As a reminder, a "widenable branch" is the pattern "br i1 (and i1 X, WC()), label %taken, label %untaken" where "WC" is the widenable condition intrinsics. The semantics of such a branch (derived from the semantics of WC) is that a new condition can be added into the condition arbitrarily without violating legality.
Broaden the definition in two ways:
Allow swapped operands to the br (and X, WC()) form
Allow widenable branch w/trivial condition (i.e. true) which takes form of br i1 WC()
The former is just general robustness (e.g. for X = non-instruction this is what instcombine produces). The later is specifically important as partial unswitching of a widenable range check produces exactly this form above the loop.
Differential Revision: https://reviews.llvm.org/D70502
Moving accesses in MemorySSA at InsertionPlace::End, when an instruction is
moved into a block, almost always means insert at the end of the block, but
before the block terminator. This matters when the block terminator is a
MemoryAccess itself (an invoke), and the insertion must be done before
the terminator for the update to be correct.
Insert an additional position: InsertionPlace:BeforeTerminator and update
current usages where this applies.
Resolves PR44027.
This is mostly NFC, but I removed the setting of the guard's calling convention onto the WC call. Why? Because it was untested, and was producing an ill defined output as the declaration's convention wasn't been changed leaving a mismatch which is UB.
This code has never been enabled. While it is tested, it's complicating some refactoring. If we decide to re-implement this, doing it in SimplifyCFG would probably make more sense anyways.
With the widenable condition construct, we have the ability to reason about branches which can be 'widened' (i.e. made to fail more often). We've got a couple o transforms which leverage this. This patch just cleans up the API a bit.
This is prep work for generalizing our definition of a widenable branch slightly. At the moment "br i1 (and A, wc()), ..." is considered widenable, but oddly, neither "br i1 (and wc(), B), ..." or "br i1 wc(), ..." is. That clearly needs addressed, so first, let's centralize the code in one place.
Unswitch (and other loop transforms) like to generate loop exit blocks with unconditional successors, and phi nodes (LCSSA, or simple multiple exiting blocks sharing an exit). Generalize the "likely very rare exit" check slightly to handle this form.
This implements a version of the predicateLoopExits transform from IndVarSimplify extended to exploit widenable conditions - and thus be much wider in scope of legality. The code structure ends up being almost entirely different, so I chose to duplicate this into the LoopPredication pass instead of trying to reuse the code in the IndVars.
The core notions of the transform are as follows:
If we have a widenable condition which controls entry into the loop, we're allowed to widen it arbitrarily. Given that, it's simply a *profitability* question as to what conditions to fold into the widenable branch.
To avoid pass ordering issues, we want to avoid widening cases that would otherwise be dischargeable. Or... widen in a form which can still be discharged. Thus, we phrase the transform as selecting one analyzeable exit from the set of analyzeable exits to keep. This avoids creating pass ordering complexities.
Since none of the above proves that we actually exit through our analyzeable exits - we might exit through something else entirely - we limit ourselves to cases where a) the latch is analyzeable and b) the latch is predicted taken, and c) the exit being removed is statically cold.
Differential Revision: https://reviews.llvm.org/D69830
It was added in 2014 in 732e0aa9fb with one use in Scalarizer.cpp.
That one use was then removed when porting to the new pass manager in
2018 in b6f76002d9.
While the RFC and the desire to get off of static initializers for
cl::opt all still stand, this code is now dead, and I think we should
delete this code until someone is ready to do the migration.
There were many clients of CommandLine.h that were it transitively
through LLVMContext.h, so I cleaned that up in 4c1a1d3cf9.
Reviewers: beanz
Differential Revision: https://reviews.llvm.org/D70280
Summary:
When scalarizing PHI nodes we might try to examine/rewrite
InsertElement nodes in predecessors. If those predecessors
are unreachable from entry, then the IR in those blocks could
have unexpected properties resulting in infinite loops in
Scatterer::operator[].
By simply treating values originating from instructions in
unreachable blocks as undef we do not need to analyse them
further.
This fixes PR41723.
Reviewers: bjope
Reviewed By: bjope
Subscribers: bjope, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70171
This file lists every pass in LLVM, and is included by Pass.h, which is
very popular. Every time we add, remove, or rename a pass in LLVM, it
caused lots of recompilation.
I found this fact by looking at this table, which is sorted by the
number of times a file was changed over the last 100,000 git commits
multiplied by the number of object files that depend on it in the
current checkout:
recompiles touches affected_files header
342380 95 3604 llvm/include/llvm/ADT/STLExtras.h
314730 234 1345 llvm/include/llvm/InitializePasses.h
307036 118 2602 llvm/include/llvm/ADT/APInt.h
213049 59 3611 llvm/include/llvm/Support/MathExtras.h
170422 47 3626 llvm/include/llvm/Support/Compiler.h
162225 45 3605 llvm/include/llvm/ADT/Optional.h
158319 63 2513 llvm/include/llvm/ADT/Triple.h
140322 39 3598 llvm/include/llvm/ADT/StringRef.h
137647 59 2333 llvm/include/llvm/Support/Error.h
131619 73 1803 llvm/include/llvm/Support/FileSystem.h
Before this change, touching InitializePasses.h would cause 1345 files
to recompile. After this change, touching it only causes 550 compiles in
an incremental rebuild.
Reviewers: bkramer, asbirlea, bollu, jdoerfert
Differential Revision: https://reviews.llvm.org/D70211
Currently we have limited support for outer loops with multiple basic
blocks after the inner loop exit. But the current checks for creating
PHIs for loop exit values only assumes the header and latches of the
outer loop. It is better to just skip incoming values defined in the
original inner loops. Those are handled earlier.
Reviewers: efriedma, mcrosier
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D70059
This patch implements a correct, but not terribly useful, transform. In particular, if we have a dynamic alloca in a loop which is guaranteed to execute, and provably not captured, we hoist the alloca out of the loop. The capture tracking is needed so that we can prove that each previous stack region dies before the next one is allocated. The transform decreases the amount of stack allocation needed by a linear factor (e.g. the iteration count of the loop).
Now, I really hope no one is actually using dynamic allocas. As such, why this patch?
Well, the actual problem I'm hoping to make progress on is allocation hoisting. There's a large draft patch out for review (https://reviews.llvm.org/D60056), and this patch was the smallest chunk of testable functionality I could come up with which takes a step vaguely in that direction.
Once this is in, it makes motivating the changes to capture tracking mentioned in TODOs testable. After that, I hope to extend this to trivial malloc free regions (i.e. free dominating all loop exits) and allocation functions for GCed languages.
Differential Revision: https://reviews.llvm.org/D69227
The change itself is straight forward and obvious, but ... there's an existing test checking for exactly the opposite. Both I and Artur think this is simply conservatism in the initial implementation. If anyone bisects a problem to this, a counter example will be very interesting.
Differential Revision: https://reviews.llvm.org/D69907
The basic idea of the transform is to convert variant loop exit conditions into invariant exit conditions by changing the iteration on which the exit is taken when we know that the trip count is unobservable. See the original patch which introduced the code for a more complete explanation.
The individual parts of this have been reviewed, the result has been fuzzed, and then further analyzed by hand, but despite all of that, I will not be suprised to see breakage here. If you see problems, please don't hesitate to revert - though please do provide a test case. The most likely class of issues are latent SCEV bugs and without a reduced test case, I'll be essentially stuck on reducing them.
(Note: A bunch of tests were opted out of the new transform to preserve coverage. That landed in a previous commit to simplify revert cycles if they turn out to be needed.)
Summary:
This patch factors out code to clone instructions -- partly for
readability and partly to facilitate an upcoming patch of my own.
Reviewers: wmi
Subscribers: hiraditya, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D69861
We had a subtle, but nasty bug in our definition of a widenable branch, and thus in the transforms which used that utility. Specifically, we returned true for any branch which included a widenable condition within it's condition, regardless of whether that widenable condition also had other uses.
The problem is that the result of the WC() call is defined to be one particular value. As such, all users must agree as to what that value is. If we widen a branch without also updating *all other users* of the WC in the same way, we have broken the required semantics.
Most of the textual diff is updating existing transforms not to leave dead uses hanging around. They're largely NFC as the dead instructions would be immediately deleted by other passes. The reason to make these changes is so that the transforms preserve the widenable branch form.
In practice, we don't get bitten by this only because it isn't profitable to CSE WC() calls and the lowering pass from guards uses distinct WC calls per branch.
Differential Revision: https://reviews.llvm.org/D69916
This patch fixes two issues noticed by inspection when going to enable the loop predication code in IndVarSimplify.
Issue 1 - Both the LoopPredication transform, and the already on by default optimizeLoopExits transform, modify the exit count of the exits they modify. (either to 0 or Infinity) Looking at the code more closely, this was not reflected into SCEV and we were instead running later transforms with incorrect SCEVs. Fixing this requires forgetting the loop, weakening a too strong assert, and updating SCEV to not pessimize results when a loop is provable untaken. I haven't been able to find a test case to demonstrate the miscompile.
Issue 2 - For modules without a data layout, we can end up with unsized pointer typed exit counts. Just bail out of this case.
I think these are the last two issues which need addressed before we enable this by default. The code has already survived a decent amount of fuzzing without revealing either of the above.
Differential Revision: https://reviews.llvm.org/D69695
Summary:
This patch factors out code to merge a basic block with its sole
successor -- partly for readability and partly to facilitate an
upcoming patch of my own.
Reviewers: wmi
Subscribers: hiraditya, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D69852
Summary:
This patch factors out common code to update the SSA form in
JumpThreading.cpp -- partly for readability and partly to facilitate
an coming patch of my own.
Reviewers: wmi
Subscribers: hiraditya, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D69811
As discussed in https://bugs.llvm.org/show_bug.cgi?id=43870,
this transform is missing a crucial legality check:
the old (non-countable) loop would early-return upon first mismatch,
but there is no such guarantee for bcmp/memcmp.
We'd need to ensure that [PtrA, PtrA+NBytes) and [PtrB, PtrB+NBytes)
are fully dereferenceable memory regions. But that would limit
the transform to constant loop trip counts and would further
cripple it because dereferenceability analysis is *very* partial.
Furthermore, even if all that is done, every single test
would need to be rewritten from scratch.
So let's just give up.
Since SCEV can cache information about location of an instruction, it should be invalidated when the instruction is moved.
There should be similar bug in code sinking part of LICM, it will be fixed in a follow-up change.
Patch Author: Daniil Suchkov
Reviewers: asbirlea, mkazantsev, reames
Reviewed By: asbirlea
Subscribers: hiraditya, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D69370
This phi simplification transform was added with:
D45448
However as shown in PR43802:
https://bugs.llvm.org/show_bug.cgi?id=43802
...we must be careful not to propagate poison when we do the substitution.
There might be some more complicated analysis possible to retain the overflow flag,
but it should always be safe and easy to drop flags (we have similar behavior in
instcombine and other passes).
Differential Revision: https://reviews.llvm.org/D69442
We were already going to all of the trouble of computing maximum constant exit counts for each loop exit, we might as well expose them through the API. The change in IndVars is mostly to demonstrate that the wired up code works, but it als very slightly strengthens the transform. The strengthened case is rather narrow though: it requires one exactly analyzeable exit, one imprecisely analyzeable exit (with the upper bound less than the precise one), and one unanalyzeable exit. I coudn't construct a reasonably stable test case.
This does increase the memory usage of the BackedgeTakenCount by a factor of 2 in the worst case.
I also noticed the loop in IndVars is O(#Exits ^ 2). This doesn't change with this patch. A future patch will cache this result inside of SCEV to avoid requering.
The static analyzer is warning about a potential null dereference, but we should be able to use cast<> directly and if not assert will fire for us.
llvm-svn: 375429
The static analyzer is warning about a potential null dereference, but we should be able to use cast<> directly and if not assert will fire for us.
llvm-svn: 375426
Summary:
When MemCpyOpt is handling aggregate type values, if an instruction (let's call it P) between the targeting load (L) and store (S) clobbers the source pointer of L, it will try to hoist S before P. This process will also hoist S's data dependency instructions.
However, the current implementation has a bug that if one of S's dependency instructions is //also// a user of P, MemCpyOpt will not prevent it from being hoisted above P and cause a use-before-define error. For example, in the newly added test file (i.e. `aggregate-type-crash.ll`), it will try to hoist both `store %my_struct %1, %my_struct* %3` and its dependent, `%3 = bitcast i8* %2 to %my_struct*`, above `%2 = call i8* @my_malloc(%my_struct* %0)`. Creating the following BB:
```
entry:
%1 = bitcast i8* %4 to %my_struct*
%2 = bitcast %my_struct* %1 to i8*
%3 = bitcast %my_struct* %0 to i8*
call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %2, i8* align 4 %3, i64 8, i1 false)
%4 = call i8* @my_malloc(%my_struct* %0)
ret void
```
Where there is a use-before-define error between `%1` and `%4`.
Update: The compiler for the Pony Programming Language [also encounter the same bug](https://github.com/ponylang/ponyc/issues/3140)
Patch by Min-Yih Hsu (myhsu)
Reviewers: eugenis, pcc, dblaikie, dneilson, t.p.northover, lattner
Reviewed By: eugenis
Subscribers: lenary, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66060
llvm-svn: 375403
We can end up with two loop exits whose exit counts are equivalent, but whose textual representation is different and non-obvious. For the sub-case where we have a series of exits which dominate one another (common), eliminate any exits which would iterate *after* a previous exit on the exiting iteration.
As noted in the TODO being removed, I'd always thought this was a good idea, but I've now seen this in a real workload as well.
Interestingly, in review, Nikita pointed out there's let another oppurtunity to leverage SCEV's reasoning. If we kept track of the min of dominanting exits so far, we could discharge exits with EC >= MDE. This is less powerful than the existing transform (since later exits aren't considered), but potentially more powerful for any case where SCEV can prove a >= b, but neither a == b or a > b. I don't have an example to illustrate that oppurtunity, but won't be suprised if we find one and return to handle that case as well.
Differential Revision: https://reviews.llvm.org/D69009
llvm-svn: 375379
Summary:
CVP, unlike InstCombine, does not run till exaustion.
It only does a single pass.
When dealing with those special binops, if we prove that they can
safely be demoted into their usual binop form,
we do set the no-wrap we deduced. But when dealing with usual binops,
we try to deduce both no-wraps.
So if we convert e.g. @llvm.uadd.with.overflow() to `add nuw`,
we won't attempt to check whether it can be `add nuw nsw`.
This patch proposes to call `processBinOp()` on newly-created binop,
which is identical to what we do for div/rem already.
Reviewers: nikic, spatel, reames
Reviewed By: nikic
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D69183
llvm-svn: 375273
Summary:
It looks like this is the only missing statistic in the CVP pass.
Since we prove NSW and NUW separately i'd think we should count them separately too.
