllowRuntime = PragmaEnableUnroll || (PragmaCount > 0) || UP.Runtime;
|
2015-07-14 02:26:27 +08:00
|
|
|
// Don't unroll a runtime trip count loop with unroll full pragma.
|
|
|
|
if (HasRuntimeUnrollDisablePragma(L) || PragmaFullUnroll) {
|
2015-03-09 14:14:18 +08:00
|
|
|
AllowRuntime = false;
|
|
|
|
}
|
2014-06-17 07:53:02 +08:00
|
|
|
if (Unrolling == Partial) {
|
2016-01-12 08:55:26 +08:00
|
|
|
bool AllowPartial = PragmaEnableUnroll || UP.Partial;
|
2014-06-17 07:53:02 +08:00
|
|
|
if (!AllowPartial && !CountSetExplicitly) {
|
|
|
|
DEBUG(dbgs() << " will not try to unroll partially because "
|
|
|
|
<< "-unroll-allow-partial not given\n");
|
2012-12-21 00:04:27 +08:00
|
|
|
return false;
|
|
|
|
}
|
2016-01-12 08:55:26 +08:00
|
|
|
if (UP.PartialThreshold != NoThreshold &&
|
|
|
|
UnrolledSize > UP.PartialThreshold) {
|
2014-06-17 07:53:02 +08:00
|
|
|
// Reduce unroll count to be modulo of TripCount for partial unrolling.
|
2016-01-12 08:55:26 +08:00
|
|
|
Count = (std::max(UP.PartialThreshold, 3u) - 2) / (LoopSize - 2);
|
2014-06-17 07:53:02 +08:00
|
|
|
while (Count != 0 && TripCount % Count != 0)
|
|
|
|
Count--;
|
|
|
|
}
|
|
|
|
} else if (Unrolling == Runtime) {
|
|
|
|
if (!AllowRuntime && !CountSetExplicitly) {
|
|
|
|
DEBUG(dbgs() << " will not try to unroll loop with runtime trip count "
|
|
|
|
<< "-unroll-runtime not given\n");
|
2010-09-10 04:02:23 +08:00
|
|
|
return false;
|
2010-02-06 07:21:31 +08:00
|
|
|
}
|
2014-06-17 07:53:02 +08:00
|
|
|
// Reduce unroll count to be the largest power-of-two factor of
|
|
|
|
// the original count which satisfies the threshold limit.
|
2016-01-12 08:55:26 +08:00
|
|
|
while (Count != 0 && UnrolledSize > UP.PartialThreshold) {
|
2014-06-17 07:53:02 +08:00
|
|
|
Count >>= 1;
|
2015-01-10 08:30:55 +08:00
|
|
|
UnrolledSize = (LoopSize-2) * Count + 2;
|
2014-06-17 07:53:02 +08:00
|
|
|
}
|
|
|
|
if (Count > UP.MaxCount)
|
|
|
|
Count = UP.MaxCount;
|
|
|
|
DEBUG(dbgs() << " partially unrolling with count: " << Count << "\n");
|
|
|
|
}
|
|
|
|
|
|
|
|
if (HasPragma) {
|
2014-07-24 04:05:44 +08:00
|
|
|
if (PragmaCount != 0)
|
|
|
|
// If loop has an unroll count pragma mark loop as unrolled to prevent
|
|
|
|
// unrolling beyond that requested by the pragma.
|
|
|
|
SetLoopAlreadyUnrolled(L);
|
2014-07-19 05:04:33 +08:00
|
|
|
|
2014-06-17 07:53:02 +08:00
|
|
|
// Emit optimization remarks if we are unable to unroll the loop
|
|
|
|
// as directed by a pragma.
|
|
|
|
DebugLoc LoopLoc = L->getStartLoc();
|
|
|
|
Function *F = Header->getParent();
|
|
|
|
LLVMContext &Ctx = F->getContext();
|
2015-08-11 01:28:08 +08:00
|
|
|
if ((PragmaCount > 0) && Count != OriginalCount) {
|
2014-06-17 07:53:02 +08:00
|
|
|
emitOptimizationRemarkMissed(
|
|
|
|
Ctx, DEBUG_TYPE, *F, LoopLoc,
|
|
|
|
"Unable to unroll loop the number of times directed by "
|
|
|
|
"unroll_count pragma because unrolled size is too large.");
|
2015-08-11 01:28:08 +08:00
|
|
|
} else if (PragmaFullUnroll && !TripCount) {
|
|
|
|
emitOptimizationRemarkMissed(
|
|
|
|
Ctx, DEBUG_TYPE, *F, LoopLoc,
|
|
|
|
"Unable to fully unroll loop as directed by unroll(full) pragma "
|
|
|
|
"because loop has a runtime trip count.");
|
|
|
|
} else if (PragmaEnableUnroll && Count != TripCount && Count < 2) {
|
|
|
|
emitOptimizationRemarkMissed(
|
|
|
|
Ctx, DEBUG_TYPE, *F, LoopLoc,
|
|
|
|
"Unable to unroll loop as directed by unroll(enable) pragma because "
|
|
|
|
"unrolled size is too large.");
|
|
|
|
} else if ((PragmaFullUnroll || PragmaEnableUnroll) && TripCount &&
|
|
|
|
Count != TripCount) {
|
|
|
|
emitOptimizationRemarkMissed(
|
|
|
|
Ctx, DEBUG_TYPE, *F, LoopLoc,
|
|
|
|
"Unable to fully unroll loop as directed by unroll pragma because "
|
|
|
|
"unrolled size is too large.");
|
2007-05-12 04:53:41 +08:00
|
|
|
}
|
2004-04-18 13:20:17 +08:00
|
|
|
}
|
2005-04-22 07:48:37 +08:00
|
|
|
|
2014-06-17 07:53:02 +08:00
|
|
|
if (Unrolling != Full && Count < 2) {
|
|
|
|
// Partial unrolling by 1 is a nop. For full unrolling, a factor
|
|
|
|
// of 1 makes sense because loop control can be eliminated.
