{4, MVT::v32i16, 150}, // (load 128i16 and) deinterleave into 4 x 32i16
{6, MVT::v2i8, 6}, // (load 12i8 and) deinterleave into 6 x 2i8
+ {6, MVT::v4i8, 14}, // (load 24i8 and) deinterleave into 6 x 4i8
{6, MVT::v2i16, 13}, // (load 12i16 and) deinterleave into 6 x 2i16
{6, MVT::v4i16, 9}, // (load 24i16 and) deinterleave into 6 x 4i16
{4, MVT::v32i16, 64}, // interleave 4 x 32i16 into 128i16 (and store)
{6, MVT::v2i8, 7}, // interleave 6 x 2i8 into 12i8 (and store)
+ {6, MVT::v4i8, 9}, // interleave 6 x 4i8 into 24i8 (and store)
{6, MVT::v2i16, 10}, // interleave 6 x 2i16 into 12i16 (and store)
{6, MVT::v4i16, 15}, // interleave 6 x 4i16 into 24i16 (and store)
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i8, i8* %in0, align 1
; AVX2: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i8, i8* %in0, align 1
-; AVX2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i8, i8* %in0, align 1
+; AVX2: LV: Found an estimated cost of 17 for VF 4 For instruction: %v0 = load i8, i8* %in0, align 1
; AVX2: LV: Found an estimated cost of 114 for VF 8 For instruction: %v0 = load i8, i8* %in0, align 1
; AVX2: LV: Found an estimated cost of 243 for VF 16 For instruction: %v0 = load i8, i8* %in0, align 1
; AVX2: LV: Found an estimated cost of 498 for VF 32 For instruction: %v0 = load i8, i8* %in0, align 1
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i8 %v5, i8* %out5, align 1
; AVX2: LV: Found an estimated cost of 10 for VF 2 For instruction: store i8 %v5, i8* %out5, align 1
-; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: store i8 %v5, i8* %out5, align 1
+; AVX2: LV: Found an estimated cost of 12 for VF 4 For instruction: store i8 %v5, i8* %out5, align 1
; AVX2: LV: Found an estimated cost of 101 for VF 8 For instruction: store i8 %v5, i8* %out5, align 1
; AVX2: LV: Found an estimated cost of 201 for VF 16 For instruction: store i8 %v5, i8* %out5, align 1
; AVX2: LV: Found an estimated cost of 498 for VF 32 For instruction: store i8 %v5, i8* %out5, align 1