================
@@ -274,6 +278,23 @@ StringRef::size_type
StringRef::find_first_not_of(StringRef Chars,
/// Note: O(size() + Chars.size())
StringRef::size_type StringRef::find_last_of(StringRef Chars,
size_t From) const {
+#ifdef __SSE2__
+ if (Chars.size() == 2) {
+ __m128i Needle0 = _mm_set1_epi8(Chars[0]);
+ __m128i Needle1 = _mm_set1_epi8(Chars[1]);
+ size_type Sz = std::min(From, Length);
+ do {
+ Sz = Sz < 16 ? 0 : Sz - 16;
+ __m128i Buffer = _mm_loadu_si128((const __m128i *)(Data + Sz));
+ unsigned Mask = _mm_movemask_epi8(_mm_or_si128(
+ _mm_cmpeq_epi8(Buffer, Needle0), _mm_cmpeq_epi8(Buffer, Needle1)));
+ if (Mask != 0) {
+ return Sz + sizeof(Mask) * CHAR_BIT - llvm::countl_zero(Mask);
+ }
+ } while (Sz);
+ return npos;
+ }
+#endif
----------------
joker-eph wrote:
Can this be abstracted or made out-of-line?
I'm wondering about the scalability of HW-specific intrinsics in-line
(anticipating for the incoming `#elif defined(ARM64)`...)
https://github.com/llvm/llvm-project/pull/71865
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