Reviewers: nikic, spatel, reames
Reviewed By: spatel
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D68740
llvm-svn: 375230
In the process of writing D69009, I realized we have two distinct sets of invariants within this single function, and basically no shared logic. The optimize loop exit transforms (including the new one in D69009) only care about *analyzeable* exits. Loop predication, on the other hand, has to reason about *all* exits. At the moment, we have the property (due to the requirement for an exact btc) that all exits are analyzeable, but that will likely change in the future as we add widenable condition support.
llvm-svn: 375138
The static analyzer is warning about a potential null dereference, but we should be able to use cast<> directly and if not assert will fire for us.
llvm-svn: 375103
We can't normally stumble into that assertion because a tautological
*conditional* `br` in loop body is required, one that always
branches to loop latch. But that should have been always folded
to an unconditional branch before we get it.
But that is not guaranteed if the pass is run standalone.
So let's just promote the assertion into a proper check.
Fixes https://bugs.llvm.org/show_bug.cgi?id=43687
llvm-svn: 375100
Summary:
There are two cases where a block is merged into its predecessor and the
MergeBlockIntoPredecessor API is not used. Update the API so it can be
reused in the other cases, in order to avoid code duplication.
Cleanup motivated by D68659.
Reviewers: chandlerc, sanjoy.google, george.burgess.iv
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D68670
llvm-svn: 375050
The problem is that we can have two loop exits, 'a' and 'b', where 'a' and 'b' would exit at the same iteration, 'a' precedes 'b' along some path, and 'b' is predicated while 'a' is not. In this case (see the previously submitted test case), we causing the loop to exit through 'b' whereas it should have exited through 'a'.
This only applies to loop exits where the exit counts are not provably inequal, but that isn't as much of a restriction as it appears. If we could order the exit counts, we'd have already removed one of the two exits. In theory, we might be able to prove inequality w/o ordering, but I didn't really explore that piece. Instead, I went for the obvious restriction and ensured we didn't predicate exits following non-predicateable exits.
Credit goes to Evgeny Brevnov for figuring out the problematic case. Fuzzing probably also found it (failures seen), but due to some silly infrastructure problems I hadn't gotten to the results before Evgeny hand reduced it from a benchmark (he manually enabled the transform). Once this is fixed, I'll try to filter through the fuzzer failures to see if there's anything additional lurking.
Differential Revision https://reviews.llvm.org/D68956
llvm-svn: 375038
Check that a call has an attached MemoryAccess before calling
getClobbering on the instruction.
If no access is attached, the instruction does not access memory.
Resolves PR43441.
llvm-svn: 374920
As reported by Joerg Sonnenberger in IRC, for 32-bit systems,
where pointer and size_t are 32-bit, if you use 64-bit-wide variable
in the loop, you could end up with loop exit count being of the type
wider than the size_t. Now, i'm not sure if we can produce `bcmp`
from that (just truncate?), but we certainly should not assert/miscompile.
llvm-svn: 374811
Add a pass to lower is.constant and objectsize intrinsics
This pass lowers is.constant and objectsize intrinsics not simplified by
earlier constant folding, i.e. if the object given is not constant or if
not using the optimized pass chain. The result is recursively simplified
and constant conditionals are pruned, so that dead blocks are removed
even for -O0. This allows inline asm blocks with operand constraints to
work all the time.
The new pass replaces the existing lowering in the codegen-prepare pass
and fallbacks in SDAG/GlobalISEL and FastISel. The latter now assert
on the intrinsics.
Differential Revision: https://reviews.llvm.org/D65280
llvm-svn: 374784
This pass lowers is.constant and objectsize intrinsics not simplified by
earlier constant folding, i.e. if the object given is not constant or if
not using the optimized pass chain. The result is recursively simplified
and constant conditionals are pruned, so that dead blocks are removed
even for -O0. This allows inline asm blocks with operand constraints to
work all the time.
The new pass replaces the existing lowering in the codegen-prepare pass
and fallbacks in SDAG/GlobalISEL and FastISel. The latter now assert
on the intrinsics.
Differential Revision: https://reviews.llvm.org/D65280
llvm-svn: 374743
Summary:
If the underlying alloca did not change, we do not necessarily need new
lifetime markers. This patch adds a check and reuses the old ones if
possible.
Reviewers: reames, ssarda, t.p.northover, hfinkel
Subscribers: hiraditya, bollu, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D68900
llvm-svn: 374692
Summary:
This is a recommit, this originally landed in rL370454 but was
subsequently reverted in rL370788 due to
https://bugs.llvm.org/show_bug.cgi?id=43206
The reduced testcase was added to bcmp-negative-tests.ll
as @pr43206_different_loops - we must ensure that the SCEV's
we got are both for the same loop we are currently investigating.
Original commit message:
@mclow.lists brought up this issue up in IRC.
It is a reasonably common problem to compare some two values for equality.
Those may be just some integers, strings or arrays of integers.
In C, there is `memcmp()`, `bcmp()` functions.
In C++, there exists `std::equal()` algorithm.
One can also write that function manually.
libstdc++'s `std::equal()` is specialized to directly call `memcmp()` for
various types, but not `std::byte` from C++2a. https://godbolt.org/z/mx2ejJ
libc++ does not do anything like that, it simply relies on simple C++'s
`operator==()`. https://godbolt.org/z/er0Zwf (GOOD!)
So likely, there exists a certain performance opportunities.
Let's compare performance of naive `std::equal()` (no `memcmp()`) with one that
is using `memcmp()` (in this case, compiled with modified compiler). {F8768213}
```
#include <algorithm>
#include <cmath>
#include <cstdint>
#include <iterator>
#include <limits>
#include <random>
#include <type_traits>
#include <utility>
#include <vector>
#include "benchmark/benchmark.h"
template <class T>
bool equal(T* a, T* a_end, T* b) noexcept {
for (; a != a_end; ++a, ++b) {
if (*a != *b) return false;
}
return true;
}
template <typename T>
std::vector<T> getVectorOfRandomNumbers(size_t count) {
std::random_device rd;
std::mt19937 gen(rd());
std::uniform_int_distribution<T> dis(std::numeric_limits<T>::min(),
std::numeric_limits<T>::max());
std::vector<T> v;
v.reserve(count);
std::generate_n(std::back_inserter(v), count,
[&dis, &gen]() { return dis(gen); });
assert(v.size() == count);
return v;
}
struct Identical {
template <typename T>
static std::pair<std::vector<T>, std::vector<T>> Gen(size_t count) {
auto Tmp = getVectorOfRandomNumbers<T>(count);
return std::make_pair(Tmp, std::move(Tmp));
}
};
struct InequalHalfway {
template <typename T>
static std::pair<std::vector<T>, std::vector<T>> Gen(size_t count) {
auto V0 = getVectorOfRandomNumbers<T>(count);
auto V1 = V0;
V1[V1.size() / size_t(2)]++; // just change the value.
return std::make_pair(std::move(V0), std::move(V1));
}
};
template <class T, class Gen>
void BM_bcmp(benchmark::State& state) {
const size_t Length = state.range(0);
const std::pair<std::vector<T>, std::vector<T>> Data =
Gen::template Gen<T>(Length);
const std::vector<T>& a = Data.first;
const std::vector<T>& b = Data.second;
assert(a.size() == Length && b.size() == a.size());
benchmark::ClobberMemory();
benchmark::DoNotOptimize(a);
benchmark::DoNotOptimize(a.data());
benchmark::DoNotOptimize(b);
benchmark::DoNotOptimize(b.data());
for (auto _ : state) {
const bool is_equal = equal(a.data(), a.data() + a.size(), b.data());
benchmark::DoNotOptimize(is_equal);
}
state.SetComplexityN(Length);
state.counters["eltcnt"] =
benchmark::Counter(Length, benchmark::Counter::kIsIterationInvariant);
state.counters["eltcnt/sec"] =
benchmark::Counter(Length, benchmark::Counter::kIsIterationInvariantRate);
const size_t BytesRead = 2 * sizeof(T) * Length;
state.counters["bytes_read/iteration"] =
benchmark::Counter(BytesRead, benchmark::Counter::kDefaults,
benchmark::Counter::OneK::kIs1024);
state.counters["bytes_read/sec"] = benchmark::Counter(
BytesRead, benchmark::Counter::kIsIterationInvariantRate,
benchmark::Counter::OneK::kIs1024);
}
template <typename T>
static void CustomArguments(benchmark::internal::Benchmark* b) {
const size_t L2SizeBytes = []() {
for (const benchmark::CPUInfo::CacheInfo& I :
benchmark::CPUInfo::Get().caches) {
if (I.level == 2) return I.size;
}
return 0;
}();
// What is the largest range we can check to always fit within given L2 cache?
const size_t MaxLen = L2SizeBytes / /*total bufs*/ 2 /
/*maximal elt size*/ sizeof(T) / /*safety margin*/ 2;
b->RangeMultiplier(2)->Range(1, MaxLen)->Complexity(benchmark::oN);
}
BENCHMARK_TEMPLATE(BM_bcmp, uint8_t, Identical)
->Apply(CustomArguments<uint8_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint16_t, Identical)
->Apply(CustomArguments<uint16_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint32_t, Identical)
->Apply(CustomArguments<uint32_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint64_t, Identical)
->Apply(CustomArguments<uint64_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint8_t, InequalHalfway)
->Apply(CustomArguments<uint8_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint16_t, InequalHalfway)
->Apply(CustomArguments<uint16_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint32_t, InequalHalfway)
->Apply(CustomArguments<uint32_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint64_t, InequalHalfway)
->Apply(CustomArguments<uint64_t>);
```
{F8768210}
```
$ ~/src/googlebenchmark/tools/compare.py --no-utest benchmarks build-{old,new}/test/llvm-bcmp-bench
RUNNING: build-old/test/llvm-bcmp-bench --benchmark_out=/tmp/tmpb6PEUx
2019-04-25 21:17:11
Running build-old/test/llvm-bcmp-bench
Run on (8 X 4000 MHz CPU s)
CPU Caches:
L1 Data 16K (x8)
L1 Instruction 64K (x4)
L2 Unified 2048K (x4)
L3 Unified 8192K (x1)
Load Average: 0.65, 3.90, 4.14
---------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
---------------------------------------------------------------------------------------------------
<...>
BM_bcmp<uint8_t, Identical>/512000 432131 ns 432101 ns 1613 bytes_read/iteration=1000k bytes_read/sec=2.20706G/s eltcnt=825.856M eltcnt/sec=1.18491G/s
BM_bcmp<uint8_t, Identical>_BigO 0.86 N 0.86 N
BM_bcmp<uint8_t, Identical>_RMS 8 % 8 %
<...>
BM_bcmp<uint16_t, Identical>/256000 161408 ns 161409 ns 4027 bytes_read/iteration=1000k bytes_read/sec=5.90843G/s eltcnt=1030.91M eltcnt/sec=1.58603G/s
BM_bcmp<uint16_t, Identical>_BigO 0.67 N 0.67 N
BM_bcmp<uint16_t, Identical>_RMS 25 % 25 %
<...>
BM_bcmp<uint32_t, Identical>/128000 81497 ns 81488 ns 8415 bytes_read/iteration=1000k bytes_read/sec=11.7032G/s eltcnt=1077.12M eltcnt/sec=1.57078G/s
BM_bcmp<uint32_t, Identical>_BigO 0.71 N 0.71 N
BM_bcmp<uint32_t, Identical>_RMS 42 % 42 %
<...>
BM_bcmp<uint64_t, Identical>/64000 50138 ns 50138 ns 10909 bytes_read/iteration=1000k bytes_read/sec=19.0209G/s eltcnt=698.176M eltcnt/sec=1.27647G/s
BM_bcmp<uint64_t, Identical>_BigO 0.84 N 0.84 N
BM_bcmp<uint64_t, Identical>_RMS 27 % 27 %
<...>
BM_bcmp<uint8_t, InequalHalfway>/512000 192405 ns 192392 ns 3638 bytes_read/iteration=1000k bytes_read/sec=4.95694G/s eltcnt=1.86266G eltcnt/sec=2.66124G/s
BM_bcmp<uint8_t, InequalHalfway>_BigO 0.38 N 0.38 N
BM_bcmp<uint8_t, InequalHalfway>_RMS 3 % 3 %
<...>
BM_bcmp<uint16_t, InequalHalfway>/256000 127858 ns 127860 ns 5477 bytes_read/iteration=1000k bytes_read/sec=7.45873G/s eltcnt=1.40211G eltcnt/sec=2.00219G/s
BM_bcmp<uint16_t, InequalHalfway>_BigO 0.50 N 0.50 N
BM_bcmp<uint16_t, InequalHalfway>_RMS 0 % 0 %
<...>
BM_bcmp<uint32_t, InequalHalfway>/128000 49140 ns 49140 ns 14281 bytes_read/iteration=1000k bytes_read/sec=19.4072G/s eltcnt=1.82797G eltcnt/sec=2.60478G/s
BM_bcmp<uint32_t, InequalHalfway>_BigO 0.40 N 0.40 N
BM_bcmp<uint32_t, InequalHalfway>_RMS 18 % 18 %
<...>
BM_bcmp<uint64_t, InequalHalfway>/64000 32101 ns 32099 ns 21786 bytes_read/iteration=1000k bytes_read/sec=29.7101G/s eltcnt=1.3943G eltcnt/sec=1.99381G/s
BM_bcmp<uint64_t, InequalHalfway>_BigO 0.50 N 0.50 N
BM_bcmp<uint64_t, InequalHalfway>_RMS 1 % 1 %
RUNNING: build-new/test/llvm-bcmp-bench --benchmark_out=/tmp/tmpQ46PP0
2019-04-25 21:19:29
Running build-new/test/llvm-bcmp-bench
Run on (8 X 4000 MHz CPU s)
CPU Caches:
L1 Data 16K (x8)
L1 Instruction 64K (x4)
L2 Unified 2048K (x4)
L3 Unified 8192K (x1)
Load Average: 1.01, 2.85, 3.71
---------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
---------------------------------------------------------------------------------------------------
<...>
BM_bcmp<uint8_t, Identical>/512000 18593 ns 18590 ns 37565 bytes_read/iteration=1000k bytes_read/sec=51.2991G/s eltcnt=19.2333G eltcnt/sec=27.541G/s
BM_bcmp<uint8_t, Identical>_BigO 0.04 N 0.04 N
BM_bcmp<uint8_t, Identical>_RMS 37 % 37 %
<...>
BM_bcmp<uint16_t, Identical>/256000 18950 ns 18948 ns 37223 bytes_read/iteration=1000k bytes_read/sec=50.3324G/s eltcnt=9.52909G eltcnt/sec=13.511G/s
BM_bcmp<uint16_t, Identical>_BigO 0.08 N 0.08 N
BM_bcmp<uint16_t, Identical>_RMS 34 % 34 %
<...>
BM_bcmp<uint32_t, Identical>/128000 18627 ns 18627 ns 37895 bytes_read/iteration=1000k bytes_read/sec=51.198G/s eltcnt=4.85056G eltcnt/sec=6.87168G/s
BM_bcmp<uint32_t, Identical>_BigO 0.16 N 0.16 N
BM_bcmp<uint32_t, Identical>_RMS 35 % 35 %
<...>
BM_bcmp<uint64_t, Identical>/64000 18855 ns 18855 ns 37458 bytes_read/iteration=1000k bytes_read/sec=50.5791G/s eltcnt=2.39731G eltcnt/sec=3.3943G/s
BM_bcmp<uint64_t, Identical>_BigO 0.32 N 0.32 N
BM_bcmp<uint64_t, Identical>_RMS 33 % 33 %
<...>
BM_bcmp<uint8_t, InequalHalfway>/512000 9570 ns 9569 ns 73500 bytes_read/iteration=1000k bytes_read/sec=99.6601G/s eltcnt=37.632G eltcnt/sec=53.5046G/s
BM_bcmp<uint8_t, InequalHalfway>_BigO 0.02 N 0.02 N
BM_bcmp<uint8_t, InequalHalfway>_RMS 29 % 29 %
<...>
BM_bcmp<uint16_t, InequalHalfway>/256000 9547 ns 9547 ns 74343 bytes_read/iteration=1000k bytes_read/sec=99.8971G/s eltcnt=19.0318G eltcnt/sec=26.8159G/s
BM_bcmp<uint16_t, InequalHalfway>_BigO 0.04 N 0.04 N
BM_bcmp<uint16_t, InequalHalfway>_RMS 29 % 29 %
<...>
BM_bcmp<uint32_t, InequalHalfway>/128000 9396 ns 9394 ns 73521 bytes_read/iteration=1000k bytes_read/sec=101.518G/s eltcnt=9.41069G eltcnt/sec=13.6255G/s
BM_bcmp<uint32_t, InequalHalfway>_BigO 0.08 N 0.08 N
BM_bcmp<uint32_t, InequalHalfway>_RMS 30 % 30 %
<...>
BM_bcmp<uint64_t, InequalHalfway>/64000 9499 ns 9498 ns 73802 bytes_read/iteration=1000k bytes_read/sec=100.405G/s eltcnt=4.72333G eltcnt/sec=6.73808G/s
BM_bcmp<uint64_t, InequalHalfway>_BigO 0.16 N 0.16 N
BM_bcmp<uint64_t, InequalHalfway>_RMS 28 % 28 %
Comparing build-old/test/llvm-bcmp-bench to build-new/test/llvm-bcmp-bench
Benchmark Time CPU Time Old Time New CPU Old CPU New
---------------------------------------------------------------------------------------------------------------------------------------
<...>
BM_bcmp<uint8_t, Identical>/512000 -0.9570 -0.9570 432131 18593 432101 18590
<...>
BM_bcmp<uint16_t, Identical>/256000 -0.8826 -0.8826 161408 18950 161409 18948
<...>
BM_bcmp<uint32_t, Identical>/128000 -0.7714 -0.7714 81497 18627 81488 18627
<...>
BM_bcmp<uint64_t, Identical>/64000 -0.6239 -0.6239 50138 18855 50138 18855
<...>
BM_bcmp<uint8_t, InequalHalfway>/512000 -0.9503 -0.9503 192405 9570 192392 9569
<...>
BM_bcmp<uint16_t, InequalHalfway>/256000 -0.9253 -0.9253 127858 9547 127860 9547
<...>
BM_bcmp<uint32_t, InequalHalfway>/128000 -0.8088 -0.8088 49140 9396 49140 9394
<...>
BM_bcmp<uint64_t, InequalHalfway>/64000 -0.7041 -0.7041 32101 9499 32099 9498
```
What can we tell from the benchmark?
