RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
Code Issues Projects Releases Wiki Activity
747bfa048d
llvm-mirror/test/CodeGen/X86/fshl.ll
Roman Lebedev e207952556 [X86] Promote i8 CMOV's (PR40965) 
Summary:
@mclow.lists brought up this issue up in IRC, it came up during
implementation of libc++ `std::midpoint()` implementation (D59099)
https://godbolt.org/z/oLrHBP

Currently LLVM X86 backend only promotes i8 CMOV if it came from 2x`trunc`.
This differential proposes to always promote i8 CMOV.

There are several concerns here:
* Is this actually more performant, or is it just the ASM that looks cuter?
* Does this result in partial register stalls?
* What about branch predictor?

# Indeed, performance should be the main point here.
Let's look at a simple microbenchmark: {F8412076}
```
#include "benchmark/benchmark.h"

#include <algorithm>
#include <cmath>
#include <cstdint>
#include <iterator>
#include <limits>
#include <random>
#include <type_traits>
#include <utility>
#include <vector>

// Future preliminary libc++ code, from Marshall Clow.
namespace std {
template <class _Tp>
__inline _Tp midpoint(_Tp __a, _Tp __b) noexcept {
  using _Up = typename std::make_unsigned<typename remove_cv<_Tp>::type>::type;

  int __sign = 1;
  _Up __m = __a;
  _Up __M = __b;
  if (__a > __b) {
    __sign = -1;
    __m = __b;
    __M = __a;
  }
  return __a + __sign * _Tp(_Up(__M - __m) >> 1);
}
}  // namespace std

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 RandRand {
  template <typename T>
  static std::pair<std::vector<T>, std::vector<T>> Gen(size_t count) {
    return std::make_pair(getVectorOfRandomNumbers<T>(count),
                          getVectorOfRandomNumbers<T>(count));
  }
};
struct ZeroRand {
  template <typename T>
  static std::pair<std::vector<T>, std::vector<T>> Gen(size_t count) {
    return std::make_pair(std::vector<T>(count, T(0)),
                          getVectorOfRandomNumbers<T>(count));
  }
};

template <class T, class Gen>
void BM_StdMidpoint(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) {
    for (size_t i = 0; i < Length; i++) {
      const auto calculated = std::midpoint(a[i], b[i]);
      benchmark::DoNotOptimize(calculated);
    }
  }
  state.SetComplexityN(Length);
  state.counters["midpoints"] =
      benchmark::Counter(Length, benchmark::Counter::kIsIterationInvariant);
  state.counters["midpoints/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 = 2 * 1024 * 1024;
  // 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);
}

// Both of the values are random.
// The comparison is unpredictable.
BENCHMARK_TEMPLATE(BM_StdMidpoint, int32_t, RandRand)
    ->Apply(CustomArguments<int32_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, uint32_t, RandRand)
    ->Apply(CustomArguments<uint32_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, int64_t, RandRand)
    ->Apply(CustomArguments<int64_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, uint64_t, RandRand)
    ->Apply(CustomArguments<uint64_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, int16_t, RandRand)
    ->Apply(CustomArguments<int16_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, uint16_t, RandRand)
    ->Apply(CustomArguments<uint16_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, int8_t, RandRand)
    ->Apply(CustomArguments<int8_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, uint8_t, RandRand)
    ->Apply(CustomArguments<uint8_t>);

// One value is always zero, and another is bigger or equal than zero.
// The comparison is predictable.
BENCHMARK_TEMPLATE(BM_StdMidpoint, uint32_t, ZeroRand)
    ->Apply(CustomArguments<uint32_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, uint64_t, ZeroRand)
    ->Apply(CustomArguments<uint64_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, uint16_t, ZeroRand)
    ->Apply(CustomArguments<uint16_t>);
BENCHMARK_TEMPLATE(BM_StdMidpoint, uint8_t, ZeroRand)
    ->Apply(CustomArguments<uint8_t>);
```

```
$ ~/src/googlebenchmark/tools/compare.py --no-utest benchmarks ./llvm-cmov-bench-OLD ./llvm-cmov-bench-NEW
RUNNING: ./llvm-cmov-bench-OLD --benchmark_out=/tmp/tmp5a5qjm
2019-03-06 21:53:31
Running ./llvm-cmov-bench-OLD
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: 1.78, 1.81, 1.36
----------------------------------------------------------------------------------------------------
Benchmark                                          Time             CPU   Iterations UserCounters<...>
----------------------------------------------------------------------------------------------------
<...>
BM_StdMidpoint<int32_t, RandRand>/131072      300398 ns       300404 ns         2330 bytes_read/iteration=1024k bytes_read/sec=3.25083G/s midpoints=305.398M midpoints/sec=436.319M/s
BM_StdMidpoint<int32_t, RandRand>_BigO          2.29 N          2.29 N
BM_StdMidpoint<int32_t, RandRand>_RMS              2 %             2 %
<...>
BM_StdMidpoint<uint32_t, RandRand>/131072     300433 ns       300433 ns         2330 bytes_read/iteration=1024k bytes_read/sec=3.25052G/s midpoints=305.398M midpoints/sec=436.278M/s
