Home | History | Annotate | Download | only in X86

Lines Matching full:masking

8217 /// masking out later).
11676 // for masking/blending then decompose into 128-bit vectors.
12576 // TODO: pre-SSE41 targets will tend to use bit masking - this could still
17165 /// for \p Mask according to \p MaskVT when lowering masking intrinsics
17216 /// necessary casting or extending for \p Mask when lowering masking intrinsics
17259 /// to MVT::i1 while lowering masking intrinsics.
19051 // we just take the hi result (by masking the lo result to zero before the