{3, MVT::v4i32, 3}, // (load 12i32 and) deinterleave into 3 x 4i32
{3, MVT::v8i32, 7}, // (load 24i32 and) deinterleave into 3 x 8i32
{3, MVT::v16i32, 14}, // (load 48i32 and) deinterleave into 3 x 16i32
+ {3, MVT::v32i32, 32}, // (load 96i32 and) deinterleave into 3 x 32i32
{3, MVT::v2i64, 1}, // (load 6i64 and) deinterleave into 3 x 2i64
{3, MVT::v4i64, 5}, // (load 12i64 and) deinterleave into 3 x 4i64
{3, MVT::v4i32, 5}, // interleave 3 x 4i32 into 12i32 (and store)
{3, MVT::v8i32, 11}, // interleave 3 x 8i32 into 24i32 (and store)
{3, MVT::v16i32, 22}, // interleave 3 x 16i32 into 48i32 (and store)
+ {3, MVT::v32i32, 48}, // interleave 3 x 32i32 into 96i32 (and store)
{3, MVT::v2i64, 4}, // interleave 3 x 2i64 into 6i64 (and store)
{3, MVT::v4i64, 6}, // interleave 3 x 4i64 into 12i64 (and store)
; AVX2: LV: Found an estimated cost of 5 for VF 4 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load float, float* %in0, align 4
-; AVX2: LV: Found an estimated cost of 228 for VF 32 For instruction: %v0 = load float, float* %in0, align 4
+; AVX2: LV: Found an estimated cost of 44 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 4 for VF 2 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 5 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 188 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 44 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 5 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 100 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 44 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 1 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 5 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 276 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 44 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 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 7 for VF 4 For instruction: store float %v2, float* %out2, align 4
; AVX2: LV: Found an estimated cost of 14 for VF 8 For instruction: store float %v2, float* %out2, align 4
; AVX2: LV: Found an estimated cost of 28 for VF 16 For instruction: store float %v2, float* %out2, align 4
-; AVX2: LV: Found an estimated cost of 228 for VF 32 For instruction: store float %v2, float* %out2, align 4
+; AVX2: LV: Found an estimated cost of 60 for VF 32 For instruction: store float %v2, float* %out2, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v2, float* %out2, align 4
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: store float %v2, float* %out2, align 4
; AVX2: LV: Found an estimated cost of 7 for VF 4 For instruction: store i32 %v2, i32* %out2, align 4
; AVX2: LV: Found an estimated cost of 14 for VF 8 For instruction: store i32 %v2, i32* %out2, align 4
; AVX2: LV: Found an estimated cost of 28 for VF 16 For instruction: store i32 %v2, i32* %out2, align 4
-; AVX2: LV: Found an estimated cost of 276 for VF 32 For instruction: store i32 %v2, i32* %out2, align 4
+; AVX2: LV: Found an estimated cost of 60 for VF 32 For instruction: store i32 %v2, i32* %out2, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v2, i32* %out2, align 4
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: store i32 %v2, i32* %out2, align 4