BM_StdMidpoint<uint32_t, RandRand>_BigO         2.29 N          2.29 N
BM_StdMidpoint<uint32_t, RandRand>_RMS             2 %             2 %
<...>
BM_StdMidpoint<int64_t, RandRand>/65536       169857 ns       169858 ns         4121 bytes_read/iteration=1024k bytes_read/sec=5.74929G/s midpoints=270.074M midpoints/sec=385.828M/s
BM_StdMidpoint<int64_t, RandRand>_BigO          2.59 N          2.59 N
BM_StdMidpoint<int64_t, RandRand>_RMS              3 %             3 %
<...>
BM_StdMidpoint<uint64_t, RandRand>/65536      169770 ns       169771 ns         4125 bytes_read/iteration=1024k bytes_read/sec=5.75223G/s midpoints=270.336M midpoints/sec=386.026M/s
BM_StdMidpoint<uint64_t, RandRand>_BigO         2.59 N          2.59 N
BM_StdMidpoint<uint64_t, RandRand>_RMS             3 %             3 %
<...>
BM_StdMidpoint<int16_t, RandRand>/262144      591169 ns       591179 ns         1182 bytes_read/iteration=1024k bytes_read/sec=1.65189G/s midpoints=309.854M midpoints/sec=443.426M/s
BM_StdMidpoint<int16_t, RandRand>_BigO          2.25 N          2.25 N
BM_StdMidpoint<int16_t, RandRand>_RMS              1 %             1 %
<...>
BM_StdMidpoint<uint16_t, RandRand>/262144     591264 ns       591274 ns         1184 bytes_read/iteration=1024k bytes_read/sec=1.65162G/s midpoints=310.378M midpoints/sec=443.354M/s
BM_StdMidpoint<uint16_t, RandRand>_BigO         2.25 N          2.25 N
BM_StdMidpoint<uint16_t, RandRand>_RMS             1 %             1 %
<...>
BM_StdMidpoint<int8_t, RandRand>/524288      2983669 ns      2983689 ns          235 bytes_read/iteration=1024k bytes_read/sec=335.156M/s midpoints=123.208M midpoints/sec=175.718M/s
BM_StdMidpoint<int8_t, RandRand>_BigO           5.69 N          5.69 N
BM_StdMidpoint<int8_t, RandRand>_RMS               0 %             0 %
<...>
BM_StdMidpoint<uint8_t, RandRand>/524288     2668398 ns      2668419 ns          262 bytes_read/iteration=1024k bytes_read/sec=374.754M/s midpoints=137.363M midpoints/sec=196.479M/s
BM_StdMidpoint<uint8_t, RandRand>_BigO          5.09 N          5.09 N
BM_StdMidpoint<uint8_t, RandRand>_RMS              0 %             0 %
<...>
BM_StdMidpoint<uint32_t, ZeroRand>/131072     300887 ns       300887 ns         2331 bytes_read/iteration=1024k bytes_read/sec=3.24561G/s midpoints=305.529M midpoints/sec=435.619M/s
BM_StdMidpoint<uint32_t, ZeroRand>_BigO         2.29 N          2.29 N
BM_StdMidpoint<uint32_t, ZeroRand>_RMS             2 %             2 %
<...>
BM_StdMidpoint<uint64_t, ZeroRand>/65536      169634 ns       169634 ns         4102 bytes_read/iteration=1024k bytes_read/sec=5.75688G/s midpoints=268.829M midpoints/sec=386.338M/s
BM_StdMidpoint<uint64_t, ZeroRand>_BigO         2.59 N          2.59 N
BM_StdMidpoint<uint64_t, ZeroRand>_RMS             3 %             3 %
<...>
BM_StdMidpoint<uint16_t, ZeroRand>/262144     592252 ns       592255 ns         1182 bytes_read/iteration=1024k bytes_read/sec=1.64889G/s midpoints=309.854M midpoints/sec=442.62M/s
BM_StdMidpoint<uint16_t, ZeroRand>_BigO         2.26 N          2.26 N
BM_StdMidpoint<uint16_t, ZeroRand>_RMS             1 %             1 %
<...>
BM_StdMidpoint<uint8_t, ZeroRand>/524288      987295 ns       987309 ns          711 bytes_read/iteration=1024k bytes_read/sec=1012.85M/s midpoints=372.769M midpoints/sec=531.028M/s
BM_StdMidpoint<uint8_t, ZeroRand>_BigO          1.88 N          1.88 N
BM_StdMidpoint<uint8_t, ZeroRand>_RMS              1 %             1 %
RUNNING: ./llvm-cmov-bench-NEW --benchmark_out=/tmp/tmpPvwpfW
2019-03-06 21:56:58
Running ./llvm-cmov-bench-NEW
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: 1.17, 1.46, 1.30
----------------------------------------------------------------------------------------------------
Benchmark                                          Time             CPU   Iterations UserCounters<...>
----------------------------------------------------------------------------------------------------
<...>
BM_StdMidpoint<int32_t, RandRand>/131072      300878 ns       300880 ns         2324 bytes_read/iteration=1024k bytes_read/sec=3.24569G/s midpoints=304.611M midpoints/sec=435.629M/s
BM_StdMidpoint<int32_t, RandRand>_BigO          2.29 N          2.29 N
BM_StdMidpoint<int32_t, RandRand>_RMS              2 %             2 %
<...>
BM_StdMidpoint<uint32_t, RandRand>/131072     300231 ns       300226 ns         2330 bytes_read/iteration=1024k bytes_read/sec=3.25276G/s midpoints=305.398M midpoints/sec=436.578M/s
BM_StdMidpoint<uint32_t, RandRand>_BigO         2.29 N          2.29 N
BM_StdMidpoint<uint32_t, RandRand>_RMS             2 %             2 %
<...>
BM_StdMidpoint<int64_t, RandRand>/65536       170819 ns       170777 ns         4115 bytes_read/iteration=1024k bytes_read/sec=5.71835G/s midpoints=269.681M midpoints/sec=383.752M/s
BM_StdMidpoint<int64_t, RandRand>_BigO          2.60 N          2.60 N
BM_StdMidpoint<int64_t, RandRand>_RMS              3 %             3 %
<...>
