RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00
Code Issues Projects Releases Wiki Activity

caseFoldingDjbHash: simplify and make the US-ASCII fast path faster

Browse Source 
The slow path (with at least one non US-ASCII) will be slower but that
doesn't matter.

Differential Revision: https://reviews.llvm.org/D61178

llvm-svn: 359294
This commit is contained in:
Fangrui Song 2019-04-26 10:56:10 +00:00
parent f4ca732478
commit c1f921435d
1 changed files with 16 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
lib/Support/DJB.cpp
View File

@ -57,29 +57,26 @@ static UTF32 foldCharDwarf(UTF32 C) {
return sys::unicode::foldCharSimple(C);
}
static uint32_t caseFoldingDjbHashCharSlow(StringRef &Buffer, uint32_t H) {
UTF32 C = chopOneUTF32(Buffer);
C = foldCharDwarf(C);
std::array<UTF8, UNI_MAX_UTF8_BYTES_PER_CODE_POINT> Storage;
StringRef Folded = toUTF8(C, Storage);
return djbHash(Folded, H);
static Optional<uint32_t> fastCaseFoldingDjbHash(StringRef Buffer, uint32_t H) {
bool allASCII = true;
for (unsigned char C : Buffer) {
H = H * 33 + ('A' <= C && C <= 'Z' ? C - 'A' + 'a' : C);
allASCII &= C <= 0x7f;
}
if (allASCII)
return H;
return None;
}
uint32_t llvm::caseFoldingDjbHash(StringRef Buffer, uint32_t H) {
if (Optional<uint32_t> Result = fastCaseFoldingDjbHash(Buffer, H))
return *Result;
std::array<UTF8, UNI_MAX_UTF8_BYTES_PER_CODE_POINT> Storage;
while (!Buffer.empty()) {
unsigned char C = Buffer.front();
if (LLVM_LIKELY(C <= 0x7f)) {
// US-ASCII, encoded as one character in utf-8.
// This is by far the most common case, so handle this specially.
if (C >= 'A' && C <= 'Z')
C = 'a' + (C - 'A'); // fold uppercase into lowercase
H = (H << 5) + H + C;
Buffer = Buffer.drop_front();
continue;
}
H = caseFoldingDjbHashCharSlow(Buffer, H);
UTF32 C = foldCharDwarf(chopOneUTF32(Buffer));
StringRef Folded = toUTF8(C, Storage);
H = djbHash(Folded, H);
}
return H;
}