maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Optimize getImpliedDisabledFeatures & getImpliedEnabledFeatures after D83273 

Previously the time complexity is O(|number of paths from the root to an
implied feature| * CPU_FWATURE_MAX) where CPU_FEATURE_MAX is 92.

The number of paths can be large (theoretically exponential).

For an inline asm statement, there is a code path
`clang::Parser::ParseAsmStatement -> clang::Sema::ActOnGCCAsmStmt -> ASTContext::getFunctionFeatureMap`
leading to potentially many calls of getImpliedEnabledFeatures (41 for my -march=native case).

We should improve the performance a bit in case the number of inline asm
statements is large (Linux kernel builds).

Reviewed By: craig.topper

Differential Revision: https://reviews.llvm.org/D85257
This commit is contained in:
Fangrui Song 2020-08-04 17:50:06 -07:00
parent 4c9ed3ed3d
commit 0c7af8c83b
1 changed files with 29 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
llvm/lib/Support/X86TargetParser.cpp
View File

@ -37,6 +37,10 @@ public:
set(I);
}
bool any() const {
return llvm::any_of(Bits, [](uint64_t V) { return V != 0; });
}
constexpr FeatureBitset &set(unsigned I) {
// GCC <6.2 crashes if this is written in a single statement.
uint32_t NewBits = Bits[I / 32] | (uint32_t(1) << (I % 32));
@ -89,6 +93,13 @@ public:
Result.Bits[I] = ~Bits[I];
return Result;
}
constexpr bool operator!=(const FeatureBitset &RHS) const {
for (unsigned I = 0, E = array_lengthof(Bits); I != E; ++I)
if (Bits[I] != RHS.Bits[I])
return true;
return false;
}
};
struct ProcInfo {
@ -552,11 +563,17 @@ void llvm::X86::getFeaturesForCPU(StringRef CPU,
// For each feature that is (transitively) implied by this feature, set it.
static void getImpliedEnabledFeatures(FeatureBitset &Bits,
const FeatureBitset &Implies) {
// Fast path: Implies is often empty.
if (!Implies.any())
return;
FeatureBitset Prev;
Bits |= Implies;
for (unsigned i = 0; i != CPU_FEATURE_MAX; ++i) {
if (Implies[i])
getImpliedEnabledFeatures(Bits, FeatureInfos[i].ImpliedFeatures);
}
do {
Prev = Bits;
for (unsigned i = CPU_FEATURE_MAX; i;)
if (Bits[--i])
Bits |= FeatureInfos[i].ImpliedFeatures;
} while (Prev != Bits);
}
/// Create bit vector of features that are implied disabled if the feature
@ -564,12 +581,14 @@ static void getImpliedEnabledFeatures(FeatureBitset &Bits,
static void getImpliedDisabledFeatures(FeatureBitset &Bits, unsigned Value) {
// Check all features looking for any dependent on this feature. If we find
// one, mark it and recursively find any feature that depend on it.
for (unsigned i = 0; i != CPU_FEATURE_MAX; ++i) {
if (FeatureInfos[i].ImpliedFeatures[Value]) {
Bits.set(i);
getImpliedDisabledFeatures(Bits, i);
}
}
FeatureBitset Prev;
Bits.set(Value);
do {
Prev = Bits;
for (unsigned i = 0; i != CPU_FEATURE_MAX; ++i)
if ((FeatureInfos[i].ImpliedFeatures & Bits).any())
Bits.set(i);
} while (Prev != Bits);
}
void llvm::X86::getImpliedFeatures(