| Commit message (Collapse) | Author | Age | Files | Lines |
... | |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
| |
local simplications off assumes.
llvm-svn: 370414
|
|
|
|
|
|
| |
Goes with the proposal in D66965.
llvm-svn: 370407
|
|
|
|
|
|
|
|
|
| |
Somewhat motivating case In PR43146:
https://bugs.llvm.org/show_bug.cgi?id=43146
But that's a lot more complicated.
llvm-svn: 370381
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
- Similar to the workaround in fix of PR30188, skip sinking common
lifetime markers of `alloca`. They are mostly left there after
inlining functions in branches.
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66950
llvm-svn: 370376
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
-phi-node-folding-threshold=3
This is the naive implementation of x86 BZHI/BEXTR instruction:
it takes input and bit count, and extracts low nbits up to bit width.
I.e. unlike shift it does not have any UB when nbits >= bitwidth.
Which means we don't need a while PHI here, simple select will do.
And if it's a select, it should then be trivial to fix codegen
to select it to BEXTR/BZHI.
See https://bugs.llvm.org/show_bug.cgi?id=34704
llvm-svn: 370369
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
`@llvm.umul.with.overflow` inverted overflow bit
Summary:
Now that with D65143/D65144 we've produce `@llvm.umul.with.overflow`,
and with D65147 we've flattened the CFG, we now can see that
the guard may have been there to prevent division by zero is redundant.
We can simply drop it:
```
----------------------------------------
Name: no overflow or zero
%iszero = icmp eq i4 %y, 0
%umul = smul_overflow i4 %x, %y
%umul.ov = extractvalue {i4, i1} %umul, 1
%umul.ov.not = xor %umul.ov, -1
%retval.0 = or i1 %iszero, %umul.ov.not
ret i1 %retval.0
=>
%iszero = icmp eq i4 %y, 0
%umul = smul_overflow i4 %x, %y
%umul.ov = extractvalue {i4, i1} %umul, 1
%umul.ov.not = xor %umul.ov, -1
%retval.0 = or i1 %iszero, %umul.ov.not
ret i1 %umul.ov.not
Done: 1
Optimization is correct!
```
Note that this is inverted from what we have in a previous patch,
here we are looking for the inverted overflow bit.
And that inversion is kinda problematic - given this particular
pattern we neither hoist that `not` closer to `ret` (then the pattern
would have been identical to the one without inversion,
and would have been handled by the previous patch), neither
do the opposite transform. But regardless, we should handle this too.
I've filled [[ https://bugs.llvm.org/show_bug.cgi?id=42720 | PR42720 ]].
Reviewers: nikic, spatel, xbolva00, RKSimon
Reviewed By: spatel
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65151
llvm-svn: 370351
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
`@llvm.umul.with.overflow` overflow bit
Summary:
Now that with D65143/D65144 we've produce `@llvm.umul.with.overflow`,
and with D65147 we've flattened the CFG, we now can see that
the guard may have been there to prevent division by zero is redundant.
We can simply drop it:
```
----------------------------------------
Name: no overflow and not zero
%iszero = icmp ne i4 %y, 0
%umul = umul_overflow i4 %x, %y
%umul.ov = extractvalue {i4, i1} %umul, 1
%retval.0 = and i1 %iszero, %umul.ov
ret i1 %retval.0
=>
%iszero = icmp ne i4 %y, 0
%umul = umul_overflow i4 %x, %y
%umul.ov = extractvalue {i4, i1} %umul, 1
%retval.0 = and i1 %iszero, %umul.ov
ret %umul.ov
Done: 1
Optimization is correct!
```
Reviewers: nikic, spatel, xbolva00
Reviewed By: spatel
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65150
llvm-svn: 370350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
hoist a 'not' from incoming values
Summary:
As it can be seen in the tests in D65143/D65144, even though we have formed an '@llvm.umul.with.overflow'
and got rid of potential for division-by-zero, the control flow remains, we still have that branch.
We have this condition:
```
// Don't fold i1 branches on PHIs which contain binary operators
// These can often be turned into switches and other things.
if (PN->getType()->isIntegerTy(1) &&
(isa<BinaryOperator>(PN->getIncomingValue(0)) ||
isa<BinaryOperator>(PN->getIncomingValue(1)) ||
isa<BinaryOperator>(IfCond)))
return false;
```
which was added back in rL121764 to help with `select` formation i think?
