{4, MVT::v16i8, 39}, // (load 64i8 and) deinterleave into 4 x 16i8
{4, MVT::v32i8, 80}, // (load 128i8 and) deinterleave into 4 x 32i8
+ {4, MVT::v2i16, 6}, // (load 8i16 and) deinterleave into 4 x 2i16
+
{8, MVT::v8i32, 40} // (load 64i32 and) deinterleave into 8 x 8i32
};
{4, MVT::v4i8, 9}, // interleave 4 x 4i8 into 16i8 (and store)
{4, MVT::v8i8, 10}, // interleave 4 x 8i8 into 32i8 (and store)
{4, MVT::v16i8, 10}, // interleave 4 x 16i8 into 64i8 (and store)
- {4, MVT::v32i8, 12} // interleave 4 x 32i8 into 128i8 (and store)
+ {4, MVT::v32i8, 12}, // interleave 4 x 32i8 into 128i8 (and store)
+
+ {4, MVT::v2i16, 2}, // interleave 4 x 2i16 into 8i16 (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 17 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
+; CHECK: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 41 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 82 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 228 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 %v3, i16* %out3, align 2
-; CHECK: LV: Found an estimated cost of 17 for VF 2 For instruction: store i16 %v3, i16* %out3, align 2
+; CHECK: LV: Found an estimated cost of 3 for VF 2 For instruction: store i16 %v3, i16* %out3, align 2
; CHECK: LV: Found an estimated cost of 49 for VF 4 For instruction: store i16 %v3, i16* %out3, align 2
; CHECK: LV: Found an estimated cost of 98 for VF 8 For instruction: store i16 %v3, i16* %out3, align 2
; CHECK: LV: Found an estimated cost of 228 for VF 16 For instruction: store i16 %v3, i16* %out3, align 2