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2008-05-14 08:24:14 +08:00
|
|
|
// Unroll the loop.
|
2015-04-14 11:20:38 +08:00
|
|
|
if (!UnrollLoop(L, Count, TripCount, AllowRuntime, UP.AllowExpensiveTripCount,
|
2015-12-17 02:40:20 +08:00
|
|
|
TripMultiple, LI, SE, &DT, &AC, PreserveLCSSA))
|
2008-05-14 08:24:14 +08:00
|
|
|
return false;
|
2004-04-18 13:20:17 +08:00
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
2016-01-12 13:21:37 +08:00
|
|
|
|
|
|
|
namespace {
|
|
|
|
class LoopUnroll : public LoopPass {
|
|
|
|
public:
|
|
|
|
static char ID; // Pass ID, replacement for typeid
|
|
|
|
LoopUnroll(Optional<unsigned> Threshold = None,
|
|
|
|
Optional<unsigned> Count = None,
|
|
|
|
Optional<bool> AllowPartial = None, Optional<bool> Runtime = None)
|
|
|
|
: LoopPass(ID), ProvidedCount(Count), ProvidedThreshold(Threshold),
|
|
|
|
ProvidedAllowPartial(AllowPartial), ProvidedRuntime(Runtime) {
|
|
|
|
initializeLoopUnrollPass(*PassRegistry::getPassRegistry());
|
|
|
|
}
|
|
|
|
|
|
|
|
Optional<unsigned> ProvidedCount;
|
|
|
|
Optional<unsigned> ProvidedThreshold;
|
|
|
|
Optional<bool> ProvidedAllowPartial;
|
|
|
|
Optional<bool> ProvidedRuntime;
|
|
|
|
|
|
|
|
bool runOnLoop(Loop *L, LPPassManager &) override {
|
|
|
|
if (skipOptnoneFunction(L))
|
|
|
|
return false;
|
|
|
|
|
|
|
|
Function &F = *L->getHeader()->getParent();
|
|
|
|
|
|
|
|
auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
|
|
|
|
LoopInfo *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
|
|
|
|
ScalarEvolution *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
|
|
|
|
const TargetTransformInfo &TTI =
|
|
|
|
getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
|
|
|
|
auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
|
|
|
|
bool PreserveLCSSA = mustPreserveAnalysisID(LCSSAID);
|
|
|
|
|
|
|
|
return tryToUnrollLoop(L, DT, LI, SE, TTI, AC, PreserveLCSSA, ProvidedCount,
|
|
|
|
ProvidedThreshold, ProvidedAllowPartial,
|
|
|
|
ProvidedRuntime);
|
|
|
|
}
|
|
|
|
|
|
|
|
/// This transformation requires natural loop information & requires that
|
|
|
|
/// loop preheaders be inserted into the CFG...
|
|
|
|
///
|
|
|
|
void getAnalysisUsage(AnalysisUsage &AU) const override {
|
|
|
|
AU.addRequired<AssumptionCacheTracker>();
|
|
|
|
AU.addRequired<TargetTransformInfoWrapperPass>();
|
[LPM] Factor all of the loop analysis usage updates into a common helper
routine.
We were getting this wrong in small ways and generally being very
inconsistent about it across loop passes. Instead, let's have a common
place where we do this. One minor downside is that this will require
some analyses like SCEV in more places than they are strictly needed.
However, this seems benign as these analyses are complete no-ops, and
without this consistency we can in many cases end up with the legacy
pass manager scheduling deciding to split up a loop pass pipeline in
order to run the function analysis half-way through. It is very, very
annoying to fix these without just being very pedantic across the board.
The only loop passes I've not updated here are ones that use
AU.setPreservesAll() such as IVUsers (an analysis) and the pass printer.