* Performance of naive equality check somewhat improves with element size,
maxing out at eltcnt/sec=1.58603G/s for uint16_t, or bytes_read/sec=19.0209G/s
for uint64_t. I think, that instability implies performance problems.
* Performance of `memcmp()`-aware benchmark always maxes out at around
bytes_read/sec=51.2991G/s for every type. That is 2.6x the throughput of the
naive variant!
* eltcnt/sec metric for the `memcmp()`-aware benchmark maxes out at
eltcnt/sec=27.541G/s for uint8_t (was: eltcnt/sec=1.18491G/s, so 24x) and
linearly decreases with element size.
For uint64_t, it's ~4x+ the elements/second.
* The call obvious is more pricey than the loop, with small element count.
As it can be seen from the full output {F8768210}, the `memcmp()` is almost
universally worse, independent of the element size (and thus buffer size) when
element count is less than 8.
So all in all, bcmp idiom does indeed pose untapped performance headroom.
This diff does implement said idiom recognition. I think a reasonable test
coverage is present, but do tell if there is anything obvious missing.
Now, quality. This does succeed to build and pass the test-suite, at least
without any non-bundled elements. {F8768216} {F8768217}
This transform fires 91 times:
```
$ /build/test-suite/utils/compare.py -m loop-idiom.NumBCmp result-new.json
Tests: 1149
Metric: loop-idiom.NumBCmp
Program result-new
MultiSourc...Benchmarks/7zip/7zip-benchmark 79.00
MultiSource/Applications/d/make_dparser 3.00
SingleSource/UnitTests/vla 2.00
MultiSource/Applications/Burg/burg 1.00
MultiSourc.../Applications/JM/lencod/lencod 1.00
MultiSource/Applications/lemon/lemon 1.00
MultiSource/Benchmarks/Bullet/bullet 1.00
MultiSourc...e/Benchmarks/MallocBench/gs/gs 1.00
MultiSourc...gs-C/TimberWolfMC/timberwolfmc 1.00
MultiSourc...Prolangs-C/simulator/simulator 1.00
```
The size changes are:
I'm not sure what's going on with SingleSource/UnitTests/vla.test yet, did not look.
```
$ /build/test-suite/utils/compare.py -m size..text result-{old,new}.json --filter-hash
Tests: 1149
Same hash: 907 (filtered out)
Remaining: 242
Metric: size..text
Program result-old result-new diff
test-suite...ingleSource/UnitTests/vla.test 753.00 833.00 10.6%
test-suite...marks/7zip/7zip-benchmark.test 1001697.00 966657.00 -3.5%
test-suite...ngs-C/simulator/simulator.test 32369.00 32321.00 -0.1%
test-suite...plications/d/make_dparser.test 89585.00 89505.00 -0.1%
test-suite...ce/Applications/Burg/burg.test 40817.00 40785.00 -0.1%
test-suite.../Applications/lemon/lemon.test 47281.00 47249.00 -0.1%
test-suite...TimberWolfMC/timberwolfmc.test 250065.00 250113.00 0.0%
test-suite...chmarks/MallocBench/gs/gs.test 149889.00 149873.00 -0.0%
test-suite...ications/JM/lencod/lencod.test 769585.00 769569.00 -0.0%
test-suite.../Benchmarks/Bullet/bullet.test 770049.00 770049.00 0.0%
test-suite...HMARK_ANISTROPIC_DIFFUSION/128 NaN NaN nan%
test-suite...HMARK_ANISTROPIC_DIFFUSION/256 NaN NaN nan%
test-suite...CHMARK_ANISTROPIC_DIFFUSION/64 NaN NaN nan%
test-suite...CHMARK_ANISTROPIC_DIFFUSION/32 NaN NaN nan%
test-suite...ENCHMARK_BILATERAL_FILTER/64/4 NaN NaN nan%
Geomean difference nan%
result-old result-new diff
count 1.000000e+01 10.00000 10.000000
mean 3.152090e+05 311695.40000 0.006749
std 3.790398e+05 372091.42232 0.036605
min 7.530000e+02 833.00000 -0.034981
25% 4.243300e+04 42401.00000 -0.000866
50% 1.197370e+05 119689.00000 -0.000392
75% 6.397050e+05 639705.00000 -0.000005
max 1.001697e+06 966657.00000 0.106242
```
I don't have timings though.
And now to the code. The basic idea is to completely replace the whole loop.
If we can't fully kill it, don't transform.
I have left one or two comments in the code, so hopefully it can be understood.
Also, there is a few TODO's that i have left for follow-ups:
* widening of `memcmp()`/`bcmp()`
* step smaller than the comparison size
* Metadata propagation
* more than two blocks as long as there is still a single backedge?
* ???
Reviewers: reames, fhahn, mkazantsev, chandlerc, craig.topper, courbet
Reviewed By: courbet
Subscribers: miyuki, hiraditya, xbolva00, nikic, jfb, gchatelet, courbet, llvm-commits, mclow.lists
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D61144
llvm-svn: 374662
In loop-vectorize, interleave count and vector factor depend on target register number. Currently, it does not
estimate different register pressure for different register class separately(especially for scalar type,
float type should not be on the same position with int type), so it's not accurate. Specifically,
it causes too many times interleaving/unrolling, result in too many register spills in loop body and hurting performance.
So we need classify the register classes in IR level, and importantly these are abstract register classes,
and are not the target register class of backend provided in td file. It's used to establish the mapping between
the types of IR values and the number of simultaneous live ranges to which we'd like to limit for some set of those types.
For example, POWER target, register num is special when VSX is enabled. When VSX is enabled, the number of int scalar register is 32(GPR),
float is 64(VSR), but for int and float vector register both are 64(VSR). So there should be 2 kinds of register class when vsx is enabled,
and 3 kinds of register class when VSX is NOT enabled.
It runs on POWER target, it makes big(+~30%) performance improvement in one specific bmk(503.bwaves_r) of spec2017 and no other obvious degressions.
Differential revision: https://reviews.llvm.org/D67148
llvm-svn: 374634
This is really a known bits style transformation, but known bits isn't context sensitive. The particular case which comes up happens to involve a range which allows range based reasoning to eliminate the mask pattern, so handle that case specifically in CVP.
InstCombine likes to generate the mask-by-low-bits pattern when widening an arithmetic expression which includes a zext in the middle.
Differential Revision: https://reviews.llvm.org/D68811
llvm-svn: 374506
Summary:
The rule for the moveAllAfterMergeBlocks API si for all instructions
from `From` to have been moved to `To`, while keeping the CFG edges (and
block terminators) unchanged.
Update all the callsites for moveAllAfterMergeBlocks to follow this.
Pending follow-up: since the same behavior is needed everytime, merge
all callsites into one. The common denominator may be the call to
`MergeBlockIntoPredecessor`.
Resolves PR43569.
Reviewers: george.burgess.iv
Subscribers: Prazek, sanjoy.google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D68659
llvm-svn: 374177
Also Revert "[LoopVectorize] Fix non-debug builds after rL374017"
This reverts commit 9f41deccc0.
This reverts commit 18b6fe07bc.
The patch is breaking PowerPC internal build, checked with author, reverting
on behalf of him for now due to timezone.
llvm-svn: 374091
* Adds a TypeSize struct to represent the known minimum size of a type
along with a flag to indicate that the runtime size is a integer multiple
of that size
* Converts existing size query functions from Type.h and DataLayout.h to
return a TypeSize result
* Adds convenience methods (including a transparent conversion operator
to uint64_t) so that most existing code 'just works' as if the return
values were still scalars.
* Uses the new size queries along with ElementCount to ensure that all
supported instructions used with scalable vectors can be constructed
in IR.
Reviewers: hfinkel, lattner, rkruppe, greened, rovka, rengolin, sdesmalen
Reviewed By: rovka, sdesmalen
Differential Revision: https://reviews.llvm.org/D53137
llvm-svn: 374042
Summary: LoopRotate is a loop pass and SE should always be available.
Reviewers: anemet, asbirlea
Reviewed By: asbirlea
Differential Revision: https://reviews.llvm.org/D68573
llvm-svn: 374026
In loop-vectorize, interleave count and vector factor depend on target register number. Currently, it does not
estimate different register pressure for different register class separately(especially for scalar type,
float type should not be on the same position with int type), so it's not accurate. Specifically,
it causes too many times interleaving/unrolling, result in too many register spills in loop body and hurting performance.
So we need classify the register classes in IR level, and importantly these are abstract register classes,
and are not the target register class of backend provided in td file. It's used to establish the mapping between
the types of IR values and the number of simultaneous live ranges to which we'd like to limit for some set of those types.
For example, POWER target, register num is special when VSX is enabled. When VSX is enabled, the number of int scalar register is 32(GPR),
float is 64(VSR), but for int and float vector register both are 64(VSR). So there should be 2 kinds of register class when vsx is enabled,
and 3 kinds of register class when VSX is NOT enabled.
It runs on POWER target, it makes big(+~30%) performance improvement in one specific bmk(503.bwaves_r) of spec2017 and no other obvious degressions.
Differential revision: https://reviews.llvm.org/D67148
llvm-svn: 374017
Doing this makes MSVC complain that `empty(someRange)` could refer to
either C++17's std::empty or LLVM's llvm::empty, which previously we
avoided via SFINAE because std::empty is defined in terms of an empty
member rather than begin and end. So, switch callers over to the new
method as it is added.
https://reviews.llvm.org/D68439
llvm-svn: 373935
There are no users that pass in LazyValueInfo, so we can simplify the
function a bit.
Reviewers: brzycki, asbirlea, davide
Reviewed By: davide
Differential Revision: https://reviews.llvm.org/D68297
llvm-svn: 373488
The static analyzer is warning about a potential null dereference, but we should be able to use cast<PHINode> directly and if not assert will fire for us.
llvm-svn: 373481
This patch implements a variation of a well known techniques for JIT compilers - we have an implementation in tree as LoopPredication - but with an interesting twist. This version does not assume the ability to execute a path which wasn't taken in the original program (such as a guard or widenable.condition intrinsic). The benefit is that this works for arbitrary IR from any frontend (including C/C++/Fortran). The tradeoff is that it's restricted to read only loops without implicit exits.
This builds on SCEV, and can thus eliminate the loop varying portion of the any early exit where all exits are understandable by SCEV. A key advantage is that fixing deficiency exposed in SCEV - already found one while writing test cases - will also benefit all of full redundancy elimination (and most other loop transforms).
I haven't seen anything in the literature which quite matches this. Given that, I'm not entirely sure that keeping the name "loop predication" is helpful. Anyone have suggestions for a better name? This is analogous to partial redundancy elimination - since we remove the condition flowing around the backedge - and has some parallels to our existing transforms which try to make conditions invariant in loops.
Factoring wise, I chose to put this in IndVarSimplify since it's a generally applicable to all workloads. I could split this off into it's own pass, but we'd then probably want to add that new pass every place we use IndVars. One solid argument for splitting it off into it's own pass is that this transform is "too good". It breaks a huge number of existing IndVars test cases as they tend to be simple read only loops. At the moment, I've opted it off by default, but if we add this to IndVars and enable, we'll have to update around 20 test files to add side effects or disable this transform.
Near term plan is to fuzz this extensively while off by default, reflect and discuss on the factoring issue mentioned just above, and then enable by default. I also need to give some though to supporting widenable conditions in this framing.
Differential Revision: https://reviews.llvm.org/D67408
llvm-svn: 373351
Summary:
The BasicBlockManager is potentially broken and should not be used.
Replace all uses of the BasicBlockPass with a FunctionBlockPass+loop on
blocks.
Reviewers: chandlerc
Subscribers: jholewinski, sanjoy.google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D68234
llvm-svn: 373254
If we happen to have the same div in two basic blocks,
and in one of those we also happen to have the rem part,
we'd match the div-rem pair, but the wrong ones.
So let's drop overly-ambiguous assert.