BM_StdMidpoint<uint64_t, RandRand>/65536      171705 ns       171708 ns         4106 bytes_read/iteration=1024k bytes_read/sec=5.68733G/s midpoints=269.091M midpoints/sec=381.671M/s
BM_StdMidpoint<uint64_t, RandRand>_BigO         2.62 N          2.62 N
BM_StdMidpoint<uint64_t, RandRand>_RMS             3 %             3 %
<...>
BM_StdMidpoint<int16_t, RandRand>/262144      592510 ns       592516 ns         1182 bytes_read/iteration=1024k bytes_read/sec=1.64816G/s midpoints=309.854M midpoints/sec=442.425M/s
BM_StdMidpoint<int16_t, RandRand>_BigO          2.26 N          2.26 N
BM_StdMidpoint<int16_t, RandRand>_RMS              1 %             1 %
<...>
BM_StdMidpoint<uint16_t, RandRand>/262144     614823 ns       614823 ns         1180 bytes_read/iteration=1024k bytes_read/sec=1.58836G/s midpoints=309.33M midpoints/sec=426.373M/s
BM_StdMidpoint<uint16_t, RandRand>_BigO         2.33 N          2.33 N
BM_StdMidpoint<uint16_t, RandRand>_RMS             4 %             4 %
<...>
BM_StdMidpoint<int8_t, RandRand>/524288      1073181 ns      1073201 ns          650 bytes_read/iteration=1024k bytes_read/sec=931.791M/s midpoints=340.787M midpoints/sec=488.527M/s
BM_StdMidpoint<int8_t, RandRand>_BigO           2.05 N          2.05 N
BM_StdMidpoint<int8_t, RandRand>_RMS               1 %             1 %
BM_StdMidpoint<uint8_t, RandRand>/524288     1071010 ns      1071020 ns          653 bytes_read/iteration=1024k bytes_read/sec=933.689M/s midpoints=342.36M midpoints/sec=489.522M/s
BM_StdMidpoint<uint8_t, RandRand>_BigO          2.05 N          2.05 N
BM_StdMidpoint<uint8_t, RandRand>_RMS              1 %             1 %
<...>
BM_StdMidpoint<uint32_t, ZeroRand>/131072     300413 ns       300416 ns         2330 bytes_read/iteration=1024k bytes_read/sec=3.2507G/s midpoints=305.398M midpoints/sec=436.302M/s
BM_StdMidpoint<uint32_t, ZeroRand>_BigO         2.29 N          2.29 N
BM_StdMidpoint<uint32_t, ZeroRand>_RMS             2 %             2 %
<...>
BM_StdMidpoint<uint64_t, ZeroRand>/65536      169667 ns       169669 ns         4123 bytes_read/iteration=1024k bytes_read/sec=5.75568G/s midpoints=270.205M midpoints/sec=386.257M/s
BM_StdMidpoint<uint64_t, ZeroRand>_BigO         2.59 N          2.59 N
BM_StdMidpoint<uint64_t, ZeroRand>_RMS             3 %             3 %
<...>
BM_StdMidpoint<uint16_t, ZeroRand>/262144     591396 ns       591404 ns         1184 bytes_read/iteration=1024k bytes_read/sec=1.65126G/s midpoints=310.378M midpoints/sec=443.257M/s
BM_StdMidpoint<uint16_t, ZeroRand>_BigO         2.26 N          2.26 N
BM_StdMidpoint<uint16_t, ZeroRand>_RMS             1 %             1 %
<...>
BM_StdMidpoint<uint8_t, ZeroRand>/524288     1069421 ns      1069413 ns          655 bytes_read/iteration=1024k bytes_read/sec=935.092M/s midpoints=343.409M midpoints/sec=490.258M/s
BM_StdMidpoint<uint8_t, ZeroRand>_BigO          2.04 N          2.04 N
BM_StdMidpoint<uint8_t, ZeroRand>_RMS              0 %             0 %
Comparing ./llvm-cmov-bench-OLD to ./llvm-cmov-bench-NEW
Benchmark                                                   Time             CPU      Time Old      Time New       CPU Old       CPU New
----------------------------------------------------------------------------------------------------------------------------------------
<...>
BM_StdMidpoint<int32_t, RandRand>/131072                 +0.0016         +0.0016        300398        300878        300404        300880
<...>
BM_StdMidpoint<uint32_t, RandRand>/131072                -0.0007         -0.0007        300433        300231        300433        300226
<...>
BM_StdMidpoint<int64_t, RandRand>/65536                  +0.0057         +0.0054        169857        170819        169858        170777
<...>
BM_StdMidpoint<uint64_t, RandRand>/65536                 +0.0114         +0.0114        169770        171705        169771        171708
<...>
BM_StdMidpoint<int16_t, RandRand>/262144                 +0.0023         +0.0023        591169        592510        591179        592516
<...>
BM_StdMidpoint<uint16_t, RandRand>/262144                +0.0398         +0.0398        591264        614823        591274        614823
<...>
BM_StdMidpoint<int8_t, RandRand>/524288                  -0.6403         -0.6403       2983669       1073181       2983689       1073201
<...>
BM_StdMidpoint<uint8_t, RandRand>/524288                 -0.5986         -0.5986       2668398       1071010       2668419       1071020
<...>
BM_StdMidpoint<uint32_t, ZeroRand>/131072                -0.0016         -0.0016        300887        300413        300887        300416
<...>
BM_StdMidpoint<uint64_t, ZeroRand>/65536                 +0.0002         +0.0002        169634        169667        169634        169669
<...>
BM_StdMidpoint<uint16_t, ZeroRand>/262144                -0.0014         -0.0014        592252        591396        592255        591404
<...>
BM_StdMidpoint<uint8_t, ZeroRand>/524288                 +0.0832         +0.0832        987295       1069421        987309       1069413
```