They seemed less relevant.
With this patch, almost all of the problems in PR24804 around loop pass
pipelines are fixed. The one remaining issue is that we run simplify-cfg
and instcombine in the middle of the loop pass pipeline. We've recently
added some loop variants of these passes that would seem substantially
cleaner to use, but this at least gets us much closer to the previous
state. Notably, the seven loop pass managers is down to three.
I've not updated the loop passes using LoopAccessAnalysis because that
analysis hasn't been fully wired into LoopSimplify/LCSSA, and it isn't
clear that those transforms want to support those forms anyways. They
all run late anyways, so this is harmless. Similarly, LSR is left alone
because it already carefully manages its forms and doesn't need to get
fused into a single loop pass manager with a bunch of other loop passes.
LoopReroll didn't use loop simplified form previously, and I've updated
the test case to match the trivially different output.
Finally, I've also factored all the pass initialization for the passes
that use this technique as well, so that should be done regularly and
reliably.
Thanks to James for the help reviewing and thinking about this stuff,
and Ben for help thinking about it as well!
Differential Revision: http://reviews.llvm.org/D17435
llvm-svn: 261316
2016-02-19 18:45:18 +08:00
|
|
|
// FIXME: Loop passes are required to preserve domtree, and for now we just
|
|
|
|
// recreate dom info if anything gets unrolled.
|
|
|
|
getLoopAnalysisUsage(AU);
|
2016-01-12 13:21:37 +08:00
|
|
|
}
|
|
|
|
};
|
|
|
|
}
|
|
|
|
|
|
|
|
char LoopUnroll::ID = 0;
|
|
|
|
INITIALIZE_PASS_BEGIN(LoopUnroll, "loop-unroll", "Unroll loops", false, false)
|
|
|
|
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
|
[LPM] Factor all of the loop analysis usage updates into a common helper
routine.
We were getting this wrong in small ways and generally being very
inconsistent about it across loop passes. Instead, let's have a common
place where we do this. One minor downside is that this will require
some analyses like SCEV in more places than they are strictly needed.
However, this seems benign as these analyses are complete no-ops, and
without this consistency we can in many cases end up with the legacy
pass manager scheduling deciding to split up a loop pass pipeline in
order to run the function analysis half-way through. It is very, very
annoying to fix these without just being very pedantic across the board.
The only loop passes I've not updated here are ones that use
AU.setPreservesAll() such as IVUsers (an analysis) and the pass printer.
They seemed less relevant.
With this patch, almost all of the problems in PR24804 around loop pass
pipelines are fixed. The one remaining issue is that we run simplify-cfg
and instcombine in the middle of the loop pass pipeline. We've recently
added some loop variants of these passes that would seem substantially
cleaner to use, but this at least gets us much closer to the previous
state. Notably, the seven loop pass managers is down to three.
I've not updated the loop passes using LoopAccessAnalysis because that
analysis hasn't been fully wired into LoopSimplify/LCSSA, and it isn't
clear that those transforms want to support those forms anyways. They
all run late anyways, so this is harmless. Similarly, LSR is left alone
because it already carefully manages its forms and doesn't need to get
fused into a single loop pass manager with a bunch of other loop passes.
LoopReroll didn't use loop simplified form previously, and I've updated
the test case to match the trivially different output.
Finally, I've also factored all the pass initialization for the passes
that use this technique as well, so that should be done regularly and
reliably.
Thanks to James for the help reviewing and thinking about this stuff,
and Ben for help thinking about it as well!
Differential Revision: http://reviews.llvm.org/D17435
llvm-svn: 261316
2016-02-19 18:45:18 +08:00
|
|
|
INITIALIZE_PASS_DEPENDENCY(LoopPass)
|
|
|
|
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
|
2016-01-12 13:21:37 +08:00
|
|
|
INITIALIZE_PASS_END(LoopUnroll, "loop-unroll", "Unroll loops", false, false)
|
|
|
|
|
|
|
|
Pass *llvm::createLoopUnrollPass(int Threshold, int Count, int AllowPartial,
|
|
|
|
int Runtime) {
|
|
|
|
// TODO: It would make more sense for this function to take the optionals
|
|
|
|
// directly, but that's dangerous since it would silently break out of tree
|
|
|
|
// callers.
|
|
|
|
return new LoopUnroll(Threshold == -1 ? None : Optional<unsigned>(Threshold),
|
|
|
|
Count == -1 ? None : Optional<unsigned>(Count),
|
|
|
|
AllowPartial == -1 ? None
|
|
|
|
: Optional<bool>(AllowPartial),
|
|
|
|
Runtime == -1 ? None : Optional<bool>(Runtime));
|
|
|
|
}
|
|
|
|
|
|
|
|
Pass *llvm::createSimpleLoopUnrollPass() {
|
|
|
|
return llvm::createLoopUnrollPass(-1, -1, 0, 0);
|
|
|
|
}
|