Fixes https://bugs.llvm.org/show_bug.cgi?id=43500
llvm-svn: 373167
The static analyzer is warning about a potential null dereference, but we should be able to use cast<StructType> directly and if not assert will fire for us.
llvm-svn: 373095
Summary:
This patch extends the current capabilities in loop fusion to fuse guarded loops
(as defined in https://reviews.llvm.org/D63885). The patch adds the necessary
safety checks to ensure that it safe to fuse the guarded loops (control flow
equivalent, no intervening code, and same guard conditions). It also provides an
alternative method to perform the actual fusion of guarded loops. The mechanics
to fuse guarded loops are slightly different then fusing non-guarded loops, so I
opted to keep them separate methods. I will be cleaning this up in later
patches, and hope to converge on a single method to fuse both guarded and
non-guarded loops, but for now I think the review will be easier to keep them
separate.
Reviewers: jdoerfert, Meinersbur, dmgreen, etiotto, Whitney
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65464
llvm-svn: 373018
For a runtime loop if we can compute its trip count upperbound:
Don't unroll if:
1. loop is not guaranteed to run either zero or upperbound iterations; and
2. trip count upperbound is less than UnrollMaxUpperBound
Unless user or TTI asked to do so.
If unrolling, limit unroll factor to loop's trip count upperbound.
Differential Revision: https://reviews.llvm.org/D62989
Change-Id: I6083c46a9d98b2e22cd855e60523fdc5a4929c73
llvm-svn: 373017
For large functions, verifying the whole function after each loop takes
non-linear time.
Differential Revision: https://reviews.llvm.org/D67571
llvm-svn: 372924
While Promoting alloca instruction of Vector Type,
Check total size in bits of its slices too.
If they don't match, don't promote the alloca instruction.
Bug : https://bugs.llvm.org/show_bug.cgi?id=42585
llvm-svn: 372480
Summary:
FlattenCFG may erase unnecessary blocks, which also invalidates iterators to those erased blocks.
Before this patch, `iterativelyFlattenCFG` could try to increment a BB iterator after that BB has been removed and crash.
This patch makes FlattenCFGPass use `WeakVH` to skip over erased blocks.
Reviewers: dblaikie, tstellar, davide, sanjoy, asbirlea, grosser
Reviewed By: asbirlea
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D67672
llvm-svn: 372347
In the example from:
https://bugs.llvm.org/show_bug.cgi?id=38502
...we hit infinite looping/crashing because we have non-standard IR -
an instruction operand is used before defined.
This and other unusual constructs are allowed in unreachable blocks,
so avoid the problem by using DominatorTree to step around landmines.
Differential Revision: https://reviews.llvm.org/D67766
llvm-svn: 372339
Add an ability to specify the max full unroll count for LoopUnrollPass pass
in pass options.
Reviewers: fhahn, fedor.sergeev
Reviewed By: fedor.sergeev
Subscribers: hiraditya, zzheng, dmgreen, llvm-commits
Differential Revision: https://reviews.llvm.org/D67701
llvm-svn: 372305
We use `< UP.Threshold` later on, so we should use LoopSize + 1, to
allow unrolling if the result won't exceed to loop size.
Fixes PR43305.
Reviewers: efriedma, dmgreen, paquette
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D67594
llvm-svn: 372084
This patch contains the basic functionality for reporting potentially
incorrect usage of __builtin_expect() by comparing the developer's
annotation against a collected PGO profile. A more detailed proposal and
discussion appears on the CFE-dev mailing list
(http://lists.llvm.org/pipermail/cfe-dev/2019-July/062971.html) and a
prototype of the initial frontend changes appear here in D65300
We revised the work in D65300 by moving the misexpect check into the
LLVM backend, and adding support for IR and sampling based profiles, in
addition to frontend instrumentation.
We add new misexpect metadata tags to those instructions directly
influenced by the llvm.expect intrinsic (branch, switch, and select)
when lowering the intrinsics. The misexpect metadata contains
information about the expected target of the intrinsic so that we can
check against the correct PGO counter when emitting diagnostics, and the
compiler's values for the LikelyBranchWeight and UnlikelyBranchWeight.
We use these branch weight values to determine when to emit the
diagnostic to the user.
A future patch should address the comment at the top of
LowerExpectIntrisic.cpp to hoist the LikelyBranchWeight and
UnlikelyBranchWeight values into a shared space that can be accessed
outside of the LowerExpectIntrinsic pass. Once that is done, the
misexpect metadata can be updated to be smaller.
In the long term, it is possible to reconstruct portions of the
misexpect metadata from the existing profile data. However, we have
avoided this to keep the code simple, and because some kind of metadata
tag will be required to identify which branch/switch/select instructions
are influenced by the use of llvm.expect
Patch By: paulkirth
Differential Revision: https://reviews.llvm.org/D66324
llvm-svn: 371635
This reverts commit r371584. It introduced a dependency from compiler-rt
to llvm/include/ADT, which is problematic for multiple reasons.
One is that it is a novel dependency edge, which needs cross-compliation
machinery for llvm/include/ADT (yes, it is true that right now
compiler-rt included only header-only libraries, however, if we allow
compiler-rt to depend on anything from ADT, other libraries will
eventually get used).
Secondly, depending on ADT from compiler-rt exposes ADT symbols from
compiler-rt, which would cause ODR violations when Clang is built with
the profile library.
llvm-svn: 371598
Currently we only rely on the induction increment to come before the
condition to ensure the required instructions get moved to the new
latch.
This patch duplicates and moves the required instructions to the
newly created latch. We move the condition to the end of the new block,
then process its operands. We stop at operands that are defined
outside the loop, or are the induction PHI.
We duplicate the instructions and update the uses in the moved
instructions, to ensure other users remain intact. See the added
test2 for such an example.
Reviewers: efriedma, mcrosier
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D67367
llvm-svn: 371595
This patch contains the basic functionality for reporting potentially
incorrect usage of __builtin_expect() by comparing the developer's
annotation against a collected PGO profile. A more detailed proposal and
discussion appears on the CFE-dev mailing list
(http://lists.llvm.org/pipermail/cfe-dev/2019-July/062971.html) and a
prototype of the initial frontend changes appear here in D65300
We revised the work in D65300 by moving the misexpect check into the
LLVM backend, and adding support for IR and sampling based profiles, in
addition to frontend instrumentation.
We add new misexpect metadata tags to those instructions directly
influenced by the llvm.expect intrinsic (branch, switch, and select)
when lowering the intrinsics. The misexpect metadata contains
information about the expected target of the intrinsic so that we can
check against the correct PGO counter when emitting diagnostics, and the
compiler's values for the LikelyBranchWeight and UnlikelyBranchWeight.
We use these branch weight values to determine when to emit the
diagnostic to the user.
A future patch should address the comment at the top of
LowerExpectIntrisic.cpp to hoist the LikelyBranchWeight and
UnlikelyBranchWeight values into a shared space that can be accessed
outside of the LowerExpectIntrinsic pass. Once that is done, the
misexpect metadata can be updated to be smaller.
In the long term, it is possible to reconstruct portions of the
misexpect metadata from the existing profile data. However, we have
avoided this to keep the code simple, and because some kind of metadata
tag will be required to identify which branch/switch/select instructions
are influenced by the use of llvm.expect
Patch By: paulkirth
Differential Revision: https://reviews.llvm.org/D66324
llvm-svn: 371584
This patch contains the basic functionality for reporting potentially
incorrect usage of __builtin_expect() by comparing the developer's
annotation against a collected PGO profile. A more detailed proposal and
discussion appears on the CFE-dev mailing list
(http://lists.llvm.org/pipermail/cfe-dev/2019-July/062971.html) and a
prototype of the initial frontend changes appear here in D65300
We revised the work in D65300 by moving the misexpect check into the
LLVM backend, and adding support for IR and sampling based profiles, in
addition to frontend instrumentation.
We add new misexpect metadata tags to those instructions directly
influenced by the llvm.expect intrinsic (branch, switch, and select)
when lowering the intrinsics. The misexpect metadata contains
information about the expected target of the intrinsic so that we can
check against the correct PGO counter when emitting diagnostics, and the
compiler's values for the LikelyBranchWeight and UnlikelyBranchWeight.
We use these branch weight values to determine when to emit the
diagnostic to the user.
A future patch should address the comment at the top of
LowerExpectIntrisic.cpp to hoist the LikelyBranchWeight and
UnlikelyBranchWeight values into a shared space that can be accessed
outside of the LowerExpectIntrinsic pass. Once that is done, the
misexpect metadata can be updated to be smaller.
In the long term, it is possible to reconstruct portions of the
misexpect metadata from the existing profile data. However, we have
avoided this to keep the code simple, and because some kind of metadata
tag will be required to identify which branch/switch/select instructions
are influenced by the use of llvm.expect
Patch By: paulkirth
Differential Revision: https://reviews.llvm.org/D66324
llvm-svn: 371484
Summary:
This is the first change to enable the TLI to be built per-function so
that -fno-builtin* handling can be migrated to use function attributes.
See discussion on D61634 for background. This is an enabler for fixing
handling of these options for LTO, for example.
This change should not affect behavior, as the provided function is not
yet used to build a specifically per-function TLI, but rather enables
that migration.
Most of the changes were very mechanical, e.g. passing a Function to the
legacy analysis pass's getTLI interface, or in Module level cases,
adding a callback. This is similar to the way the per-function TTI
analysis works.
There was one place where we were looking for builtins but not in the
context of a specific function. See FindCXAAtExit in
lib/Transforms/IPO/GlobalOpt.cpp. I'm somewhat concerned my workaround
could provide the wrong behavior in some corner cases. Suggestions
welcome.
Reviewers: chandlerc, hfinkel
Subscribers: arsenm, dschuff, jvesely, nhaehnle, mehdi_amini, javed.absar, sbc100, jgravelle-google, eraman, aheejin, steven_wu, george.burgess.iv, dexonsmith, jfb, asbirlea, gchatelet, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66428
llvm-svn: 371284
If we have:
bb5:
br i1 %arg3, label %bb6, label %bb7
bb6:
%tmp = getelementptr inbounds i32, i32* %arg1, i64 2
store i32 3, i32* %tmp, align 4
br label %bb9
bb7:
%tmp8 = getelementptr inbounds i32, i32* %arg1, i64 2
store i32 3, i32* %tmp8, align 4
br label %bb9
bb9: ; preds = %bb4, %bb6, %bb7
...
We can't sink stores directly into bb9.
This patch creates new BB that is successor of %bb6 and %bb7
and sinks stores into that block.
SplitFooterBB is the parameter to the pass that controls
that behavior.
Change-Id: I7fdf50a772b84633e4b1b860e905bf7e3e29940f
Differential: https://reviews.llvm.org/D66234
llvm-svn: 371089
When I dug into this, it turns out to be *much* more involved than I'd realized and doesn't actually simplify anything.
The general purpose of the leader table is that we want to find the most-dominating definition quickly. The problem for equivalance folding is slightly different; we want to find the most dominating *value* whose definition block dominates our use quickly.
To make this change, we'd end up having to restructure the leader table (either the sorting thereof, or maybe even introducing multiple leader tables per value) and that complexity is just not worth it.
llvm-svn: 370824
This extends the existing logic for propagating constant expressions in an analogous manner for what we do across basic blocks. The core point is that we chose some order of operands, and canonicalize uses towards that one.
The heuristic used is inspired by the one used across blocks; in a follow up change, I'd plan to common them so that the cross block version uses the slightly stronger ordering herein.
As noted by the TODOs in the code, there's a good amount of room for improving the existing code and making it more powerful. Some follow up work planned.
Differential Revision: https://reviews.llvm.org/D66977
llvm-svn: 370791
Use a { iN undef, i1 false } struct as the base, and only insert
the first operand, instead of using { iN undef, i1 undef } as the
base and inserting both. This is the same as what we do in InstCombine.
Differential Revision: https://reviews.llvm.org/D67034
llvm-svn: 370573
This is an updated version of https://reviews.llvm.org/D66909 to fix PR42605.
Basically, current phi translatation translates an old value number to an new
value number for a call instruction based on the literal equality of call
expression, without verifying there is no clobber in between. This is incorrect.
To get a finegrain check, use MachineDependence analysis to do the job. However,
this is still not ideal. Although given a call instruction,
`MemoryDependenceResults::getCallDependencyFrom` returns identical call
instructions without clobber in between using MemDepResult with its DepType to
be `Def`. However, identical is too strict here and we want it to be relaxed a
little to consider phi-translation -- callee is the same, param operands can be
different. That means changing the semantic of `MemDepResult::Def` and I don't
know the potential impact.
So currently the patch is still conservative to only handle
MemDepResult::NonFuncLocal, which means the current call has no function local
clobber. If there is clobber, even if the clobber doesn't stand in between the
current call and the call with the new value, we won't do phi-translate.
Differential Revision: https://reviews.llvm.org/D67013
llvm-svn: 370547
Summary:
@mclow.lists brought up this issue up in IRC.
It is a reasonably common problem to compare some two values for equality.
Those may be just some integers, strings or arrays of integers.
In C, there is `memcmp()`, `bcmp()` functions.
In C++, there exists `std::equal()` algorithm.
One can also write that function manually.
libstdc++'s `std::equal()` is specialized to directly call `memcmp()` for
various types, but not `std::byte` from C++2a. https://godbolt.org/z/mx2ejJ
libc++ does not do anything like that, it simply relies on simple C++'s
`operator==()`. https://godbolt.org/z/er0Zwf (GOOD!)
So likely, there exists a certain performance opportunities.