What can we tell from the benchmark?
* `BM_StdMidpoint<[u]int8_t, RandRand>` indeed has the worst performance.
* All `BM_StdMidpoint<uint{8,16,32}_t, ZeroRand>` are all performant, even the 8-bit case.
  That is because there we are computing mid point between zero and some random number,
  thus if the branch predictor is in use, it is in optimal situation.
* Promoting 8-bit CMOV did improve performance of `BM_StdMidpoint<[u]int8_t, RandRand>`, by -59%..-64%.

# What about branch predictor?
* `BM_StdMidpoint<uint8_t, ZeroRand>` was faster than `BM_StdMidpoint<uint{16,32,64}_t, ZeroRand>`,
  which may mean that well-predicted branch is better than `cmov`.
* Promoting 8-bit CMOV degraded performance of `BM_StdMidpoint<uint8_t, ZeroRand>`,
  `cmov` is up to +10% worse than well-predicted branch.
* However, i do not believe this is a concern. If the branch is well predicted,  then the PGO
  will also say that it is well predicted, and LLVM will happily expand cmov back into branch:
  https://godbolt.org/z/P5ufig

# What about partial register stalls?
I'm not really able to answer that.
What i can say is that if the branch is unpredictable (if it is predictable, then use PGO and you'll have branch)
in ~50% of cases you will have to pay branch misprediction penalty.
```
$ grep -i MispredictPenalty X86Sched*.td
X86SchedBroadwell.td:  let MispredictPenalty = 16;
X86SchedHaswell.td:  let MispredictPenalty = 16;
X86SchedSandyBridge.td:  let MispredictPenalty = 16;
X86SchedSkylakeClient.td:  let MispredictPenalty = 14;
X86SchedSkylakeServer.td:  let MispredictPenalty = 14;
X86ScheduleBdVer2.td:  let MispredictPenalty = 20; // Minimum branch misdirection penalty.
X86ScheduleBtVer2.td:  let MispredictPenalty = 14; // Minimum branch misdirection penalty
X86ScheduleSLM.td:  let MispredictPenalty = 10;
X86ScheduleZnver1.td:  let MispredictPenalty = 17;
```
.. which it can be as small as 10 cycles and as large as 20 cycles.
Partial register stalls do not seem to be an issue for AMD CPU's.
For intel CPU's, they should be around ~5 cycles?
Is that actually an issue here? I'm not sure.

In short, i'd say this is an improvement, at least on this microbenchmark.

Fixes [[ https://bugs.llvm.org/show_bug.cgi?id=40965 | PR40965 ]].

