{2, MVT::v4i32, 2}, // (load 8i32 and) deinterleave into 2 x 4i32
{2, MVT::v8i32, 4}, // (load 16i32 and) deinterleave into 2 x 8i32
{2, MVT::v16i32, 8}, // (load 32i32 and) deinterleave into 2 x 16i32
+ {2, MVT::v32i32, 16}, // (load 64i32 and) deinterleave into 2 x 32i32
{2, MVT::v4i64, 6}, // (load 8i64 and) deinterleave into 2 x 4i64
{2, MVT::v4i32, 2}, // interleave 2 x 4i32 into 8i32 (and store)
{2, MVT::v8i32, 4}, // interleave 2 x 8i32 into 16i32 (and store)
{2, MVT::v16i32, 8}, // interleave 2 x 16i32 into 32i32 (and store)
+ {2, MVT::v32i32, 16}, // interleave 2 x 32i32 into 64i32 (and store)
{2, MVT::v4i64, 6}, // interleave 2 x 4i64 into 8i64 (and store)
; AVX2: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 6 for VF 8 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 12 for VF 16 For instruction: %v0 = load float, float* %in0, align 4
-; AVX2: LV: Found an estimated cost of 152 for VF 32 For instruction: %v0 = load float, float* %in0, align 4
+; AVX2: LV: Found an estimated cost of 24 for VF 32 For instruction: %v0 = load float, float* %in0, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, float* %in0, align 4
; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 6 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 12 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 184 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 24 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 3 for VF 4 For instruction: store float %v1, float* %out1, align 4
; AVX2: LV: Found an estimated cost of 6 for VF 8 For instruction: store float %v1, float* %out1, align 4
; AVX2: LV: Found an estimated cost of 12 for VF 16 For instruction: store float %v1, float* %out1, align 4
-; AVX2: LV: Found an estimated cost of 152 for VF 32 For instruction: store float %v1, float* %out1, align 4
+; AVX2: LV: Found an estimated cost of 24 for VF 32 For instruction: store float %v1, float* %out1, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v1, float* %out1, align 4
; AVX512: LV: Found an estimated cost of 2 for VF 2 For instruction: store float %v1, float* %out1, align 4
; AVX2: LV: Found an estimated cost of 3 for VF 4 For instruction: store i32 %v1, i32* %out1, align 4
; AVX2: LV: Found an estimated cost of 6 for VF 8 For instruction: store i32 %v1, i32* %out1, align 4
; AVX2: LV: Found an estimated cost of 12 for VF 16 For instruction: store i32 %v1, i32* %out1, align 4
-; AVX2: LV: Found an estimated cost of 184 for VF 32 For instruction: store i32 %v1, i32* %out1, align 4
+; AVX2: LV: Found an estimated cost of 24 for VF 32 For instruction: store i32 %v1, i32* %out1, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v1, i32* %out1, align 4
; AVX512: LV: Found an estimated cost of 2 for VF 2 For instruction: store i32 %v1, i32* %out1, align 4