Let's compare performance of naive `std::equal()` (no `memcmp()`) with one that
is using `memcmp()` (in this case, compiled with modified compiler). {F8768213}
```
#include <algorithm>
#include <cmath>
#include <cstdint>
#include <iterator>
#include <limits>
#include <random>
#include <type_traits>
#include <utility>
#include <vector>
#include "benchmark/benchmark.h"
template <class T>
bool equal(T* a, T* a_end, T* b) noexcept {
for (; a != a_end; ++a, ++b) {
if (*a != *b) return false;
}
return true;
}
template <typename T>
std::vector<T> getVectorOfRandomNumbers(size_t count) {
std::random_device rd;
std::mt19937 gen(rd());
std::uniform_int_distribution<T> dis(std::numeric_limits<T>::min(),
std::numeric_limits<T>::max());
std::vector<T> v;
v.reserve(count);
std::generate_n(std::back_inserter(v), count,
[&dis, &gen]() { return dis(gen); });
assert(v.size() == count);
return v;
}
struct Identical {
template <typename T>
static std::pair<std::vector<T>, std::vector<T>> Gen(size_t count) {
auto Tmp = getVectorOfRandomNumbers<T>(count);
return std::make_pair(Tmp, std::move(Tmp));
}
};
struct InequalHalfway {
template <typename T>
static std::pair<std::vector<T>, std::vector<T>> Gen(size_t count) {
auto V0 = getVectorOfRandomNumbers<T>(count);
auto V1 = V0;
V1[V1.size() / size_t(2)]++; // just change the value.
return std::make_pair(std::move(V0), std::move(V1));
}
};
template <class T, class Gen>
void BM_bcmp(benchmark::State& state) {
const size_t Length = state.range(0);
const std::pair<std::vector<T>, std::vector<T>> Data =
Gen::template Gen<T>(Length);
const std::vector<T>& a = Data.first;
const std::vector<T>& b = Data.second;
assert(a.size() == Length && b.size() == a.size());
benchmark::ClobberMemory();
benchmark::DoNotOptimize(a);
benchmark::DoNotOptimize(a.data());
benchmark::DoNotOptimize(b);
benchmark::DoNotOptimize(b.data());
for (auto _ : state) {
const bool is_equal = equal(a.data(), a.data() + a.size(), b.data());
benchmark::DoNotOptimize(is_equal);
}
state.SetComplexityN(Length);
state.counters["eltcnt"] =
benchmark::Counter(Length, benchmark::Counter::kIsIterationInvariant);
state.counters["eltcnt/sec"] =
benchmark::Counter(Length, benchmark::Counter::kIsIterationInvariantRate);
const size_t BytesRead = 2 * sizeof(T) * Length;
state.counters["bytes_read/iteration"] =
benchmark::Counter(BytesRead, benchmark::Counter::kDefaults,
benchmark::Counter::OneK::kIs1024);
state.counters["bytes_read/sec"] = benchmark::Counter(
BytesRead, benchmark::Counter::kIsIterationInvariantRate,
benchmark::Counter::OneK::kIs1024);
}
template <typename T>
static void CustomArguments(benchmark::internal::Benchmark* b) {
const size_t L2SizeBytes = []() {
for (const benchmark::CPUInfo::CacheInfo& I :
benchmark::CPUInfo::Get().caches) {
if (I.level == 2) return I.size;
}
return 0;
}();
// What is the largest range we can check to always fit within given L2 cache?
const size_t MaxLen = L2SizeBytes / /*total bufs*/ 2 /
/*maximal elt size*/ sizeof(T) / /*safety margin*/ 2;
b->RangeMultiplier(2)->Range(1, MaxLen)->Complexity(benchmark::oN);
}
BENCHMARK_TEMPLATE(BM_bcmp, uint8_t, Identical)
->Apply(CustomArguments<uint8_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint16_t, Identical)
->Apply(CustomArguments<uint16_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint32_t, Identical)
->Apply(CustomArguments<uint32_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint64_t, Identical)
->Apply(CustomArguments<uint64_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint8_t, InequalHalfway)
->Apply(CustomArguments<uint8_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint16_t, InequalHalfway)
->Apply(CustomArguments<uint16_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint32_t, InequalHalfway)
->Apply(CustomArguments<uint32_t>);
BENCHMARK_TEMPLATE(BM_bcmp, uint64_t, InequalHalfway)
->Apply(CustomArguments<uint64_t>);
```
{F8768210}
```
$ ~/src/googlebenchmark/tools/compare.py --no-utest benchmarks build-{old,new}/test/llvm-bcmp-bench
RUNNING: build-old/test/llvm-bcmp-bench --benchmark_out=/tmp/tmpb6PEUx
2019-04-25 21:17:11
Running build-old/test/llvm-bcmp-bench
Run on (8 X 4000 MHz CPU s)
CPU Caches:
L1 Data 16K (x8)
L1 Instruction 64K (x4)
L2 Unified 2048K (x4)
L3 Unified 8192K (x1)
Load Average: 0.65, 3.90, 4.14
---------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
---------------------------------------------------------------------------------------------------
<...>
BM_bcmp<uint8_t, Identical>/512000 432131 ns 432101 ns 1613 bytes_read/iteration=1000k bytes_read/sec=2.20706G/s eltcnt=825.856M eltcnt/sec=1.18491G/s
BM_bcmp<uint8_t, Identical>_BigO 0.86 N 0.86 N
BM_bcmp<uint8_t, Identical>_RMS 8 % 8 %
<...>
BM_bcmp<uint16_t, Identical>/256000 161408 ns 161409 ns 4027 bytes_read/iteration=1000k bytes_read/sec=5.90843G/s eltcnt=1030.91M eltcnt/sec=1.58603G/s
BM_bcmp<uint16_t, Identical>_BigO 0.67 N 0.67 N
BM_bcmp<uint16_t, Identical>_RMS 25 % 25 %
<...>
BM_bcmp<uint32_t, Identical>/128000 81497 ns 81488 ns 8415 bytes_read/iteration=1000k bytes_read/sec=11.7032G/s eltcnt=1077.12M eltcnt/sec=1.57078G/s
BM_bcmp<uint32_t, Identical>_BigO 0.71 N 0.71 N
BM_bcmp<uint32_t, Identical>_RMS 42 % 42 %
<...>
BM_bcmp<uint64_t, Identical>/64000 50138 ns 50138 ns 10909 bytes_read/iteration=1000k bytes_read/sec=19.0209G/s eltcnt=698.176M eltcnt/sec=1.27647G/s
BM_bcmp<uint64_t, Identical>_BigO 0.84 N 0.84 N
BM_bcmp<uint64_t, Identical>_RMS 27 % 27 %
<...>
BM_bcmp<uint8_t, InequalHalfway>/512000 192405 ns 192392 ns 3638 bytes_read/iteration=1000k bytes_read/sec=4.95694G/s eltcnt=1.86266G eltcnt/sec=2.66124G/s
BM_bcmp<uint8_t, InequalHalfway>_BigO 0.38 N 0.38 N
BM_bcmp<uint8_t, InequalHalfway>_RMS 3 % 3 %
<...>
BM_bcmp<uint16_t, InequalHalfway>/256000 127858 ns 127860 ns 5477 bytes_read/iteration=1000k bytes_read/sec=7.45873G/s eltcnt=1.40211G eltcnt/sec=2.00219G/s
BM_bcmp<uint16_t, InequalHalfway>_BigO 0.50 N 0.50 N
BM_bcmp<uint16_t, InequalHalfway>_RMS 0 % 0 %
<...>
BM_bcmp<uint32_t, InequalHalfway>/128000 49140 ns 49140 ns 14281 bytes_read/iteration=1000k bytes_read/sec=19.4072G/s eltcnt=1.82797G eltcnt/sec=2.60478G/s
BM_bcmp<uint32_t, InequalHalfway>_BigO 0.40 N 0.40 N
BM_bcmp<uint32_t, InequalHalfway>_RMS 18 % 18 %
<...>
BM_bcmp<uint64_t, InequalHalfway>/64000 32101 ns 32099 ns 21786 bytes_read/iteration=1000k bytes_read/sec=29.7101G/s eltcnt=1.3943G eltcnt/sec=1.99381G/s
BM_bcmp<uint64_t, InequalHalfway>_BigO 0.50 N 0.50 N
BM_bcmp<uint64_t, InequalHalfway>_RMS 1 % 1 %
RUNNING: build-new/test/llvm-bcmp-bench --benchmark_out=/tmp/tmpQ46PP0
2019-04-25 21:19:29
Running build-new/test/llvm-bcmp-bench
Run on (8 X 4000 MHz CPU s)
CPU Caches:
L1 Data 16K (x8)
L1 Instruction 64K (x4)
L2 Unified 2048K (x4)
L3 Unified 8192K (x1)
Load Average: 1.01, 2.85, 3.71
---------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
---------------------------------------------------------------------------------------------------
<...>
BM_bcmp<uint8_t, Identical>/512000 18593 ns 18590 ns 37565 bytes_read/iteration=1000k bytes_read/sec=51.2991G/s eltcnt=19.2333G eltcnt/sec=27.541G/s
BM_bcmp<uint8_t, Identical>_BigO 0.04 N 0.04 N
BM_bcmp<uint8_t, Identical>_RMS 37 % 37 %
<...>
BM_bcmp<uint16_t, Identical>/256000 18950 ns 18948 ns 37223 bytes_read/iteration=1000k bytes_read/sec=50.3324G/s eltcnt=9.52909G eltcnt/sec=13.511G/s
BM_bcmp<uint16_t, Identical>_BigO 0.08 N 0.08 N
BM_bcmp<uint16_t, Identical>_RMS 34 % 34 %
<...>
BM_bcmp<uint32_t, Identical>/128000 18627 ns 18627 ns 37895 bytes_read/iteration=1000k bytes_read/sec=51.198G/s eltcnt=4.85056G eltcnt/sec=6.87168G/s
BM_bcmp<uint32_t, Identical>_BigO 0.16 N 0.16 N
BM_bcmp<uint32_t, Identical>_RMS 35 % 35 %
<...>
BM_bcmp<uint64_t, Identical>/64000 18855 ns 18855 ns 37458 bytes_read/iteration=1000k bytes_read/sec=50.5791G/s eltcnt=2.39731G eltcnt/sec=3.3943G/s
BM_bcmp<uint64_t, Identical>_BigO 0.32 N 0.32 N
BM_bcmp<uint64_t, Identical>_RMS 33 % 33 %
<...>
BM_bcmp<uint8_t, InequalHalfway>/512000 9570 ns 9569 ns 73500 bytes_read/iteration=1000k bytes_read/sec=99.6601G/s eltcnt=37.632G eltcnt/sec=53.5046G/s
BM_bcmp<uint8_t, InequalHalfway>_BigO 0.02 N 0.02 N
BM_bcmp<uint8_t, InequalHalfway>_RMS 29 % 29 %
<...>
BM_bcmp<uint16_t, InequalHalfway>/256000 9547 ns 9547 ns 74343 bytes_read/iteration=1000k bytes_read/sec=99.8971G/s eltcnt=19.0318G eltcnt/sec=26.8159G/s
BM_bcmp<uint16_t, InequalHalfway>_BigO 0.04 N 0.04 N
BM_bcmp<uint16_t, InequalHalfway>_RMS 29 % 29 %
<...>
BM_bcmp<uint32_t, InequalHalfway>/128000 9396 ns 9394 ns 73521 bytes_read/iteration=1000k bytes_read/sec=101.518G/s eltcnt=9.41069G eltcnt/sec=13.6255G/s
BM_bcmp<uint32_t, InequalHalfway>_BigO 0.08 N 0.08 N
BM_bcmp<uint32_t, InequalHalfway>_RMS 30 % 30 %
<...>
BM_bcmp<uint64_t, InequalHalfway>/64000 9499 ns 9498 ns 73802 bytes_read/iteration=1000k bytes_read/sec=100.405G/s eltcnt=4.72333G eltcnt/sec=6.73808G/s
BM_bcmp<uint64_t, InequalHalfway>_BigO 0.16 N 0.16 N
BM_bcmp<uint64_t, InequalHalfway>_RMS 28 % 28 %
Comparing build-old/test/llvm-bcmp-bench to build-new/test/llvm-bcmp-bench
Benchmark Time CPU Time Old Time New CPU Old CPU New
---------------------------------------------------------------------------------------------------------------------------------------
<...>
BM_bcmp<uint8_t, Identical>/512000 -0.9570 -0.9570 432131 18593 432101 18590
<...>
BM_bcmp<uint16_t, Identical>/256000 -0.8826 -0.8826 161408 18950 161409 18948
<...>
BM_bcmp<uint32_t, Identical>/128000 -0.7714 -0.7714 81497 18627 81488 18627
<...>
BM_bcmp<uint64_t, Identical>/64000 -0.6239 -0.6239 50138 18855 50138 18855
<...>
BM_bcmp<uint8_t, InequalHalfway>/512000 -0.9503 -0.9503 192405 9570 192392 9569
<...>
BM_bcmp<uint16_t, InequalHalfway>/256000 -0.9253 -0.9253 127858 9547 127860 9547
<...>
BM_bcmp<uint32_t, InequalHalfway>/128000 -0.8088 -0.8088 49140 9396 49140 9394
<...>
BM_bcmp<uint64_t, InequalHalfway>/64000 -0.7041 -0.7041 32101 9499 32099 9498
```
What can we tell from the benchmark?
* Performance of naive equality check somewhat improves with element size,
maxing out at eltcnt/sec=1.58603G/s for uint16_t, or bytes_read/sec=19.0209G/s
for uint64_t. I think, that instability implies performance problems.
* Performance of `memcmp()`-aware benchmark always maxes out at around
bytes_read/sec=51.2991G/s for every type. That is 2.6x the throughput of the
naive variant!
* eltcnt/sec metric for the `memcmp()`-aware benchmark maxes out at
eltcnt/sec=27.541G/s for uint8_t (was: eltcnt/sec=1.18491G/s, so 24x) and
linearly decreases with element size.
For uint64_t, it's ~4x+ the elements/second.
* The call obvious is more pricey than the loop, with small element count.
As it can be seen from the full output {F8768210}, the `memcmp()` is almost
universally worse, independent of the element size (and thus buffer size) when
element count is less than 8.
So all in all, bcmp idiom does indeed pose untapped performance headroom.
This diff does implement said idiom recognition. I think a reasonable test
coverage is present, but do tell if there is anything obvious missing.
Now, quality. This does succeed to build and pass the test-suite, at least
without any non-bundled elements. {F8768216} {F8768217}
This transform fires 91 times:
```
$ /build/test-suite/utils/compare.py -m loop-idiom.NumBCmp result-new.json
Tests: 1149
Metric: loop-idiom.NumBCmp
Program result-new
MultiSourc...Benchmarks/7zip/7zip-benchmark 79.00
MultiSource/Applications/d/make_dparser 3.00
SingleSource/UnitTests/vla 2.00
MultiSource/Applications/Burg/burg 1.00
MultiSourc.../Applications/JM/lencod/lencod 1.00
MultiSource/Applications/lemon/lemon 1.00
MultiSource/Benchmarks/Bullet/bullet 1.00
MultiSourc...e/Benchmarks/MallocBench/gs/gs 1.00
MultiSourc...gs-C/TimberWolfMC/timberwolfmc 1.00
MultiSourc...Prolangs-C/simulator/simulator 1.00
```
The size changes are:
I'm not sure what's going on with SingleSource/UnitTests/vla.test yet, did not look.
```
$ /build/test-suite/utils/compare.py -m size..text result-{old,new}.json --filter-hash
Tests: 1149
Same hash: 907 (filtered out)
Remaining: 242
Metric: size..text
Program result-old result-new diff
test-suite...ingleSource/UnitTests/vla.test 753.00 833.00 10.6%
test-suite...marks/7zip/7zip-benchmark.test 1001697.00 966657.00 -3.5%
test-suite...ngs-C/simulator/simulator.test 32369.00 32321.00 -0.1%
test-suite...plications/d/make_dparser.test 89585.00 89505.00 -0.1%
test-suite...ce/Applications/Burg/burg.test 40817.00 40785.00 -0.1%
test-suite.../Applications/lemon/lemon.test 47281.00 47249.00 -0.1%
test-suite...TimberWolfMC/timberwolfmc.test 250065.00 250113.00 0.0%
test-suite...chmarks/MallocBench/gs/gs.test 149889.00 149873.00 -0.0%
test-suite...ications/JM/lencod/lencod.test 769585.00 769569.00 -0.0%
test-suite.../Benchmarks/Bullet/bullet.test 770049.00 770049.00 0.0%
test-suite...HMARK_ANISTROPIC_DIFFUSION/128 NaN NaN nan%
test-suite...HMARK_ANISTROPIC_DIFFUSION/256 NaN NaN nan%
test-suite...CHMARK_ANISTROPIC_DIFFUSION/64 NaN NaN nan%
test-suite...CHMARK_ANISTROPIC_DIFFUSION/32 NaN NaN nan%
test-suite...ENCHMARK_BILATERAL_FILTER/64/4 NaN NaN nan%
Geomean difference nan%
result-old result-new diff
count 1.000000e+01 10.00000 10.000000
mean 3.152090e+05 311695.40000 0.006749
std 3.790398e+05 372091.42232 0.036605
min 7.530000e+02 833.00000 -0.034981
25% 4.243300e+04 42401.00000 -0.000866
50% 1.197370e+05 119689.00000 -0.000392
75% 6.397050e+05 639705.00000 -0.000005
max 1.001697e+06 966657.00000 0.106242
```
I don't have timings though.
