1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-18 18:42:46 +02:00

[ADT] Remove StatisticBase and make NoopStatistic empty

In LLVM_ENABLE_STATS=0 builds, `llvm::Statistic` maps to `llvm::NoopStatistic`
but has 3 unused pointers. GlobalOpt considers that the pointers can potentially
retain allocated objects, so GlobalOpt cannot optimize out the `NoopStatistic`
variables (see D69428 for more context), wasting 23KiB for stage 2 clang.

This patch makes `NoopStatistic` empty and thus reclaims the wasted space.  The
clang size is even smaller than applying D69428 (slightly smaller in both .bss and
.text).
```
# This means the D69428 optimization on clang is mostly nullified by this patch.
HEAD+D69428: size(.bss) = 0x0725a8
HEAD+D101211: size(.bss) = 0x072238

# bloaty - HEAD+D69428 vs HEAD+D101211
# With D101211, we also save a lot of string table space (.rodata).
    FILE SIZE        VM SIZE
 --------------  --------------
  -0.0%     -32  -0.0%     -24    .eh_frame
  -0.0%    -336  [ = ]       0    .symtab
  -0.0%    -360  [ = ]       0    .strtab
  [ = ]       0  -0.2%    -880    .bss
  -0.0% -2.11Ki  -0.0% -2.11Ki    .rodata
  -0.0% -2.89Ki  -0.0% -2.89Ki    .text
  -0.0% -5.71Ki  -0.0% -5.88Ki    TOTAL
```

Note: LoopFuse is a disabled pass. This patch adds `#if LLVM_ENABLE_STATS` so
`OptimizationRemarkMissed` is skipped in LLVM_ENABLE_STATS==0 builds.  If these
`OptimizationRemarkMissed` are useful and not noisy, we can replace
`llvm::Statistic` with `llvm::TrackingStatistic` in the future.

Reviewed By: lattner

Differential Revision: https://reviews.llvm.org/D101211
This commit is contained in:
Fangrui Song 2021-04-26 13:39:35 -07:00
parent ca9962891d
commit 7fa56f879f
2 changed files with 17 additions and 17 deletions

View File

@ -46,27 +46,22 @@ class raw_ostream;
class raw_fd_ostream;
class StringRef;
class StatisticBase {
class TrackingStatistic {
public:
const char *DebugType;
const char *Name;
const char *Desc;
const char *const DebugType;
const char *const Name;
const char *const Desc;
StatisticBase(const char *DebugType, const char *Name, const char *Desc)
: DebugType(DebugType), Name(Name), Desc(Desc) {}
const char *getDebugType() const { return DebugType; }
const char *getName() const { return Name; }
const char *getDesc() const { return Desc; }
};
class TrackingStatistic : public StatisticBase {
public:
std::atomic<unsigned> Value;
std::atomic<bool> Initialized;
TrackingStatistic(const char *DebugType, const char *Name, const char *Desc)
: StatisticBase(DebugType, Name, Desc), Value(0), Initialized(false) {}
: DebugType(DebugType), Name(Name), Desc(Desc), Value(0),
Initialized(false) {}
const char *getDebugType() const { return DebugType; }
const char *getName() const { return Name; }
const char *getDesc() const { return Desc; }
unsigned getValue() const { return Value.load(std::memory_order_relaxed); }
@ -132,9 +127,10 @@ protected:
void RegisterStatistic();
};
class NoopStatistic : public StatisticBase {
class NoopStatistic {
public:
using StatisticBase::StatisticBase;
NoopStatistic(const char * /*DebugType*/, const char * /*Name*/,
const char * /*Desc*/) {}
unsigned getValue() const { return 0; }

View File

@ -372,11 +372,13 @@ private:
bool reportInvalidCandidate(llvm::Statistic &Stat) const {
using namespace ore;
assert(L && Preheader && "Fusion candidate not initialized properly!");
#if LLVM_ENABLE_STATS
++Stat;
ORE.emit(OptimizationRemarkAnalysis(DEBUG_TYPE, Stat.getName(),
L->getStartLoc(), Preheader)
<< "[" << Preheader->getParent()->getName() << "]: "
<< "Loop is not a candidate for fusion: " << Stat.getDesc());
#endif
return false;
}
};
@ -1533,6 +1535,7 @@ private:
assert(FC0.Preheader && FC1.Preheader &&
"Expecting valid fusion candidates");
using namespace ore;
#if LLVM_ENABLE_STATS
++Stat;
ORE.emit(RemarkKind(DEBUG_TYPE, Stat.getName(), FC0.L->getStartLoc(),
FC0.Preheader)
@ -1540,6 +1543,7 @@ private:
<< "]: " << NV("Cand1", StringRef(FC0.Preheader->getName()))
<< " and " << NV("Cand2", StringRef(FC1.Preheader->getName()))
<< ": " << Stat.getDesc());
#endif
}
/// Fuse two guarded fusion candidates, creating a new fused loop.