That check prevents us to flatten the CFG here, even though we know
we no longer need that guard and will be able to drop everything
but the '@llvm.umul.with.overflow' + `not`.
As it can be seen from tests, we end here because the `not` is being
sinked into the PHI's incoming values by InstCombine,
so we can't workaround this by hoisting it to after PHI.
Thus i suggest that we relax that check to not bailout if we'd get to hoist the `not`.
Reviewers: craig.topper, spatel, fhahn, nikic
Reviewed By: spatel
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65147
llvm-svn: 370349
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
overflow bit extraction
Summary:
`((%x * %y) u/ %x) != %y` is one of (3?) common ways to check that
some unsigned multiplication (will not) overflow.
Currently, we don't catch it. We could:
```
$ /repositories/alive2/build-Clang-unknown/alive -root-only ~/llvm-patch1.ll
Processing /home/lebedevri/llvm-patch1.ll..
----------------------------------------
Name: no overflow
%o0 = mul i4 %y, %x
%o1 = udiv i4 %o0, %x
%r = icmp ne i4 %o1, %y
ret i1 %r
=>
%n0 = umul_overflow i4 %x, %y
%o0 = extractvalue {i4, i1} %n0, 0
%o1 = udiv %o0, %x
%r = extractvalue {i4, i1} %n0, 1
ret %r
Done: 1
Optimization is correct!
----------------------------------------
Name: no overflow
%o0 = mul i4 %y, %x
%o1 = udiv i4 %o0, %x
%r = icmp eq i4 %o1, %y
ret i1 %r
=>
%n0 = umul_overflow i4 %x, %y
%o0 = extractvalue {i4, i1} %n0, 0
%o1 = udiv %o0, %x
%n1 = extractvalue {i4, i1} %n0, 1
%r = xor %n1, -1
ret i1 %r
Done: 1
Optimization is correct!
```
Reviewers: nikic, spatel, efriedma, xbolva00, RKSimon
Reviewed By: nikic
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65144
llvm-svn: 370348
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
overflow bit extraction
Summary:
`(-1 u/ %x) u< %y` is one of (3?) common ways to check that
some unsigned multiplication (will not) overflow.
Currently, we don't catch it. We could:
```
----------------------------------------
Name: no overflow
%o0 = udiv i4 -1, %x
%r = icmp ult i4 %o0, %y
=>
%o0 = udiv i4 -1, %x
%n0 = umul_overflow i4 %x, %y
%r = extractvalue {i4, i1} %n0, 1
Done: 1
Optimization is correct!
----------------------------------------
Name: no overflow, swapped
%o0 = udiv i4 -1, %x
%r = icmp ugt i4 %y, %o0
=>
%o0 = udiv i4 -1, %x
%n0 = umul_overflow i4 %x, %y
%r = extractvalue {i4, i1} %n0, 1
Done: 1
Optimization is correct!
----------------------------------------
Name: overflow
%o0 = udiv i4 -1, %x
%r = icmp uge i4 %o0, %y
=>
%o0 = udiv i4 -1, %x
%n0 = umul_overflow i4 %x, %y
%n1 = extractvalue {i4, i1} %n0, 1
%r = xor %n1, -1
Done: 1
Optimization is correct!
----------------------------------------
Name: overflow
%o0 = udiv i4 -1, %x
%r = icmp ule i4 %y, %o0
=>
%o0 = udiv i4 -1, %x
%n0 = umul_overflow i4 %x, %y
%n1 = extractvalue {i4, i1} %n0, 1
%r = xor %n1, -1
Done: 1
Optimization is correct!
```
As it can be observed from tests, while simply forming the `@llvm.umul.with.overflow`
is easy, if we were looking for the inverted answer, then more work needs to be done
to cleanup the now-pointless control-flow that was guarding against division-by-zero.
This is being addressed in follow-up patches.
