Lines Matching full:masked
1108 // XMM register mask efficiently, we could transform all x86 masked intrinsics
1109 // to LLVM masked intrinsics and remove the x86 masked intrinsic defs.
1116 // This masked load instruction creates a zero vector.
1137 // The pass-through vector for an x86 masked load is a zero vector.
1144 // XMM register mask efficiently, we could transform all x86 masked intrinsics
1145 // to LLVM masked intrinsics and remove the x86 masked intrinsic defs.
1152 // this masked store instruction does nothing.
1182 // 'Replace uses' doesn't work for stores. Erase the original masked store.
