{4, MVT::v16i32, 32}, // (load 64i32 and) deinterleave into 4 x 16i32
{4, MVT::v2i64, 6}, // (load 8i64 and) deinterleave into 4 x 2i64
+ {4, MVT::v4i64, 8}, // (load 16i64 and) deinterleave into 4 x 4i64
{6, MVT::v2i8, 6}, // (load 12i8 and) deinterleave into 6 x 2i8
{6, MVT::v4i8, 14}, // (load 24i8 and) deinterleave into 6 x 4i8
{4, MVT::v16i32, 32}, // interleave 4 x 16i32 into 64i32 (and store)
{4, MVT::v2i64, 6}, // interleave 4 x 2i64 into 8i64 (and store)
+ {4, MVT::v4i64, 8}, // interleave 4 x 4i64 into 16i64 (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)
;
; 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 8 for VF 2 For instruction: %v0 = load double, double* %in0, align 8
-; AVX2: LV: Found an estimated cost of 32 for VF 4 For instruction: %v0 = load double, double* %in0, align 8
+; AVX2: LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load double, double* %in0, align 8
; AVX2: LV: Found an estimated cost of 64 for VF 8 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 8 for VF 2 For instruction: %v0 = load i64, i64* %in0, align 8
-; AVX2: LV: Found an estimated cost of 52 for VF 4 For instruction: %v0 = load i64, i64* %in0, align 8
+; AVX2: LV: Found an estimated cost of 12 for VF 4 For instruction: %v0 = load i64, i64* %in0, align 8
; AVX2: LV: Found an estimated cost of 104 for VF 8 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 %v3, double* %out3, align 8
; AVX2: LV: Found an estimated cost of 8 for VF 2 For instruction: store double %v3, double* %out3, align 8
-; AVX2: LV: Found an estimated cost of 32 for VF 4 For instruction: store double %v3, double* %out3, align 8
+; AVX2: LV: Found an estimated cost of 12 for VF 4 For instruction: store double %v3, double* %out3, align 8
; AVX2: LV: Found an estimated cost of 64 for VF 8 For instruction: store double %v3, double* %out3, align 8
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store double %v3, double* %out3, align 8
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, i64* %out3, align 8
; AVX2: LV: Found an estimated cost of 8 for VF 2 For instruction: store i64 %v3, i64* %out3, align 8
-; AVX2: LV: Found an estimated cost of 52 for VF 4 For instruction: store i64 %v3, i64* %out3, align 8
+; AVX2: LV: Found an estimated cost of 12 for VF 4 For instruction: store i64 %v3, i64* %out3, align 8
; AVX2: LV: Found an estimated cost of 104 for VF 8 For instruction: store i64 %v3, i64* %out3, align 8
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %v3, i64* %out3, align 8