Reviewers: nikic, spatel, efriedma, xbolva00, RKSimon
Reviewed By: nikic, xbolva00
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D65143
llvm-svn: 370347
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Finally, the fold i was looking forward to :)
The legality check is muddy, i doubt i've groked the full generalization,
but it handles all the cases i care about, and can come up with:
https://rise4fun.com/Alive/26j
I.e. we can perform the fold if **any** of the following is true:
* The shift amount is either zero or one less than widest bitwidth
* Either of the values being shifted has at most lowest bit set
* The value that is being shifted by `shl` (which is not truncated) should have no less leading zeros than the total shift amount;
* The value that is being shifted by `lshr` (which **is** truncated) should have no less leading zeros than the widest bit width minus total shift amount minus one
I strongly suspect there is some better generalization, but i'm not aware of it as of right now.
For now i also avoided using actual `computeKnownBits()`, but restricted it to constants.
Reviewers: spatel, nikic, xbolva00
Reviewed By: spatel
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66383
llvm-svn: 370324
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
This patch adds very basic deduction for noalias.
Reviewers: jdoerfert, sstefan1
Reviewed By: jdoerfert
Tags: LLVM
Differential Revision: https://reviews.llvm.org/D66207
llvm-svn: 370295
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
As dependences between abstract attributes can become stale, e.g., if
one was sufficient to imply another one at some point but it has since
been wakened to the point it is not usable for the formerly implied one.
To weed out spurious dependences, and thereby eliminate unneeded
updates, we introduce an option to determine how often the dependence
cache is cleared and recomputed during the fixpoint iteration.
Note that the initial value was determined such that we see a positive
result on our tests.
Differential Revision: https://reviews.llvm.org/D63315
llvm-svn: 370230
|
|
|
|
| |
llvm-svn: 370222
|
|
|
|
|
|
|
| |
Due to missing vector support in this function, recursion can
generate worse code in some cases.
llvm-svn: 370221
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Until we have proper call-site information we should not recompute
liveness and return information for each call site. This patch directly
uses the function versions and introduces TODOs at the usage sites.
The required iterations to get to the fixpoint are most of the time
reduced by this change and we always avoid work duplication.
Reviewers: sstefan1, uenoku
Subscribers: hiraditya, bollu, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66562
llvm-svn: 370208
|
|
|
|
|
|
|
|
|
|
|
|
| |
Allow vectorizing loops that have reductions when tail is folded by masking.
A select is introduced in VPlan, choosing between the last value carried by the
loop-exit/live-out instruction of the reduction, and the penultimate value
carried by the reduction phi, according to the "i < n" mask of fold-tail.
This select replaces the last value as the live-out value of the loop.
Differential Revision: https://reviews.llvm.org/D66720
llvm-svn: 370173
|
|
|
|
| |
llvm-svn: 370170
|
|
|
|
| |
llvm-svn: 370169
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Example
define dso_local noalias i8* @_Z6maixxnv() local_unnamed_addr #0 {
entry:
%call = tail call noalias dereferenceable_or_null(64) i8* @malloc(i64 64) #6
ret i8* %call
}
Reviewers: jdoerfert
Reviewed By: jdoerfert
Subscribers: aaron.ballman, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66651
llvm-svn: 370168
|
|
|
|
|
|
|
|
|
| |
signed,"
This reverts commit r370083 because it caused check-lld failures on
sanitizer-x86_64-linux-fast.
llvm-svn: 370142
|
|
|
|
|
|
| |
vector of pointers. Fix other portions.
llvm-svn: 370114
|
|
|
|
|
|
|
| |
This patch splats the scalar index if necessary before using it
in any integer casts or other arithmetic.
llvm-svn: 370112
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
process
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
|
|
|
|
|
|
| |
32 bit unsigned, and 64 bit pointers.
llvm-svn: 370083
|
|
|
|
| |
llvm-svn: 370046
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Handle pattern [0]:
int ctz(unsigned int a)
{
int c = __clz(a & -a);
return a ? 31 - c : c;
}
In reality, the compiler can generate much better code for cttz, so fold away this pattern.
