{4, MVT::v4i32, 8}, // (load 16i32 and) deinterleave into 4 x 4i32
{4, MVT::v8i32, 16}, // (load 32i32 and) deinterleave into 4 x 8i32
{4, MVT::v16i32, 32}, // (load 64i32 and) deinterleave into 4 x 16i32
+ {4, MVT::v32i32, 68}, // (load 128i32 and) deinterleave into 4 x 32i32
{4, MVT::v2i64, 6}, // (load 8i64 and) deinterleave into 4 x 2i64
{4, MVT::v4i64, 8}, // (load 16i64 and) deinterleave into 4 x 4i64
{4, MVT::v4i32, 6}, // interleave 4 x 4i32 into 16i32 (and store)
{4, MVT::v8i32, 16}, // interleave 4 x 8i32 into 32i32 (and store)
{4, MVT::v16i32, 32}, // interleave 4 x 16i32 into 64i32 (and store)
+ {4, MVT::v32i32, 64}, // interleave 4 x 32i32 into 128i32 (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)
; AVX2: LV: Found an estimated cost of 10 for VF 4 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: %v0 = load float, float* %in0, align 4
-; AVX2: LV: Found an estimated cost of 304 for VF 32 For instruction: %v0 = load float, float* %in0, align 4
+; AVX2: LV: Found an estimated cost of 84 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 5 for VF 2 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 10 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 280 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 84 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 10 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 192 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 84 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 10 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 104 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 84 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 10 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 368 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 84 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 5 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: store float %v3, float* %out3, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: store float %v3, float* %out3, align 4
; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: store float %v3, float* %out3, align 4
-; AVX2: LV: Found an estimated cost of 304 for VF 32 For instruction: store float %v3, float* %out3, align 4
+; AVX2: LV: Found an estimated cost of 80 for VF 32 For instruction: store float %v3, float* %out3, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v3, float* %out3, align 4
; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: store float %v3, float* %out3, align 4
; AVX2: LV: Found an estimated cost of 8 for VF 4 For instruction: store i32 %v3, i32* %out3, align 4
; AVX2: LV: Found an estimated cost of 20 for VF 8 For instruction: store i32 %v3, i32* %out3, align 4
; AVX2: LV: Found an estimated cost of 40 for VF 16 For instruction: store i32 %v3, i32* %out3, align 4
-; AVX2: LV: Found an estimated cost of 368 for VF 32 For instruction: store i32 %v3, i32* %out3, align 4
+; AVX2: LV: Found an estimated cost of 80 for VF 32 For instruction: store i32 %v3, i32* %out3, align 4
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v3, i32* %out3, align 4
; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: store i32 %v3, i32* %out3, align 4