Reviewers: craig.topper, RKSimon, spatel, andreadb, nikic

Reviewed By: craig.topper, andreadb

Subscribers: jfb, jdoerfert, llvm-commits, mclow.lists

Tags: #llvm, #libc

Differential Revision: https://reviews.llvm.org/D59035

llvm-svn: 356300
2019-03-15 21:17:53 +00:00

506 lines
16 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefixes=CHECK,X86,X86-FAST
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+slow-shld | FileCheck %s --check-prefixes=CHECK,X86,X86-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefixes=CHECK,X64,X64-FAST
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+slow-shld | FileCheck %s --check-prefixes=CHECK,X64,X64-SLOW
declare i8 @llvm.fshl.i8(i8, i8, i8) nounwind readnone
declare i16 @llvm.fshl.i16(i16, i16, i16) nounwind readnone
declare i32 @llvm.fshl.i32(i32, i32, i32) nounwind readnone
declare i64 @llvm.fshl.i64(i64, i64, i64) nounwind readnone
;
; Variable Funnel Shift
;
define i8 @var_shift_i8(i8 %x, i8 %y, i8 %z) nounwind {
; X86-LABEL: var_shift_i8:
; X86: # %bb.0:
; X86-NEXT: movb {{[0-9]+}}(%esp), %ah
; X86-NEXT: movb {{[0-9]+}}(%esp), %al
; X86-NEXT: movb {{[0-9]+}}(%esp), %dl
; X86-NEXT: andb $7, %dl
; X86-NEXT: movb %al, %ch
; X86-NEXT: movb %dl, %cl
; X86-NEXT: shlb %cl, %ch
; X86-NEXT: movb $8, %cl
; X86-NEXT: subb %dl, %cl
; X86-NEXT: shrb %cl, %ah
; X86-NEXT: testb %dl, %dl
; X86-NEXT: je .LBB0_2
; X86-NEXT: # %bb.1:
; X86-NEXT: orb %ah, %ch
; X86-NEXT: movb %ch, %al
; X86-NEXT: .LBB0_2:
; X86-NEXT: retl
;
; X64-LABEL: var_shift_i8:
; X64: # %bb.0:
; X64-NEXT: andb $7, %dl
; X64-NEXT: movl %edi, %eax
; X64-NEXT: movl %edx, %ecx
; X64-NEXT: shlb %cl, %al
; X64-NEXT: movb $8, %cl
; X64-NEXT: subb %dl, %cl
; X64-NEXT: shrb %cl, %sil
; X64-NEXT: orb %al, %sil
; X64-NEXT: movzbl %sil, %eax
; X64-NEXT: testb %dl, %dl
; X64-NEXT: cmovel %edi, %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
%tmp = tail call i8 @llvm.fshl.i8(i8 %x, i8 %y, i8 %z)
ret i8 %tmp
}
define i16 @var_shift_i16(i16 %x, i16 %y, i16 %z) nounwind {
; X86-FAST-LABEL: var_shift_i16:
; X86-FAST: # %bb.0:
; X86-FAST-NEXT: movzwl {{[0-9]+}}(%esp), %edx
; X86-FAST-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X86-FAST-NEXT: movb {{[0-9]+}}(%esp), %cl
; X86-FAST-NEXT: andb $15, %cl
; X86-FAST-NEXT: shldw %cl, %dx, %ax
; X86-FAST-NEXT: retl
;
; X86-SLOW-LABEL: var_shift_i16:
; X86-SLOW: # %bb.0:
; X86-SLOW-NEXT: pushl %edi
; X86-SLOW-NEXT: pushl %esi
; X86-SLOW-NEXT: movzwl {{[0-9]+}}(%esp), %esi
; X86-SLOW-NEXT: movb {{[0-9]+}}(%esp), %dl
; X86-SLOW-NEXT: andb $15, %dl
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SLOW-NEXT: movl %eax, %edi
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shll %cl, %edi
; X86-SLOW-NEXT: movb $16, %cl
; X86-SLOW-NEXT: subb %dl, %cl
; X86-SLOW-NEXT: shrl %cl, %esi
; X86-SLOW-NEXT: testb %dl, %dl
; X86-SLOW-NEXT: je .LBB1_2
; X86-SLOW-NEXT: # %bb.1:
; X86-SLOW-NEXT: orl %esi, %edi
; X86-SLOW-NEXT: movl %edi, %eax
; X86-SLOW-NEXT: .LBB1_2:
; X86-SLOW-NEXT: # kill: def $ax killed $ax killed $eax
; X86-SLOW-NEXT: popl %esi
; X86-SLOW-NEXT: popl %edi
; X86-SLOW-NEXT: retl
;
; X64-FAST-LABEL: var_shift_i16:
; X64-FAST: # %bb.0:
; X64-FAST-NEXT: movl %edx, %ecx
; X64-FAST-NEXT: movl %edi, %eax
; X64-FAST-NEXT: andb $15, %cl
; X64-FAST-NEXT: # kill: def $cl killed $cl killed $ecx
; X64-FAST-NEXT: shldw %cl, %si, %ax
; X64-FAST-NEXT: # kill: def $ax killed $ax killed $eax
; X64-FAST-NEXT: retq
;
; X64-SLOW-LABEL: var_shift_i16:
; X64-SLOW: # %bb.0:
; X64-SLOW-NEXT: movzwl %si, %eax
; X64-SLOW-NEXT: andb $15, %dl
; X64-SLOW-NEXT: movl %edi, %esi
; X64-SLOW-NEXT: movl %edx, %ecx
; X64-SLOW-NEXT: shll %cl, %esi
; X64-SLOW-NEXT: movb $16, %cl
; X64-SLOW-NEXT: subb %dl, %cl
; X64-SLOW-NEXT: shrl %cl, %eax
; X64-SLOW-NEXT: orl %esi, %eax
; X64-SLOW-NEXT: testb %dl, %dl
; X64-SLOW-NEXT: cmovel %edi, %eax
; X64-SLOW-NEXT: # kill: def $ax killed $ax killed $eax