https://godbolt.org/z/c5kPtV
[0] https://community.arm.com/community-help/f/discussions/2114/count-trailing-zeros
Reviewers: spatel, nikic, lebedev.ri, dmgreen, hfinkel
Reviewed By: hfinkel
Subscribers: hfinkel, javed.absar, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66308
llvm-svn: 370037
|
|
|
|
|
|
|
|
|
|
|
|
| |
Reviewers: lebedev.ri
Subscribers: llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66761
llvm-svn: 369996
|
|
|
|
|
|
|
|
|
|
|
|
| |
Reviewers: eugenis
Subscribers: hiraditya, cfe-commits, #sanitizers, llvm-commits
Tags: #clang, #sanitizers, #llvm
Differential Revision: https://reviews.llvm.org/D66695
llvm-svn: 369979
|
|
|
|
| |
llvm-svn: 369959
|
|
|
|
|
|
|
|
|
|
| |
for vectors
Extend the transform introduced in https://reviews.llvm.org/D66608 to work for vector geps as well.
Differential Revision: https://reviews.llvm.org/D66671
llvm-svn: 369949
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Try to verify how many iterations we need for a fixpoint in our tests.
This patch adjust the way we count to make it easier to follow. It also
adjusts the bounds to actually account for a fixpoint and not only the
minimum number to pass all checks.
Reviewers: uenoku, sstefan1
Subscribers: hiraditya, bollu, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66757
llvm-svn: 369945
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
By default, the Attributor tracks potential dependences between abstract
attributes based on the issued Attributor::getAAFor queries. This
simplifies the development of new abstract attributes but it can also
lead to spurious dependences that might increase compile time and make
internalization harder (D63312). With this patch, abstract attributes
can opt-out of implicit dependence tracking and instead register
dependences explicitly. It is up to the implementation to make sure all
existing dependences are registered.
Differential Revision: https://reviews.llvm.org/D63314
llvm-svn: 369935
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
When reconstructing the CFG of the loop after unrolling,
LoopUnroll could in some cases remove the phi operands of
loop-carried values instead of preserving them, resulting
in undef phi values after loop unrolling.
When doing this reconstruction, avoid removing incoming
phi values for phis in the successor blocks if the successor
is the block we are jumping to anyway.
Patch-by: ebevhan
Reviewers: fhahn, efriedma
Reviewed By: fhahn
Subscribers: bjope, lebedev.ri, zzheng, dmgreen, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66334
llvm-svn: 369886
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
`matchThreeWayIntCompare()` looks for
```
select i1 (a == b),
i32 Equal,
i32 (select i1 (a < b), i32 Less, i32 Greater)
```
but both of these selects/compares can be in it's commuted form,
so out of 8 variants, only the two most basic ones is handled.
This fixes regression being introduced in D66232.
Reviewers: spatel, nikic, efriedma, xbolva00
Reviewed By: spatel
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66607
llvm-svn: 369841
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
If we have e.g.:
```
%t = icmp ult i32 %x, 65536
%r = select i1 %t, i32 %y, i32 65535
```
the constants `65535` and `65536` are suspiciously close.
We could perform a transformation to deduplicate them:
```
Name: ult
%t = icmp ult i32 %x, 65536
%r = select i1 %t, i32 %y, i32 65535
=>
%t.inv = icmp ugt i32 %x, 65535
%r = select i1 %t.inv, i32 65535, i32 %y
```
https://rise4fun.com/Alive/avb
While this may seem esoteric, this should certainly be good for vectors
(less constant pool usage) and for opt-for-size - need to have only one constant.
But the real fun part here is that it allows further transformation,
in particular it finishes cleaning up the `clamp` folding,
see e.g. `canonicalize-clamp-with-select-of-constant-threshold-pattern.ll`.
We start with e.g.
