{4, MVT::v16i16, 75}, // (load 64i16 and) deinterleave into 4 x 16i16
{4, MVT::v32i16, 150}, // (load 128i16 and) deinterleave into 4 x 32i16
+ {6, MVT::v2i16, 13}, // (load 12i16 and) deinterleave into 6 x 2i16
+
{8, MVT::v8i32, 40} // (load 64i32 and) deinterleave into 8 x 8i32
};
{4, MVT::v8i16, 10}, // interleave 4 x 8i16 into 32i16 (and store)
{4, MVT::v16i16, 32}, // interleave 4 x 16i16 into 64i16 (and store)
{4, MVT::v32i16, 64}, // interleave 4 x 32i16 into 128i16 (and store)
+
+ {6, MVT::v2i16, 10}, // interleave 6 x 2i16 into 12i16 (and store)
};
if (Opcode == Instruction::Load) {
; CHECK: LV: Checking a loop in "test"
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
-; CHECK: LV: Found an estimated cost of 31 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
+; CHECK: LV: Found an estimated cost of 16 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 58 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 123 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 342 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Checking a loop in "test"
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v5, i16* %out5, align 2
-; CHECK: LV: Found an estimated cost of 35 for VF 2 For instruction: store i16 %v5, i16* %out5, align 2
+; CHECK: LV: Found an estimated cost of 13 for VF 2 For instruction: store i16 %v5, i16* %out5, align 2
; CHECK: LV: Found an estimated cost of 66 for VF 4 For instruction: store i16 %v5, i16* %out5, align 2
; CHECK: LV: Found an estimated cost of 147 for VF 8 For instruction: store i16 %v5, i16* %out5, align 2
; CHECK: LV: Found an estimated cost of 342 for VF 16 For instruction: store i16 %v5, i16* %out5, align 2