; X64-SLOW-NEXT: retq
%tmp = tail call i16 @llvm.fshl.i16(i16 %x, i16 %y, i16 %z)
ret i16 %tmp
}
define i32 @var_shift_i32(i32 %x, i32 %y, i32 %z) nounwind {
; X86-FAST-LABEL: var_shift_i32:
; X86-FAST: # %bb.0:
; X86-FAST-NEXT: movb {{[0-9]+}}(%esp), %cl
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-FAST-NEXT: shldl %cl, %edx, %eax
; X86-FAST-NEXT: retl
;
; X86-SLOW-LABEL: var_shift_i32:
; X86-SLOW: # %bb.0:
; X86-SLOW-NEXT: pushl %edi
; X86-SLOW-NEXT: pushl %esi
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-SLOW-NEXT: movb {{[0-9]+}}(%esp), %dl
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SLOW-NEXT: movl %eax, %edi
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: shll %cl, %edi
; X86-SLOW-NEXT: andb $31, %dl
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: negb %cl
; X86-SLOW-NEXT: shrl %cl, %esi
; X86-SLOW-NEXT: testb %dl, %dl
; X86-SLOW-NEXT: je .LBB2_2
; X86-SLOW-NEXT: # %bb.1:
; X86-SLOW-NEXT: orl %esi, %edi
; X86-SLOW-NEXT: movl %edi, %eax
; X86-SLOW-NEXT: .LBB2_2:
; X86-SLOW-NEXT: popl %esi
; X86-SLOW-NEXT: popl %edi
; X86-SLOW-NEXT: retl
;
; X64-FAST-LABEL: var_shift_i32:
; X64-FAST: # %bb.0:
; X64-FAST-NEXT: movl %edx, %ecx
; X64-FAST-NEXT: movl %edi, %eax
; X64-FAST-NEXT: # kill: def $cl killed $cl killed $ecx
; X64-FAST-NEXT: shldl %cl, %esi, %eax
; X64-FAST-NEXT: retq
;
; X64-SLOW-LABEL: var_shift_i32:
; X64-SLOW: # %bb.0:
; X64-SLOW-NEXT: movl %esi, %eax
; X64-SLOW-NEXT: movl %edi, %esi
; X64-SLOW-NEXT: movl %edx, %ecx
; X64-SLOW-NEXT: shll %cl, %esi
; X64-SLOW-NEXT: andb $31, %dl
; X64-SLOW-NEXT: movl %edx, %ecx
; X64-SLOW-NEXT: negb %cl
; X64-SLOW-NEXT: shrl %cl, %eax
; X64-SLOW-NEXT: orl %esi, %eax
; X64-SLOW-NEXT: testb %dl, %dl
; X64-SLOW-NEXT: cmovel %edi, %eax
; X64-SLOW-NEXT: retq
%tmp = tail call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 %z)
ret i32 %tmp
}
define i32 @var_shift_i32_optsize(i32 %x, i32 %y, i32 %z) nounwind optsize {
; X86-LABEL: var_shift_i32_optsize:
; X86: # %bb.0:
; X86-NEXT: movb {{[0-9]+}}(%esp), %cl
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: shldl %cl, %edx, %eax
; X86-NEXT: retl
;
; X64-LABEL: var_shift_i32_optsize:
; X64: # %bb.0:
; X64-NEXT: movl %edx, %ecx
; X64-NEXT: movl %edi, %eax
; X64-NEXT: # kill: def $cl killed $cl killed $ecx
; X64-NEXT: shldl %cl, %esi, %eax
; X64-NEXT: retq
%tmp = tail call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 %z)
ret i32 %tmp
}
define i64 @var_shift_i64(i64 %x, i64 %y, i64 %z) nounwind {
; X86-FAST-LABEL: var_shift_i64:
; X86-FAST: # %bb.0:
; X86-FAST-NEXT: pushl %ebp
; X86-FAST-NEXT: pushl %ebx
; X86-FAST-NEXT: pushl %edi
; X86-FAST-NEXT: pushl %esi
; X86-FAST-NEXT: pushl %eax
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-FAST-NEXT: movl %eax, (%esp) # 4-byte Spill
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %ebp
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X86-FAST-NEXT: andl $63, %ebx
; X86-FAST-NEXT: movl %eax, %edi
; X86-FAST-NEXT: movl %ebx, %ecx
; X86-FAST-NEXT: shll %cl, %edi
; X86-FAST-NEXT: shldl %cl, %eax, %ebp
; X86-FAST-NEXT: testb $32, %bl
; X86-FAST-NEXT: je .LBB4_2
; X86-FAST-NEXT: # %bb.1:
; X86-FAST-NEXT: movl %edi, %ebp
; X86-FAST-NEXT: xorl %edi, %edi
; X86-FAST-NEXT: .LBB4_2:
; X86-FAST-NEXT: movb $64, %cl
; X86-FAST-NEXT: subb %bl, %cl
; X86-FAST-NEXT: movl %edx, %esi
; X86-FAST-NEXT: shrl %cl, %esi
; X86-FAST-NEXT: shrdl %cl, %edx, (%esp) # 4-byte Folded Spill
; X86-FAST-NEXT: testb $32, %cl
; X86-FAST-NEXT: jne .LBB4_3
; X86-FAST-NEXT: # %bb.4:
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-FAST-NEXT: movl (%esp), %ecx # 4-byte Reload
; X86-FAST-NEXT: testl %ebx, %ebx
; X86-FAST-NEXT: jne .LBB4_6
; X86-FAST-NEXT: jmp .LBB4_7
; X86-FAST-NEXT: .LBB4_3:
; X86-FAST-NEXT: movl %esi, %ecx
; X86-FAST-NEXT: xorl %esi, %esi
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-FAST-NEXT: testl %ebx, %ebx