```
%dont_need_to_clamp_positive = icmp sle i32 %X, 32767
%dont_need_to_clamp_negative = icmp sge i32 %X, -32768
%clamp_limit = select i1 %dont_need_to_clamp_positive, i32 -32768, i32 32767
%dont_need_to_clamp = and i1 %dont_need_to_clamp_positive, %dont_need_to_clamp_negative
%R = select i1 %dont_need_to_clamp, i32 %X, i32 %clamp_limit
```
without this patch we currently produce
```
%1 = icmp slt i32 %X, 32768
%2 = icmp sgt i32 %X, -32768
%3 = select i1 %2, i32 %X, i32 -32768
%R = select i1 %1, i32 %3, i32 32767
```
which isn't really a `clamp` - both comparisons are performed on the original value,
this patch changes it into
```
%1.inv = icmp sgt i32 %X, 32767
%2 = icmp sgt i32 %X, -32768
%3 = select i1 %2, i32 %X, i32 -32768
%R = select i1 %1.inv, i32 32767, i32 %3
```
and then the magic happens! Some further transform finishes polishing it and we finally get:
```
%t1 = icmp sgt i32 %X, -32768
%t2 = select i1 %t1, i32 %X, i32 -32768
%t3 = icmp slt i32 %t2, 32767
%R = select i1 %t3, i32 %t2, i32 32767
```
which is beautiful and just what we want.
Proofs for `getFlippedStrictnessPredicateAndConstant()` for de-canonicalization:
https://rise4fun.com/Alive/THl
Proofs for the fold itself: https://rise4fun.com/Alive/THl
Reviewers: spatel, dmgreen, nikic, xbolva00
Reviewed By: spatel
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66232
llvm-svn: 369840
|
|
|
|
| |
llvm-svn: 369839
|
|
|
|
| |
llvm-svn: 369831
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
We can now manifest alignment information in load/store instructions if
the pointer is known to have a better alignment.
Reviewers: uenoku, sstefan1, lebedev.ri
Subscribers: hiraditya, bollu, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66567
llvm-svn: 369804
|
|
|
|
|
|
|
|
|
|
|
|
| |
This is a patch split from https://reviews.llvm.org/D66374. It tries to add
a new format of profile called ExtBinary. The format adds a section header
table to the profile and organize the profile in sections, so the future
extension like adding a new section or extending an existing section will be
easier while keeping backward compatiblity feasible.
Differential Revision: https://reviews.llvm.org/D66513
llvm-svn: 369798
|
|
|
|
|
|
|
|
| |
Started implementing the vector case and realized the scalar case hadn't handled the GEP producing a different type than the base correctly. It's entertaining seeing what slips through review when we're focused on the 'hard' parts. :(
Also adding an extra vector test as it happened to be in workspace and wasn't worth separating.
llvm-svn: 369795
|
|
|
|
|
|
|
|
|
|
| |
This generalizes the isGEPKnownNonNull rule from ValueTracking to apply when we do not know if the base is non-null, and thus need to replace one condition with another.
The core notion is that since an inbounds GEP can only form null if the base pointer is null and the offset is zero. However, if the offset is non-zero, the the "inbounds" marker makes the result poison. Thus, we're free to ignore the case where the offset is non-zero. Similarly, there's no case under which a non-null base can result in a null result without generating poison.
Differential Revision: https://reviews.llvm.org/D66608
llvm-svn: 369789
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
If the unique return value is a constant we now replace call uses with
that constant.
Reviewers: sstefan1, uenoku
Subscribers: hiraditya, bollu, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66551
llvm-svn: 369785
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
If we have a loop in which the dereferenceability of a pointer decreases
we did slowly decrease it iteration by iteration, leading to a timeout.
With this patch we detect such circular reasoning and indicate a
fixpoint early.
Reviewers: uenoku, sstefan1
Subscribers: hiraditya, bollu, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66558
llvm-svn: 369784
|
|
|
|
|
|
| |
Differential Revision: https://reviews.llvm.org/D66612
llvm-svn: 369772
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
If we have a negative inbounds offset dereferenceabily "grows". However,
until we do not handle the overflow that can occur in the
dereferenceable bytes and the problem with loops, we simply do not grow
the state.
Reviewers: sstefan1, uenoku
Subscribers: hiraditya, bollu, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66557
llvm-svn: 369771
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
When we have new attributes and we end the fixpoint iteration because
the iteration limit is reached, we need to treat the new ones as if they
changed in the last iteration, as they might have.
This adds a test for which we should not derive anything regardless of
the iteration limit, e.g., if we abort there should not be any
attributes manifested in the IR.
Reviewers: uenoku, sstefan1
Subscribers: hiraditya, bollu, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D66549
llvm-svn: 369768
|
|
|
|
|
|
| |
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
|