And now to the code. The basic idea is to completely replace the whole loop.
If we can't fully kill it, don't transform.
I have left one or two comments in the code, so hopefully it can be understood.
Also, there is a few TODO's that i have left for follow-ups:
* widening of `memcmp()`/`bcmp()`
* step smaller than the comparison size
* Metadata propagation
* more than two blocks as long as there is still a single backedge?
* ???
Reviewers: reames, fhahn, mkazantsev, chandlerc, craig.topper, courbet
Reviewed By: courbet
Subscribers: hiraditya, xbolva00, nikic, jfb, gchatelet, courbet, llvm-commits, mclow.lists
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D61144
llvm-svn: 370454
The code we had isSafeToLoadUnconditionally was blatantly wrong. This function takes a "Size" argument which is supposed to describe the span loaded from. Instead, the code use the size of the pointer passed (which may be unrelated!) and only checks that span. For any Size > LoadSize, this can and does lead to miscompiles.
Worse, the generic code just a few lines above correctly handles the cases which *are* valid. So, let's delete said code.
Removing this code revealed two issues:
1) As noted by jdoerfert the removed code incorrectly handled external globals. The test update in SROA is to stop testing incorrect behavior.
2) SROA was confusing bytes and bits, but this wasn't obvious as the Size parameter was being essentially ignored anyway. Fixed.
Differential Revision: https://reviews.llvm.org/D66778
llvm-svn: 370102
We were computing the loop exit value, but not ensuring the addrec belonged to the loop whose exit value we were computing. I couldn't actually trip this; the test case shows the basic setup which *might* trip this, but none of the variations I've tried actually do.
llvm-svn: 369730
The alignment is calculated incorrectly, thus sometimes it doesn't generate aligned mov instructions, as shown by the example below:
```
// b.cc
typedef long long index;
extern "C" index g_tid;
extern "C" index g_num;
void add3(float* __restrict__ a, float* __restrict__ b, float* __restrict__ c) {
index n = 64*1024;
index m = 16*1024;
index k = 4*1024;
index tid = g_tid;
index num = g_num;
__builtin_assume_aligned(a, 32);
__builtin_assume_aligned(b, 32);
__builtin_assume_aligned(c, 32);
for (index i0=tid*k; i0<m; i0+=num*k)
for (index i1=0; i1<n*m; i1+=m)
for (index i2=0; i2<k; i2++)
c[i1+i0+i2] = b[i0+i2] + a[i1+i0+i2];
}
```
Compile with `clang b.cc -Ofast -march=skylake -mavx2 -S`
```
vmovaps -224(%rdi,%rbx,4), %ymm0
vmovups -192(%rdi,%rbx,4), %ymm1 # should be movaps
vmovups -160(%rdi,%rbx,4), %ymm2 # should be movaps
vmovups -128(%rdi,%rbx,4), %ymm3 # should be movaps
vaddps -224(%rsi,%rbx,4), %ymm0, %ymm0
vaddps -192(%rsi,%rbx,4), %ymm1, %ymm1
vaddps -160(%rsi,%rbx,4), %ymm2, %ymm2
vaddps -128(%rsi,%rbx,4), %ymm3, %ymm3
vmovaps %ymm0, -224(%rdx,%rbx,4)
vmovups %ymm1, -192(%rdx,%rbx,4) # should be movaps
vmovups %ymm2, -160(%rdx,%rbx,4) # should be movaps
vmovups %ymm3, -128(%rdx,%rbx,4) # should be movaps
```
Differential Revision: https://reviews.llvm.org/D66575
Patch by Dun Liang
llvm-svn: 369723
Currently we do not properly translate addresses with PHIs if LoadBB !=
LI->getParent(), because PHITranslateAddr expects a direct predecessor as argument,
because it considers all instructions outside of the current block to
not requiring translation.
The amount of cases that trigger this should be very low, as most single
predecessor blocks should be folded into their predecessor by GVN before
we actually start with value numbering. It is still not guaranteed to
happen, so we should do PHI translation along all edges between the
loads' block and the predecessor where we have to place a load.
There are a few test cases showing current limits of the PHI translation, which
could be improved later.
Reviewers: spatel, reames, efriedma, john.brawn
Reviewed By: efriedma
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65020
llvm-svn: 369570
Summary:
Simplify the API using Optional<> and address comments in
https://reviews.llvm.org/D66165
Reviewers: vitalybuka
Subscribers: hiraditya, llvm-commits, ostannard, pcc
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66317
llvm-svn: 369300
Summary:
When inserting uses from outside the MemorySSA creation, we don't
normally need to rename uses, based on the assumption that there will be
no inserted Phis (if Def existed that required a Phi, that Phi already
exists). However, when dealing with unreachable blocks, MemorySSA will
optimize away Phis whose incoming blocks are unreachable, and these Phis end
up being re-added when inserting a Use.
There are two potential solutions here:
1. Analyze the inserted Phis and clean them up if they are unneeded
(current method for cleaning up trivial phis does not cover this)
2. Leave the Phi in place and rename uses, the same way as whe inserting
defs.
This patch use approach 2.
Resolves first test in PR42940.
Reviewers: george.burgess.iv
Subscribers: Prazek, sanjoy.google, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66033
llvm-svn: 369291
This patch applies only to the new pass manager.
Currently, when MSSA Analysis is available, and pass to each loop pass, it will be preserved by that loop pass.
Hence, mark the analysis preserved based on that condition, vs the current `EnableMSSALoopDependency`. This leaves the global flag to affect only the entry point in the loop pass manager (in FunctionToLoopPassAdaptor).
llvm-svn: 369181
Now that we've moved to C++14, we no longer need the llvm::make_unique
implementation from STLExtras.h. This patch is a mechanical replacement
of (hopefully) all the llvm::make_unique instances across the monorepo.
llvm-svn: 369013
We already supported rewriting loop exit values for multiple exit loops, but if any of the loop exits were not computable, we gave up on all loop exit values. This patch generalizes the existing code to handle individual computable loop exits where possible.
As discussed in the review, this is a starting point for figuring out a better API. The code is a bit ugly, but getting it in lets us test as we go.
Differential Revision: https://reviews.llvm.org/D65544
llvm-svn: 368898
I'm planning on handling intrinsics that will benefit from checking
the address space enums. Don't bother moving the address collection
for now, since those won't need th enums.
llvm-svn: 368895
Summary:
We can't speculate around indirect branches: indirectbr and invoke. The
callbr instruction needs to be included here.
Reviewers: nickdesaulniers, manojgupta, chandlerc
Reviewed By: chandlerc
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66200
llvm-svn: 368873
Summary:
Hoisting/sinking instruction out of a loop isn't always beneficial. Hoisting an instruction from a cold block inside a loop body out of the loop could hurt performance. This change makes Loop ICM profile aware - it now checks block frequency to make sure hoisting/sinking anly moves instruction to colder block.
Test Plan:
ninja check
Reviewers: asbirlea, sanjoy, reames, nikic, hfinkel, vsk
Reviewed By: asbirlea
Subscribers: fhahn, vsk, davidxl, xbolva00, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65060
llvm-svn: 368526
This is an extension of a transform that tries to produce positive floating-point
constants to improve canonicalization (and hopefully lead to more reassociation
and CSE).
The original patches were:
D4904
D5363 (rL221721)
But as the test diffs show, these were limited to basic patterns by walking from
an instruction to its single user rather than recursively moving up the def-use
sequence. No fast-math is required here because we're only rearranging implicit
FP negations in intermediate ops.
A motivating bug is:
https://bugs.llvm.org/show_bug.cgi?id=32939
Differential Revision: https://reviews.llvm.org/D65954
llvm-svn: 368512
Summary:
Make sure that we report that changes has been made
by InstSimplify also in situations when only trivially
dead instructions has been removed. If for example a call
is removed the call graph must be updated.
Bug seem to have been introduced by llvm-svn r367173
(commit 02b9e45a7e), since the code in question
was rewritten in that commit.
Reviewers: spatel, chandlerc, foad
Reviewed By: spatel
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65973
llvm-svn: 368401
For some targets the LICM pass can result in sub-optimal code in some
cases where it would be better not to run the pass, but it isn't
always possible to suppress the transformations heuristically.
Where the front-end has insight into such cases it is beneficial
to attach loop metadata to disable the pass - this change adds the
llvm.licm.disable metadata to enable that.
Differential Revision: https://reviews.llvm.org/D64557
llvm-svn: 368296
D62198 introduced an option to relax the checks for
hasOnlyUniformBranches. This commit turns the option on by default, for
better code generation in some cases in AMDGPU.
Differential Revision: https://reviews.llvm.org/D63198
Change-Id: I9cbff002a1e74d3b7eb96b4192dc8129936d537d
llvm-svn: 368042
This patch adds an ability to disable profile based peeling
causing the peeling of all iterations and as a result prohibits
further unroll/peeling attempts on that loop.
The motivation to get an ability to separate peeling usage in
pipeline where in the first part we peel only separate iterations if needed
and later in pipeline we apply the full peeling which will prohibit further peeling.
Reviewers: reames, fhahn
Reviewed By: reames
Subscribers: hiraditya, zzheng, dmgreen, llvm-commits
Differential Revision: https://reviews.llvm.org/D64983
llvm-svn: 367668
Current peeling cost model can decide to peel off not all iterations
but only some of them to eliminate conditions on phi. At the same time
if any peeling happens the door for further unroll/peel optimizations on that
loop closes because the part of the code thinks that if peeling happened
it is profile based peeling and all iterations are peeled off.
To resolve this inconsistency the patch provides the flag which states whether
the full peeling basing on profile is enabled or not and peeling cost model
is able to modify this field like it does not PeelCount.
In a separate patch I will introduce an option to allow/disallow peeling basing
on profile.
To avoid infinite loop peeling the patch tracks the total number of peeled iteration
through llvm.loop.peeled.count loop metadata.
Reviewers: reames, fhahn
Reviewed By: reames
Subscribers: hiraditya, zzheng, dmgreen, llvm-commits
Differential Revision: https://reviews.llvm.org/D64972
llvm-svn: 367647
Summary:
While there is always a `Value::replaceAllUsesWith()`,
sometimes the replacement needs to be conditional.
I have only cleaned a few cases where `replaceUsesWithIf()`
could be used, to both add test coverage,
and show that it is actually useful.
Reviewers: jdoerfert, spatel, RKSimon, craig.topper
Reviewed By: jdoerfert
Subscribers: dschuff, sbc100, jgravelle-google, hiraditya, aheejin, george.burgess.iv, asbirlea, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65528
llvm-svn: 367548
This is a prepatory patch for future work on support exit value rewriting in loops with a mixture of computable and non-computable exit counts. The intention is to be "mostly NFC" - i.e. not enable any interesting new transforms - but in practice, there are some small output changes.
The test differences are caused by cases wherewhere getSCEVAtScope can simplify a single entry phi without needing any knowledge of the loop.
llvm-svn: 367485
We have some code marks instructions with struct operands as overdefined,
but if the instruction is a call to a function with tracked arguments,
this breaks the assumption that the lattice values of all call sites
are not overdefined and will be replaced by a constant.
This also re-adds the assertion from D65222, with additionally skipping
non-callsite uses. This patch should address the cases reported in which
the assertion fired.
Fixes PR42738.
Reviewers: efriedma, davide
Reviewed By: efriedma
Differential Revision: https://reviews.llvm.org/D65439
llvm-svn: 367430
Summary:
While `-div-rem-pairs` pass can decompose rem in div+rem pair when div-rem pair
is unsupported by target, nothing performs the opposite fold.
We can't do that in InstCombine or DAGCombine since neither of those has access to TTI.
So it makes most sense to teach `-div-rem-pairs` about it.
If we matched rem in expanded form, we know we will be able to place div-rem pair
next to each other so we won't regress the situation.
Also, we shouldn't decompose rem if we matched already-decomposed form.
This is surprisingly straight-forward otherwise.
The original patch was committed in rL367288 but was reverted in rL367289
because it exposed pre-existing RAUW issues in internal data structures
of the pass; those now have been addressed in a previous patch.
https://bugs.llvm.org/show_bug.cgi?id=42673
Reviewers: spatel, RKSimon, efriedma, ZaMaZaN4iK, bogner
Reviewed By: bogner
Subscribers: bogner, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65298
llvm-svn: 367419
Summary:
`DivRemPairs` internally creates two maps:
* {sign, divident, divisor} -> div instruction
* {sign, divident, divisor} -> rem instruction
Then it iterates over rem map, and looks if there is an entry
in div map with the same key. Then depending on some internal logic
it may RAUW rem instruction with something else.
But if that rem instruction is an input to other div/rem,
then it was used as a key in these maps, so the old value (used in key)
is now dandling, because RAUW didn't update those maps.
And we can't even RAUW map keys in general, there's `ValueMap`,
but we don't have a single `Value` as key...
The bug was discovered via D65298, and the test there exists.
Now, i'm not sure how to expose this issue in trunk.
The bug is clearly there if i change the map keys to be `AssertingVH`/`PoisoningVH`,
but i guess this didn't miscompiled anything thus far?
I really don't think this is benin without that patch.
The fix is actually rather straight-forward - instead of trying to somehow
shoe-horn `ValueMap` here (doesn't fit, key isn't just `Value`), or writing a new
`ValueMap` with key being a struct of `Value`s, we can just have an intermediate
data structure - a vector, each entry containing matching `Div, Rem` pair,
and pre-filling it before doing any modifications.
This way we won't need to query map after doing RAUW, so no bug is possible.
Reviewers: spatel, bogner, RKSimon, craig.topper
Reviewed By: spatel
Subscribers: hiraditya, hans, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65451
llvm-svn: 367417
LoopInfo can be easily preserved by passing it to the functions that
modify the CFG (SplitCriticalEdge and MergeBlockIntoPredecessor.
SplitCriticalEdge also preserves LoopSimplify and LCSSA form when when passing in
LoopInfo. The test case shows that we preserve LoopSimplify and
LoopInfo. Adding addPreservedID(LCSSAID) did not preserve LCSSA for some
reason.
Also I am not sure if it is possible to preserve those in the new pass
manager, as they aren't analysis passes.
Reviewers: reames, hfinkel, davide, jdoerfert
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D65137
llvm-svn: 367332
Summary:
This patch extends the use of the OptimizationRemarkEmitter to provide
information about loops that are not fused, and loops that are not eligible for
fusion. In particular, it uses the OptimizationRemarkAnalysis to identify loops
that are not eligible for fusion and the OptimizationRemarkMissed to identify
loops that cannot be fused.
It also reuses the statistics to provide the messages used in the
OptimizationRemarks. This provides common message strings between the
optimization remarks and the statistics.
I would like feedback on this approach, in general. If people are OK with this,
I will flesh out additional remarks in subsequent commits.
