(VMOVSSrr (v4f32 VR128:$src1),
(EXTRACT_SUBREG (v4f32 VR128:$src2), sub_ss))>;
+ // 256-bit variants
+ def : Pat<(v8i32 (X86Movsd VR256:$src1, VR256:$src2)),
+ (SUBREG_TO_REG (i32 0),
+ (VMOVSSrr (EXTRACT_SUBREG (v8i32 VR256:$src1), sub_ss),
+ (EXTRACT_SUBREG (v8i32 VR256:$src2), sub_ss)), sub_xmm)>;
+ def : Pat<(v8f32 (X86Movsd VR256:$src1, VR256:$src2)),
+ (SUBREG_TO_REG (i32 0),
+ (VMOVSSrr (EXTRACT_SUBREG (v8f32 VR256:$src1), sub_ss),
+ (EXTRACT_SUBREG (v8f32 VR256:$src2), sub_ss)), sub_xmm)>;
+
// Shuffle with VMOVSD
def : Pat<(v2f64 (X86Movsd VR128:$src1, (scalar_to_vector FR64:$src2))),
(VMOVSDrr VR128:$src1, FR64:$src2)>;
(VMOVSDrr VR128:$src1, (EXTRACT_SUBREG (v4i32 VR128:$src2),
sub_sd))>;
+ // 256-bit variants
+ def : Pat<(v4i64 (X86Movsd VR256:$src1, VR256:$src2)),
+ (SUBREG_TO_REG (i32 0),
+ (VMOVSDrr (EXTRACT_SUBREG (v4i64 VR256:$src1), sub_sd),
+ (EXTRACT_SUBREG (v4i64 VR256:$src2), sub_sd)), sub_xmm)>;
+ def : Pat<(v4f64 (X86Movsd VR256:$src1, VR256:$src2)),
+ (SUBREG_TO_REG (i32 0),
+ (VMOVSDrr (EXTRACT_SUBREG (v4f64 VR256:$src1), sub_sd),
+ (EXTRACT_SUBREG (v4f64 VR256:$src2), sub_sd)), sub_xmm)>;
+
+
// FIXME: Instead of a X86Movlps there should be a X86Movsd here, the problem
// is during lowering, where it's not possible to recognize the fold cause
// it has two uses through a bitcast. One use disappears at isel time and the