; X86-FAST-NEXT: je .LBB4_7
; X86-FAST-NEXT: .LBB4_6:
; X86-FAST-NEXT: orl %esi, %ebp
; X86-FAST-NEXT: orl %ecx, %edi
; X86-FAST-NEXT: movl %edi, %eax
; X86-FAST-NEXT: movl %ebp, %edx
; X86-FAST-NEXT: .LBB4_7:
; X86-FAST-NEXT: addl $4, %esp
; X86-FAST-NEXT: popl %esi
; X86-FAST-NEXT: popl %edi
; X86-FAST-NEXT: popl %ebx
; X86-FAST-NEXT: popl %ebp
; X86-FAST-NEXT: retl
;
; X86-SLOW-LABEL: var_shift_i64:
; X86-SLOW: # %bb.0:
; X86-SLOW-NEXT: pushl %ebp
; X86-SLOW-NEXT: pushl %ebx
; X86-SLOW-NEXT: pushl %edi
; X86-SLOW-NEXT: pushl %esi
; X86-SLOW-NEXT: subl $8, %esp
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %ebx
; X86-SLOW-NEXT: andl $63, %ebx
; X86-SLOW-NEXT: movb $64, %dh
; X86-SLOW-NEXT: subb %bl, %dh
; X86-SLOW-NEXT: movl %eax, (%esp) # 4-byte Spill
; X86-SLOW-NEXT: movb %dh, %cl
; X86-SLOW-NEXT: shrl %cl, %eax
; X86-SLOW-NEXT: movb %dh, %dl
; X86-SLOW-NEXT: andb $31, %dl
; X86-SLOW-NEXT: movl %edx, %ecx
; X86-SLOW-NEXT: negb %cl
; X86-SLOW-NEXT: movl %esi, %ebp
; X86-SLOW-NEXT: shll %cl, %ebp
; X86-SLOW-NEXT: testb %dl, %dl
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SLOW-NEXT: movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: je .LBB4_2
; X86-SLOW-NEXT: # %bb.1:
; X86-SLOW-NEXT: orl %eax, %ebp
; X86-SLOW-NEXT: movl %ebp, (%esp) # 4-byte Spill
; X86-SLOW-NEXT: .LBB4_2:
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %ebp
; X86-SLOW-NEXT: movl %ebp, %eax
; X86-SLOW-NEXT: movl %ebx, %ecx
; X86-SLOW-NEXT: shll %cl, %eax
; X86-SLOW-NEXT: movb %bl, %ch
; X86-SLOW-NEXT: andb $31, %ch
; X86-SLOW-NEXT: movb %ch, %cl
; X86-SLOW-NEXT: negb %cl
; X86-SLOW-NEXT: shrl %cl, %edi
; X86-SLOW-NEXT: testb %ch, %ch
; X86-SLOW-NEXT: je .LBB4_4
; X86-SLOW-NEXT: # %bb.3:
; X86-SLOW-NEXT: orl %edi, %eax
; X86-SLOW-NEXT: movl %eax, %ebp
; X86-SLOW-NEXT: .LBB4_4:
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SLOW-NEXT: movl %eax, %edi
; X86-SLOW-NEXT: movl %ebx, %ecx
; X86-SLOW-NEXT: shll %cl, %edi
; X86-SLOW-NEXT: testb $32, %bl
; X86-SLOW-NEXT: je .LBB4_6
; X86-SLOW-NEXT: # %bb.5:
; X86-SLOW-NEXT: movl %edi, %ebp
; X86-SLOW-NEXT: xorl %edi, %edi
; X86-SLOW-NEXT: .LBB4_6:
; X86-SLOW-NEXT: movb %dh, %cl
; X86-SLOW-NEXT: shrl %cl, %esi
; X86-SLOW-NEXT: testb $32, %dh
; X86-SLOW-NEXT: jne .LBB4_7
; X86-SLOW-NEXT: # %bb.8:
; X86-SLOW-NEXT: movl (%esp), %ecx # 4-byte Reload
; X86-SLOW-NEXT: testl %ebx, %ebx
; X86-SLOW-NEXT: jne .LBB4_10
; X86-SLOW-NEXT: jmp .LBB4_11
; X86-SLOW-NEXT: .LBB4_7:
; X86-SLOW-NEXT: movl %esi, %ecx
; X86-SLOW-NEXT: xorl %esi, %esi
; X86-SLOW-NEXT: testl %ebx, %ebx
; X86-SLOW-NEXT: je .LBB4_11
; X86-SLOW-NEXT: .LBB4_10:
; X86-SLOW-NEXT: orl %esi, %ebp
; X86-SLOW-NEXT: orl %ecx, %edi
; X86-SLOW-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-SLOW-NEXT: movl %edi, %eax
; X86-SLOW-NEXT: .LBB4_11:
; X86-SLOW-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Reload
; X86-SLOW-NEXT: addl $8, %esp
; X86-SLOW-NEXT: popl %esi
; X86-SLOW-NEXT: popl %edi
; X86-SLOW-NEXT: popl %ebx
; X86-SLOW-NEXT: popl %ebp
; X86-SLOW-NEXT: retl
;
; X64-FAST-LABEL: var_shift_i64:
; X64-FAST: # %bb.0:
; X64-FAST-NEXT: movq %rdx, %rcx
; X64-FAST-NEXT: movq %rdi, %rax
; X64-FAST-NEXT: # kill: def $cl killed $cl killed $rcx
; X64-FAST-NEXT: shldq %cl, %rsi, %rax
; X64-FAST-NEXT: retq
;
; X64-SLOW-LABEL: var_shift_i64:
; X64-SLOW: # %bb.0:
; X64-SLOW-NEXT: movq %rsi, %rax
; X64-SLOW-NEXT: movq %rdi, %rsi
; X64-SLOW-NEXT: movl %edx, %ecx
; X64-SLOW-NEXT: shlq %cl, %rsi
; X64-SLOW-NEXT: andb $63, %dl
; X64-SLOW-NEXT: movl %edx, %ecx
; X64-SLOW-NEXT: negb %cl
; X64-SLOW-NEXT: shrq %cl, %rax
; X64-SLOW-NEXT: orq %rsi, %rax
; X64-SLOW-NEXT: testb %dl, %dl
; X64-SLOW-NEXT: cmoveq %rdi, %rax
; X64-SLOW-NEXT: retq
%tmp = tail call i64 @llvm.fshl.i64(i64 %x, i64 %y, i64 %z)
ret i64 %tmp
}
;
; Const Funnel Shift
;
define i8 @const_shift_i8(i8 %x, i8 %y) nounwind {
; X86-LABEL: const_shift_i8:
; X86: # %bb.0:
; X86-NEXT: movb {{[0-9]+}}(%esp), %al
; X86-NEXT: movb {{[0-9]+}}(%esp), %cl
; X86-NEXT: shrb %cl
; X86-NEXT: shlb $7, %al
; X86-NEXT: orb %cl, %al
; X86-NEXT: retl
;
; X64-LABEL: const_shift_i8:
; X64: # %bb.0:
; X64-NEXT: # kill: def $esi killed $esi def $rsi
; X64-NEXT: # kill: def $edi killed $edi def $rdi
; X64-NEXT: shrb %sil
; X64-NEXT: shlb $7, %dil
; X64-NEXT: leal (%rdi,%rsi), %eax
; X64-NEXT: # kill: def $al killed $al killed $eax
; X64-NEXT: retq
%tmp = tail call i8 @llvm.fshl.i8(i8 %x, i8 %y, i8 7)
ret i8 %tmp
}
define i16 @const_shift_i16(i16 %x, i16 %y) nounwind {
; X86-FAST-LABEL: const_shift_i16:
; X86-FAST: # %bb.0:
; X86-FAST-NEXT: movzwl {{[0-9]+}}(%esp), %ecx
; X86-FAST-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X86-FAST-NEXT: shldw $7, %cx, %ax
; X86-FAST-NEXT: retl
;
; X86-SLOW-LABEL: const_shift_i16:
; X86-SLOW: # %bb.0:
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SLOW-NEXT: movzwl {{[0-9]+}}(%esp), %ecx
; X86-SLOW-NEXT: shrl $9, %ecx
; X86-SLOW-NEXT: shll $7, %eax
; X86-SLOW-NEXT: orl %ecx, %eax
; X86-SLOW-NEXT: # kill: def $ax killed $ax killed $eax
; X86-SLOW-NEXT: retl
;
; X64-FAST-LABEL: const_shift_i16:
; X64-FAST: # %bb.0:
; X64-FAST-NEXT: movl %edi, %eax
; X64-FAST-NEXT: shldw $7, %si, %ax
; X64-FAST-NEXT: # kill: def $ax killed $ax killed $eax
; X64-FAST-NEXT: retq
;
; X64-SLOW-LABEL: const_shift_i16:
; X64-SLOW: # %bb.0:
; X64-SLOW-NEXT: movzwl %si, %eax
; X64-SLOW-NEXT: shll $7, %edi
; X64-SLOW-NEXT: shrl $9, %eax
; X64-SLOW-NEXT: orl %edi, %eax
; X64-SLOW-NEXT: # kill: def $ax killed $ax killed $eax
; X64-SLOW-NEXT: retq
%tmp = tail call i16 @llvm.fshl.i16(i16 %x, i16 %y, i16 7)
ret i16 %tmp
}
define i32 @const_shift_i32(i32 %x, i32 %y) nounwind {
; X86-FAST-LABEL: const_shift_i32:
; X86-FAST: # %bb.0:
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-FAST-NEXT: shldl $7, %ecx, %eax
; X86-FAST-NEXT: retl
;
; X86-SLOW-LABEL: const_shift_i32:
; X86-SLOW: # %bb.0:
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SLOW-NEXT: shrl $25, %ecx
; X86-SLOW-NEXT: shll $7, %eax
; X86-SLOW-NEXT: orl %ecx, %eax
; X86-SLOW-NEXT: retl
;
; X64-FAST-LABEL: const_shift_i32:
; X64-FAST: # %bb.0:
; X64-FAST-NEXT: movl %edi, %eax
; X64-FAST-NEXT: shldl $7, %esi, %eax
; X64-FAST-NEXT: retq
;
; X64-SLOW-LABEL: const_shift_i32:
; X64-SLOW: # %bb.0:
; X64-SLOW-NEXT: # kill: def $esi killed $esi def $rsi
; X64-SLOW-NEXT: # kill: def $edi killed $edi def $rdi
; X64-SLOW-NEXT: shrl $25, %esi
; X64-SLOW-NEXT: shll $7, %edi
; X64-SLOW-NEXT: leal (%rdi,%rsi), %eax
; X64-SLOW-NEXT: retq
%tmp = tail call i32 @llvm.fshl.i32(i32 %x, i32 %y, i32 7)
ret i32 %tmp
}
define i64 @const_shift_i64(i64 %x, i64 %y) nounwind {
; X86-FAST-LABEL: const_shift_i64:
; X86-FAST: # %bb.0:
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-FAST-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-FAST-NEXT: shrdl $25, %ecx, %eax
; X86-FAST-NEXT: shldl $7, %ecx, %edx
; X86-FAST-NEXT: retl
;
; X86-SLOW-LABEL: const_shift_i64:
; X86-SLOW: # %bb.0:
; X86-SLOW-NEXT: pushl %esi
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-SLOW-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-SLOW-NEXT: shrl $25, %esi
; X86-SLOW-NEXT: movl %ecx, %eax
; X86-SLOW-NEXT: shll $7, %eax
; X86-SLOW-NEXT: orl %esi, %eax
; X86-SLOW-NEXT: shrl $25, %ecx
; X86-SLOW-NEXT: shll $7, %edx
; X86-SLOW-NEXT: orl %ecx, %edx
; X86-SLOW-NEXT: popl %esi
; X86-SLOW-NEXT: retl
;
; X64-FAST-LABEL: const_shift_i64:
; X64-FAST: # %bb.0:
; X64-FAST-NEXT: movq %rdi, %rax
; X64-FAST-NEXT: shldq $7, %rsi, %rax
; X64-FAST-NEXT: retq
;
; X64-SLOW-LABEL: const_shift_i64:
; X64-SLOW: # %bb.0:
; X64-SLOW-NEXT: shrq $57, %rsi
; X64-SLOW-NEXT: shlq $7, %rdi
; X64-SLOW-NEXT: leaq (%rdi,%rsi), %rax
; X64-SLOW-NEXT: retq
%tmp = tail call i64 @llvm.fshl.i64(i64 %x, i64 %y, i64 7)
ret i64 %tmp
}
Reference in New Issue View Git Blame Copy Permalink