Subscribers: hiraditya, jsji, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63844
llvm-svn: 367327
test-suite/MultiSource/Benchmarks/DOE-ProxyApps-C/miniGMG broke:
Only PHI nodes may reference their own value!
%sub33 = srem i32 %sub33, %ranks_in_i
This reverts commit r367288.
llvm-svn: 367289
Summary:
While `-div-rem-pairs` pass can decompose rem in div+rem pair when div-rem pair
is unsupported by target, nothing performs the opposite fold.
We can't do that in InstCombine or DAGCombine since neither of those has access to TTI.
So it makes most sense to teach `-div-rem-pairs` about it.
If we matched rem in expanded form, we know we will be able to place div-rem pair
next to each other so we won't regress the situation.
Also, we shouldn't decompose rem if we matched already-decomposed form.
This is surprisingly straight-forward otherwise.
https://bugs.llvm.org/show_bug.cgi?id=42673
Reviewers: spatel, RKSimon, efriedma, ZaMaZaN4iK, bogner
Reviewed By: bogner
Subscribers: bogner, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65298
llvm-svn: 367288
The test case from:
https://bugs.llvm.org/show_bug.cgi?id=42771
...shows a ~30x slowdown caused by the awkward loop iteration (rL207302) that is
seemingly done just to avoid invalidating the instruction iterator. We can instead
delay instruction deletion until we reach the end of the block (or we could delay
until we reach the end of all blocks).
There's a test diff here for a degenerate case with llvm.assume that is not
meaningful in itself, but serves to verify this change in logic.
This change probably doesn't result in much overall compile-time improvement
because we call '-instsimplify' as a standalone pass only once in the standard
-O2 opt pipeline currently.
Differential Revision: https://reviews.llvm.org/D65336
llvm-svn: 367173
unreachable loop.
updatePredecessorProfileMetadata in jumpthreading tries to find the
first dominating predecessor block for a PHI value by searching upwards
the predecessor block chain.
But jumpthreading may see some temporary IR state which contains
unreachable bb not being cleaned up. If an unreachable loop happens to
be on the predecessor block chain, keeping chasing the predecessor
block will run into an infinite loop.
The patch fixes it.
Differential Revision: https://reviews.llvm.org/D65310
llvm-svn: 367154
Just move the utility function to LoopUtils.cpp to re-use it in loop peeling.
Reviewers: reames, Ashutosh
Reviewed By: reames
Subscribers: hiraditya, asbirlea, llvm-commits
Differential Revision: https://reviews.llvm.org/D65264
llvm-svn: 367085
We should only zap returns in functions, where all live users have a
replace-able value (are not overdefined). Unused return values should be
undefined.
This should make it easier to detect bugs like in PR42738.
Alternatively we could bail out of zapping the function returns, but I
think it would be better to address those divergences between function
and call-site values where they are actually caused.
Reviewers: davide, efriedma
Reviewed By: davide, efriedma
Differential Revision: https://reviews.llvm.org/D65222
llvm-svn: 366998
The original code failed to account for the fact that one exit can have a pointer exit count without all of them having pointer exit counts. This could cause two separate bugs:
1) We might exit the loop early, and leave optimizations undone. This is what triggered the assertion failure in the reported test case.
2) We might optimize one exit, then exit without indicating a change. This could result in an analysis invalidaton bug if no other transform is done by the rest of indvars.
Note that the pointer exit counts are a really fragile concept. They show up only when we have a pointer IV w/o a datalayout to provide their size. It's really questionable to me whether the complexity implied is worth it.
llvm-svn: 366829
I don't have an IR sample which is actually failing, but the issue described in the comment is theoretically possible, and should be guarded against even if there's a different root cause for the bot failures.
llvm-svn: 366241
Continue in the spirit of D63618, and use exit count reasoning to prove away loop exits which can not be taken since the backedge taken count of the loop as a whole is provably less than the minimal BE count required to take this particular loop exit.
As demonstrated in the newly added tests, this triggers in a number of cases where IndVars was previously unable to discharge obviously redundant exit tests. And some not so obvious ones.
Differential Revision: https://reviews.llvm.org/D63733
llvm-svn: 365920
Summary:
We will need to handle IntToPtr which I will submit in a separate patch as it's
not going to be NFC.
Reviewers: eugenis, pcc
Reviewed By: eugenis
Subscribers: hiraditya, cfe-commits, llvm-commits
Tags: #clang, #llvm
Differential Revision: https://reviews.llvm.org/D63940
llvm-svn: 365709
Only instructions with two or more unique successors should be considered for unswitching.
Patch Author: Daniil Suchkov.
Reviewers: reames, asbirlea, skatkov
Reviewed By: skatkov
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D64404
llvm-svn: 365611
This makes the functions in Loads.h require a type to be specified
independently of the pointer Value so that when pointers have no structure
other than address-space, it can still do its job.
Most callers had an obvious memory operation handy to provide this type, but a
SROA and ArgumentPromotion were doing more complicated analysis. They get
updated to merge the properties of the various instructions they were
considering.
llvm-svn: 365468
D63921 requires getExitEdges fills a vector of Edge pairs where
BasicBlocks are not constant.
The rest Loop API mostly returns non-const BasicBlocks, so to be more consistent with
other Loop API getExitEdges is modified to return non-const BasicBlocks as well.
This is an alternative solution to D64060.
Reviewers: reames, fhahn
Reviewed By: reames, fhahn
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D64309
llvm-svn: 365437
A while back, I added support for NE latches formed by LFTR. I didn't think that quite through, as LFTR will also produce the inverse EQ form for some loops and I hadn't handled that. This change just adds handling for that case as well.
llvm-svn: 365419
We had versions of this code scattered around, so consolidate into one location.
Not strictly NFC since the order of intermediate results may change in some places, but since these operations are associatives, should not change results.
llvm-svn: 365259
If the block being cloned contains a PHI node, in general, we need to
clone that PHI node, even though it's trivial. If the operand of the PHI
is an instruction in the block being cloned, the correct value for the
operand doesn't exist until SSAUpdater constructs it.
We usually don't hit this issue because we try to avoid threading across
loop headers, but it's possible to hit this in some cases involving
irreducible CFGs. I added a flag to allow threading across loop headers
to make the testcase easier to understand.
Thanks to Brian Rzycki for reducing the testcase.
Fixes https://bugs.llvm.org/show_bug.cgi?id=42085.
Differential Revision: https://reviews.llvm.org/D63913
llvm-svn: 365094
As noted in the test change, this is not trivially NFC, but all of the changes in output are cases where the SCEVExpander form is more canonical/optimal than the hand generation.
llvm-svn: 365075
The motivation for this is two fold:
1) Make the output (and thus tests) a bit more readable to a human trying to understand the result of the transform
2) Reduce spurious diffs in a potential future change to restructure all of this logic to use SCEVExpander (which hoists by default)
llvm-svn: 365066
What we want to know here is whether we're already using this value
for the loop condition, so make the query about that. We can extend
this to a more general "based-on" relationship, rather than a direct
icmp use later.
llvm-svn: 364715
The whole indvars pass works on loops in simplified form, so there
is always a unique latch. Convert the condition into an assertion
in needsLFTR (though we also assert this in later LFTR functions).
Additionally update the comment on getLoopTest() now that we are
dealing with multiple exits.
llvm-svn: 364713
Fixes https://bugs.llvm.org/show_bug.cgi?id=41998. Usually when we
have a truncated exit count we'll truncate the IV when comparing
against the limit, in which case exit count overflow in post-inc
form doesn't matter. However, for pointer IVs we don't do that, so
we have to be careful about incrementing the IV in the wide type.
I'm fixing this by removing the IVCount variable (which was
ExitCount or ExitCount+1) and replacing it with a UsePostInc flag,
and then moving the actual limit adjustment to the individual cases
(which are: pointer IV where we add to the wide type, integer IV
where we add to the narrow type, and constant integer IV where we
add to the wide type).
Differential Revision: https://reviews.llvm.org/D63686
llvm-svn: 364709
This allows later passes (in particular InstCombine) to optimize more
cases.
One that's important to us is `memcmp(p, q, constant) < 0` and memcmp(p, q, constant) > 0.
llvm-svn: 364412
Inference of nowrap flags in CVP has been disabled, because it
triggered a bug in LFTR (https://bugs.llvm.org/show_bug.cgi?id=31181).
This issue has been fixed in D60935, so we should be able to reenable
nowrap flag inference now.
Differential Revision: https://reviews.llvm.org/D62776
llvm-svn: 364228
In rL364135, I taught IndVars to fold exiting branches in loops with a zero backedge taken count (i.e. loops that only run one iteration). This extends that to eliminate the dead comparison left around.
llvm-svn: 364155
This turned out to be surprisingly effective. I was originally doing this just for completeness sake, but it seems like there are a lot of cases where SCEV's exit count reasoning is stronger than it's isKnownPredicate reasoning.
Once this is in, I'm thinking about trying to build on the same infrastructure to eliminate provably untaken checks. There may be something generally interesting here.
Differential Revision: https://reviews.llvm.org/D63618
llvm-svn: 364135
Summary:
The motivation for this was to propagate fast-math flags like nnan and
ninf on vector floating point operations to the corresponding scalar
operations to take advantage of follow-on optimizations. But I think
the same argument applies to all of our IR flags: if they apply to the
vector operation then they also apply to all the individual scalar
operations, and they might enable follow-on optimizations.
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63593
llvm-svn: 364051
Also, add a FIXME for the unsafe transform on a unary FNeg. A unary FNeg can only be transformed to a FMul by -1.0 when the nnan flag is present. The unary FNeg project is a WIP, so the unsafe transformation is acceptable until that work is complete.
The bogus assert with introduced in D63445.
llvm-svn: 363998
Summary:
The getClobberingMemoryAccess API checks for clobbering accesses in a loop by walking the backedge. This may check if a memory access is being
clobbered by the loop in a previous iteration, depending how smart AA got over the course of the updates in MemorySSA (it does not occur when built from scratch).
If no clobbering access is found inside the loop, it will optimize to an access outside the loop. This however does not mean that access is safe to sink.
Given:
```
for i
load a[i]
store a[i]
```
The access corresponding to the load can be optimized to outside the loop, and the load can be hoisted. But it is incorrect to sink it.
In order to sink the load, we'd need to check no Def clobbers the Use in the same iteration. With this patch we currently restrict sinking to either
Defs not existing in the loop, or Defs preceding the load in the same block. An easy extension is to ensure the load (Use) post-dominates all Defs.
Caught by PR42294.
This issue also shed light on the converse problem: hoisting stores in this same scenario would be illegal. With this patch we restrict
hoisting of stores to the case when their corresponding Defs are dominating all Uses in the loop.
Reviewers: george.burgess.iv
Subscribers: jlebar, Prazek, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63582
llvm-svn: 363982
I can't actually come up with a test case this triggers on without an out of tree change, but in theory, it's a bug in the recently added multiple exit LFTR support. The root issue is that an exiting block common to two loops can (in theory) have computable exit counts for both loops. Rewriting the exit of an inner loop in terms of the outer loops IV would cause the inner loop to either a) run forever, or b) terminate on the first iteration.
In practice, we appear to get lucky and not have the exit count computable for the outer loop, except when it's trivially zero. Given we bail on zero exit counts, we don't appear to ever trigger this. But I can't come up with a reason we *can't* compute an exit count for the outer loop on the common exiting block, so this may very well be triggering in some cases.
llvm-svn: 363964
Teach IndVarSimply's LinearFunctionTestReplace transform to handle multiple exit loops. LFTR does two key things 1) it rewrites (all) exit tests in terms of a common IV potentially eliminating one in the process and 2) it moves any offset/indexing/f(i) style logic out of the loop.
This turns out to actually be pretty easy to implement. SCEV already has all the information we need to know what the backedge taken count is for each individual exit. (We use that when computing the BE taken count for the loop as a whole.) We basically just need to iterate through the exiting blocks and apply the existing logic with the exit specific BE taken count. (The previously landed NFC makes this super obvious.)
I chose to go ahead and apply this to all loop exits instead of only latch exits as originally proposed. After reviewing other passes, the only case I could find where LFTR form was harmful was LoopPredication. I've fixed the latch case, and guards aren't LFTRed anyways. We'll have some more work to do on the way towards widenable_conditions, but that's easily deferred.
I do want to note that I added one bit after the review. When running tests, I saw a new failure (no idea why didn't see previously) which pointed out LFTR can rewrite a constant condition back to a loop varying one. This was theoretically possible with a single exit, but the zero case covered it in practice. With multiple exits, we saw this happening in practice for the eliminate-comparison.ll test case because we'd compute a ExitCount for one of the exits which was guaranteed to never actually be reached. Since LFTR ran after simplifyAndExtend, we'd immediately turn around and undo the simplication work we'd just done. The solution seemed obvious, so I didn't bother with another round of review.
Differential Revision: https://reviews.llvm.org/D62625
llvm-svn: 363883
(Recommit of r363293 which was reverted when a dependent patch was.)
As pointed out by Nikita in D62625, BackedgeTakenCount is generally used to refer to the backedge taken count of the loop. A conditional backedge taken count - one which only applies if a particular exit is taken - is called a ExitCount in SCEV code, so be consistent here.
llvm-svn: 363875
[SROA] Enhance SROA to handle `addrspacecast`ed allocas
- Fix typo in original change
- Add additional handling to ensure all return pointers are properly
casted.
Summary:
- After `addrspacecast` is allowed to be eliminated in SROA, the
adjusting of storage pointer (from `alloca) needs to handle the
potential different address spaces between the storage pointer (from
alloca) and the pointer being used.
Reviewers: arsenm
Subscribers: wdng, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63501
llvm-svn: 363743
Summary:
- After `addrspacecast` is allowed to be eliminated in SROA, the
adjusting of storage pointer (from `alloca) needs to handle the
potential different address spaces between the storage pointer (from
alloca) and the pointer being used.
Reviewers: arsenm
Subscribers: wdng, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63501
llvm-svn: 363711
This patch really contains two pieces:
Teach SCEV how to fold a phi in the header of a loop to the value on the backedge when a) the backedge is known to execute at least once, and b) the value is safe to use globally within the scope dominated by the original phi.
Teach IndVarSimplify's rewriteLoopExitValues to allow loop invariant expressions which already exist (and thus don't need new computation inserted) even in loops where we can't optimize away other uses.
Differential Revision: https://reviews.llvm.org/D63224
llvm-svn: 363619
Recommit r363289 with a bug fix for crash identified in pr42279. Issue was that a loop exit test does not have to be an icmp, leading to a null dereference crash when new logic was exercised for that case. Test case previously committed in r363601.
Original commit comment follows:
This contains fixes for two cases where we might invalidate inbounds and leave it stale in the IR (a miscompile). Case 1 is when switching to an IV with no dynamically live uses, and case 2 is when doing pre-to-post conversion on the same pointer type IV.
The basic scheme used is to prove that using the given IV (pre or post increment forms) would have to already trigger UB on the path to the test we're modifying. As such, our potential UB triggering use does not change the semantics of the original program.
As was pointed out in the review thread by Nikita, this is defending against a separate issue from the hasConcreteDef case. This is about poison, that's about undef. Unfortunately, the two are different, see Nikita's comment for a fuller explanation, he explains it well.
