{2, MVT::v2i64, 2}, // (load 4i64 and) deinterleave into 2 x 2i64
{2, MVT::v4i64, 4}, // (load 8i64 and) deinterleave into 2 x 4i64
+ {2, MVT::v8i64, 8}, // (load 16i64 and) deinterleave into 2 x 8i64
{3, MVT::v2i8, 10}, // (load 6i8 and) deinterleave into 3 x 2i8
{3, MVT::v4i8, 4}, // (load 12i8 and) deinterleave into 3 x 4i8
{2, MVT::v2i64, 2}, // interleave 2 x 2i64 into 4i64 (and store)
{2, MVT::v4i64, 4}, // interleave 2 x 4i64 into 8i64 (and store)
+ {2, MVT::v8i64, 8}, // interleave 2 x 8i64 into 16i64 (and store)
{3, MVT::v2i8, 7}, // interleave 3 x 2i8 into 6i8 (and store)
{3, MVT::v4i8, 8}, // interleave 3 x 4i8 into 12i8 (and store)
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, double* %in0, align 8
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load double, double* %in0, align 8
; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load double, double* %in0, align 8
-; AVX2: LV: Found an estimated cost of 32 for VF 8 For instruction: %v0 = load double, double* %in0, align 8
+; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: %v0 = load double, double* %in0, align 8
; AVX2: LV: Found an estimated cost of 64 for VF 16 For instruction: %v0 = load double, double* %in0, align 8
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load double, double* %in0, align 8
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, i64* %in0, align 8
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i64, i64* %in0, align 8
; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i64, i64* %in0, align 8
-; AVX2: LV: Found an estimated cost of 52 for VF 8 For instruction: %v0 = load i64, i64* %in0, align 8
+; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: %v0 = load i64, i64* %in0, align 8
; AVX2: LV: Found an estimated cost of 104 for VF 16 For instruction: %v0 = load i64, i64* %in0, align 8
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i64, i64* %in0, align 8
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, double* %out1, align 8
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: store double %v1, double* %out1, align 8
; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: store double %v1, double* %out1, align 8
-; AVX2: LV: Found an estimated cost of 32 for VF 8 For instruction: store double %v1, double* %out1, align 8
+; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: store double %v1, double* %out1, align 8
; AVX2: LV: Found an estimated cost of 64 for VF 16 For instruction: store double %v1, double* %out1, align 8
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v1, double* %out1, align 8
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, i64* %out1, align 8
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: store i64 %v1, i64* %out1, align 8
; AVX2: LV: Found an estimated cost of 6 for VF 4 For instruction: store i64 %v1, i64* %out1, align 8
-; AVX2: LV: Found an estimated cost of 52 for VF 8 For instruction: store i64 %v1, i64* %out1, align 8
+; AVX2: LV: Found an estimated cost of 12 for VF 8 For instruction: store i64 %v1, i64* %out1, align 8
; AVX2: LV: Found an estimated cost of 104 for VF 16 For instruction: store i64 %v1, i64* %out1, align 8
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v1, i64* %out1, align 8