(!cast<I>(OpcPrefix#SSrr_Int) v4f32:$dst, v4f32:$src)>;
}
- // With SSE 4.1, insertps/blendi are preferred to movsd, so match those too.
+ // With SSE 4.1, blendi is preferred to movsd, so match that too.
let Predicates = [UseSSE41] in {
- // extracted scalar math op with insert via insertps
- def : Pat<(v4f32 (X86insertps (v4f32 VR128:$dst), (v4f32 (scalar_to_vector
- (Op (f32 (vector_extract (v4f32 VR128:$dst), (iPTR 0))),
- FR32:$src))), (iPTR 0))),
- (!cast<I>(OpcPrefix#SSrr_Int) v4f32:$dst,
- (COPY_TO_REGCLASS FR32:$src, VR128))>;
-
// extracted scalar math op with insert via blend
def : Pat<(v4f32 (X86Blendi (v4f32 VR128:$dst), (v4f32 (scalar_to_vector
(Op (f32 (vector_extract (v4f32 VR128:$dst), (iPTR 0))),
// Repeat everything for AVX, except for the movss + scalar combo...
// because that one shouldn't occur with AVX codegen?
let Predicates = [HasAVX] in {
- // extracted scalar math op with insert via insertps
- def : Pat<(v4f32 (X86insertps (v4f32 VR128:$dst), (v4f32 (scalar_to_vector
- (Op (f32 (vector_extract (v4f32 VR128:$dst), (iPTR 0))),
- FR32:$src))), (iPTR 0))),
- (!cast<I>("V"#OpcPrefix#SSrr_Int) v4f32:$dst,
- (COPY_TO_REGCLASS FR32:$src, VR128))>;
-
// extracted scalar math op with insert via blend
def : Pat<(v4f32 (X86Blendi (v4f32 VR128:$dst), (v4f32 (scalar_to_vector
(Op (f32 (vector_extract (v4f32 VR128:$dst), (iPTR 0))),