(Note: I'm going to address Nikita's last style comment in a separate commit just to minimize chance of subtle bugs being introduced due to typos.)
Differential Revision: https://reviews.llvm.org/D62939
llvm-svn: 363613
Summary:
Update compare normalization in SimpleValue hashing to break ties (when
the same value is being compared to itself) by switching to the swapped
predicate if it has a lower numerical value. This brings the hashing in
line with isEqual, which already recognizes the self-compares with
swapped predicates as equal.
Fixes PR 42280.
Reviewers: spatel, efriedma, nikic, fhahn, uabelho
Reviewed By: nikic
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D63349
llvm-svn: 363598
Summary:
There is PHINode::getBasicBlockIndex() and PHINode::setIncomingValue()
but no function to replace incoming value for a specified BasicBlock*
predecessor.
Clearly, there are a lot of places that could use that functionality.
Reviewer: craig.topper, lebedev.ri, Meinersbur, kbarton, fhahn
Reviewed By: Meinersbur, fhahn
Subscribers: fhahn, hiraditya, zzheng, jsji, llvm-commits
Tag: LLVM
Differential Revision: https://reviews.llvm.org/D63338
llvm-svn: 363566
If an addrspacecast needed to be inserted again, this was creating a
clone of the original cast for each user. Just use the original, which
also saves losing the value name.
llvm-svn: 363562
There is a circular dependency between SROA and InferAddressSpaces
today that requires running both multiple times in order to be able to
eliminate all simple allocas and addrspacecasts. InferAddressSpaces
can't remove addrspacecasts when written to memory, and SROA helps
move pointers out of memory.
This should avoid inserting new commuting addrspacecasts with GEPs,
since there are unresolved questions about pointer wrapping between
different address spaces.
For now, don't replace volatile operations that don't match the alloca
addrspace, as it would change the address space of the access. It may
be still OK to insert an addrspacecast from the new alloca, but be
more conservative for now.
llvm-svn: 363462
As pointed out by Nikita in D62625, BackedgeTakenCount is generally used to refer to the backedge taken count of the loop. A conditional backedge taken count - one which only applies if a particular exit is taken - is called a ExitCount in SCEV code, so be consistent here.
llvm-svn: 363293
This contains fixes for two cases where we might invalidate inbounds and leave it stale in the IR (a miscompile). Case 1 is when switching to an IV with no dynamically live uses, and case 2 is when doing pre-to-post conversion on the same pointer type IV.
The basic scheme used is to prove that using the given IV (pre or post increment forms) would have to already trigger UB on the path to the test we're modifying. As such, our potential UB triggering use does not change the semantics of the original program.
As was pointed out in the review thread by Nikita, this is defending against a separate issue from the hasConcreteDef case. This is about poison, that's about undef. Unfortunately, the two are different, see Nikita's comment for a fuller explanation, he explains it well.
(Note: I'm going to address Nikita's last style comment in a separate commit just to minimize chance of subtle bugs being introduced due to typos.)
Differential Revision: https://reviews.llvm.org/D62939
llvm-svn: 363289
Summary:
The logic in EarlyCSE that looks through 'not' operations in the
predicate recognizes e.g. that `select (not (cmp sgt X, Y)), X, Y` is
equivalent to `select (cmp sgt X, Y), Y, X`. Without this change,
however, only the latter is recognized as a form of `smin X, Y`, so the
two expressions receive different hash codes. This leads to missed
optimization opportunities when the quadratic probing for the two hashes
doesn't happen to collide, and assertion failures when probing doesn't
collide on insertion but does collide on a subsequent table grow
operation.
This change inverts the order of some of the pattern matching, checking
first for the optional `not` and then for the min/max/abs patterns, so
that e.g. both expressions above are recognized as a form of `smin X, Y`.
It also adds an assertion to isEqual verifying that it implies equal
hash codes; this fires when there's a collision during insertion, not
just grow, and so will make it easier to notice if these functions fall
out of sync again. A new flag --earlycse-debug-hash is added which can
be used when changing the hash function; it forces hash collisions so
that any pair of values inserted which compare as equal but hash
differently will be caught by the isEqual assertion.
Reviewers: spatel, nikic
Reviewed By: spatel, nikic
Subscribers: lebedev.ri, arsenm, craig.topper, efriedma, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62644
llvm-svn: 363274
This case is slightly tricky, because loop distribution should be
allowed in some cases, and not others. As long as runtime dependency
checks don't need to be introduced, this should be OK. This is further
complicated by the fact that LoopDistribute partially ignores if LAA
says that vectorization is safe, and then does its own runtime pointer
legality checks.
Note this pass still does not handle noduplicate correctly, as this
should always be forbidden with it. I'm not going to bother trying to
fix it, as it would require more effort and I think noduplicate should
be removed.
https://reviews.llvm.org/D62607
llvm-svn: 363160
Summary:
The method `getLoopPassPreservedAnalyses` should not mark MemorySSA as
preserved, because it's being called in a lot of passes that do not
preserve MemorySSA.
Instead, mark the MemorySSA analysis as preserved by each pass that does
preserve it.
These changes only affect the new pass mananger.
Reviewers: chandlerc
Subscribers: mehdi_amini, jlebar, Prazek, george.burgess.iv, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62536
llvm-svn: 363091
This was discussed as part of D62880. The basic thought is that computing BE taken count after widening should produce (on average) an equally good backedge taken count as the one before widening. Since there's only one test in the suite which is impacted by this change, and it's essentially equivelent codegen, that seems to be a reasonable assertion. This change was separated from r362971 so that if this turns out to be problematic, the triggering piece is obvious and easily revertable.
For the nestedIV example from elim-extend.ll, we end up with the following BE counts:
BEFORE: (-2 + (-1 * %innercount) + %limit)
AFTER: (-1 + (sext i32 (-1 + %limit) to i64) + (-1 * (sext i32 %innercount to i64))<nsw>)
Note that before is an i32 type, and the after is an i64. Truncating the i64 produces the i32.
llvm-svn: 362975
This change does the plumbing to wire an ExitingBB parameter through the LFTR implementation, and reorganizes the code to work in terms of a set of individual loop exits. Most of it is fairly obvious, but there's one key complexity which makes it worthy of consideration. The actual multi-exit LFTR patch is in D62625 for context.
Specifically, it turns out the existing code uses the backedge taken count from before a IV is widened. Oddly, we can end up with a different (more expensive, but semantically equivelent) BE count for the loop when requerying after widening. For the nestedIV example from elim-extend, we end up with the following BE counts:
BEFORE: (-2 + (-1 * %innercount) + %limit)
AFTER: (-1 + (sext i32 (-1 + %limit) to i64) + (-1 * (sext i32 %innercount to i64))<nsw>)
This is the only test in tree which seems sensitive to this difference. The actual result of using the wider BETC on this example is that we actually produce slightly better code. :)
In review, we decided to accept that test change. This patch is structured to preserve the old behavior, but a separate change will immediate follow with the behavior change. (I wanted it separate for problem attribution purposes.)
Differential Revision: https://reviews.llvm.org/D62880
llvm-svn: 362971
Summary: Move some code around, in preparation for later fixes
to the non-integral addrspace handling (D59661)
Patch By Jameson Nash <jameson@juliacomputing.com>
Reviewed By: reames, loladiro
Differential Revision: https://reviews.llvm.org/D59729
llvm-svn: 362853
This is a really silly bug that even a simple test w/an unconditional latch would have caught. I tried to guard against the case, but put it in the wrong if check. Oops.
llvm-svn: 362727
The AllConstant check needs to be moved out of the if/else if chain to
avoid a test regression. The "there is no SimplifyZExt" comment
puzzles me, since there is SimplifyCastInst. Additionally, the
Simplify* calls seem to not see the operand as constant, so this needs
to be tried if the simplify failed.
llvm-svn: 362653
This reverts commit 5b32f60ec3.
The fix is in commit 4f9e68148b.
This patch fixes the CorrelatedValuePropagation pass to keep
prof branch_weights metadata of SwitchInst consistent.
It makes use of SwitchInstProfUpdateWrapper.
New tests are added.
Reviewed By: nikic
Differential Revision: https://reviews.llvm.org/D62126
llvm-svn: 362583
Fix for https://bugs.llvm.org/show_bug.cgi?id=31181 and partial fix
for LFTR poison handling issues in general.
When LFTR moves a condition from pre-inc to post-inc, it may now
depend on value that is poison due to nowrap flags. To avoid this,
we clear any nowrap flag that SCEV cannot prove for the post-inc
addrec.
Additionally, LFTR may switch to a different IV that is dynamically
dead and as such may be arbitrarily poison. This patch will correct
nowrap flags in some but not all cases where this happens. This is
related to the adoption of IR nowrap flags for the pre-inc addrec.
(See some of the switch_to_different_iv tests, where flags are not
dropped or insufficiently dropped.)
Finally, there are likely similar issues with the handling of GEP
inbounds, but we don't have a test case for this yet.
Differential Revision: https://reviews.llvm.org/D60935
llvm-svn: 362292
At the moment, LoopPredication completely bails out if it sees a latch of the form:
%cmp = icmp ne %iv, %N
br i1 %cmp, label %loop, label %exit
OR
%cmp = icmp ne %iv.next, %NPlus1
br i1 %cmp, label %loop, label %exit
This is unfortunate since this is exactly the form that LFTR likes to produce. So, go ahead and recognize simple cases where we can.
For pre-increment loops, we leverage the fact that LFTR likes canonical counters (i.e. those starting at zero) and a (presumed) range fact on RHS to discharge the check trivially.
For post-increment forms, the key insight is in remembering that LFTR had to insert a (N+1) for the RHS. CVP can hopefully prove that add nsw/nuw (if there's appropriate range on N to start with). This leaves us both with the post-inc IV and the RHS involving an nsw/nuw add, and SCEV can discharge that with no problem.
This does still need to be extended to handle non-one steps, or other harder patterns of variable (but range restricted) starting values. That'll come later.
Differential Revision: https://reviews.llvm.org/D62748
llvm-svn: 362282
If we can determine that a saturating add/sub will not overflow based
on range analysis, convert it into a simple binary operation. This is
a sibling transform to the existing with.overflow handling.
Reapplying this with an additional check that the saturating intrinsic
has integer type, as LVI currently does not support vector types.
Differential Revision: https://reviews.llvm.org/D62703
llvm-svn: 362263
Noticed on D62703. LVI only handles plain integers, not vectors of
integers. This was previously not an issue, because vector support
for with.overflow is only a relatively recent addition.
llvm-svn: 362261
If we can determine that a saturating add/sub will not overflow
based on range analysis, convert it into a simple binary operation.
This is a sibling transform to the existing with.overflow handling.
Differential Revision: https://reviews.llvm.org/D62703
llvm-svn: 362242
Summary:
I'm adding ORE to memset/memcpy formation, with tests,
but mainly this is split off from D61144.
Reviewers: reames, anemet, thegameg, craig.topper
Reviewed By: thegameg
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62631
llvm-svn: 362092
This reverts commit 53f2f32865.
As reported on D62126, this causes assertion failures if the switch
has incorrect branch_weights metadata, which may happen as a result
of other transforms not handling it correctly yet.
llvm-svn: 361881
This patch fixes the CorrelatedValuePropagation pass to keep
prof branch_weights metadata of SwitchInst consistent.
It makes use of SwitchInstProfUpdateWrapper.
New tests are added.
Reviewed By: nikic
Differential Revision: https://reviews.llvm.org/D62126
llvm-svn: 361808
The code to preserve LCSSA PHIs currently only properly supports
reduction PHIs and PHIs for values defined outside the latches.
This patch improves the LCSSA PHI handling to cover PHIs for values
defined in the latches.
Fixes PR41725.
Reviewers: efriedma, mcrosier, davide, jdoerfert
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D61576
llvm-svn: 361743
The guaranteed no-wrap region is never empty, it always contains at
least zero, so these optimizations don't ever apply.
To make this more obviously true, replace the conversative return
in makeGNWR with an assertion.
llvm-svn: 361698
Just a minor refactoring to use the new helper method
DataLayout::typeSizeEqualsStoreSize(). This is done when
checking if getTypeSizeInBits is equal/non-equal to
getTypeStoreSizeInBits.
llvm-svn: 361613
This change relaxes the checks for hasOnlyUniformBranches such that our
region is uniform if:
1. All conditional branches that are direct children are uniform.
2. And either:
a. All sub-regions are uniform.
b. There is one or less conditional branches among the direct
children.
Differential Revision: https://reviews.llvm.org/D62198
llvm-svn: 361610
Summary:
The DeadStoreElimination pass now skips doing
PartialStoreMerging when stores overlap according to
OW_PartialEarlierWithFullLater and at least one of
the stores is having a store size that is different
from the size of the type being stored.
This solves problems seen in
https://bugs.llvm.org/show_bug.cgi?id=41949
for which we in the past could end up with
mis-compiles or assertions.
The content and location of the padding bits is not
formally described (or undefined) in the LangRef
at the moment. So the solution is chosen based on
that we cannot assume anything about the padding bits
when having a store that clobbers more memory than
indicated by the type of the value that is stored
(such as storing an i6 using an 8-bit store instruction).
Fixes: https://bugs.llvm.org/show_bug.cgi?id=41949
Reviewers: spatel, efriedma, fhahn
Reviewed By: efriedma
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62250
llvm-svn: 361605
Summary:
This PR extends the loop object with more utilities to get loop bounds, step, induction variable, and guard branch. There already exists passes which try to obtain the loop induction variable in their own pass, e.g. loop interchange. It would be useful to have a common area to get these information. Moreover, loop fusion (https://reviews.llvm.org/D55851) is planning to use getGuard() to extend the kind of loops it is able to fuse, e.g. rotated loop with non-constant upper bound, which would have a loop guard.
/// Example:
/// for (int i = lb; i < ub; i+=step)
/// <loop body>
/// --- pseudo LLVMIR ---
/// beforeloop:
/// guardcmp = (lb < ub)
/// if (guardcmp) goto preheader; else goto afterloop
/// preheader:
/// loop:
/// i1 = phi[{lb, preheader}, {i2, latch}]
/// <loop body>
/// i2 = i1 + step
/// latch:
/// cmp = (i2 < ub)
/// if (cmp) goto loop
/// exit:
/// afterloop:
///
/// getBounds
/// getInitialIVValue --> lb
/// getStepInst --> i2 = i1 + step
/// getStepValue --> step
/// getFinalIVValue --> ub
/// getCanonicalPredicate --> '<'
/// getDirection --> Increasing
/// getGuard --> if (guardcmp) goto loop; else goto afterloop
/// getInductionVariable --> i1
/// getAuxiliaryInductionVariable --> {i1}
/// isCanonical --> false
Committed on behalf of @Whitney (Whitney Tsang).
Reviewers: kbarton, hfinkel, dmgreen, Meinersbur, jdoerfert, syzaara, fhahn
Reviewed By: kbarton
Subscribers: tvvikram, bmahjour, etiotto, fhahn, jsji, hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D60565
llvm-svn: 361517
`fadd` and `fsub` have recently (r351850) been added as `atomicrmw`
operations. This diff adds lowering cases for them to the LowerAtomic
transform.
Patch by Josh Berdine!
llvm-svn: 361512
Philip Reames