{4, MVT::v16i16, 75}, // (load 64i16 and) deinterleave into 4 x 16i16
{4, MVT::v32i16, 150}, // (load 128i16 and) deinterleave into 4 x 32i16
+ {4, MVT::v2i32, 4}, // (load 8i32 and) deinterleave into 4 x 2i32
+
{6, MVT::v2i8, 6}, // (load 12i8 and) deinterleave into 6 x 2i8
{6, MVT::v4i8, 14}, // (load 24i8 and) deinterleave into 6 x 4i8
{6, MVT::v8i8, 18}, // (load 48i8 and) deinterleave into 6 x 8i8
{4, MVT::v16i16, 32}, // interleave 4 x 16i16 into 64i16 (and store)
{4, MVT::v32i16, 64}, // interleave 4 x 32i16 into 128i16 (and store)
+ {4, MVT::v2i32, 5}, // interleave 4 x 2i32 into 8i32 (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)
{6, MVT::v8i8, 16}, // interleave 6 x 8i8 into 48i8 (and store)
; AVX1: LV: Found an estimated cost of 152 for VF 16 For instruction: %v0 = load float, float* %in0, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load float, float* %in0, align 4
-; AVX2: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load float, float* %in0, align 4
+; AVX2: 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 34 for VF 4 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 76 for VF 8 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 152 for VF 16 For instruction: %v0 = load float, float* %in0, align 4
; AVX1: LV: Found an estimated cost of 184 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: 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 42 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 92 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 184 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX1: LV: Found an estimated cost of 152 for VF 16 For instruction: store float %v3, float* %out3, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store float %v3, float* %out3, align 4
-; AVX2: LV: Found an estimated cost of 13 for VF 2 For instruction: store float %v3, float* %out3, align 4
+; AVX2: LV: Found an estimated cost of 6 for VF 2 For instruction: store float %v3, float* %out3, align 4
; AVX2: LV: Found an estimated cost of 30 for VF 4 For instruction: store float %v3, float* %out3, align 4
; AVX2: LV: Found an estimated cost of 76 for VF 8 For instruction: store float %v3, float* %out3, align 4
; AVX2: LV: Found an estimated cost of 152 for VF 16 For instruction: store float %v3, float* %out3, align 4
; AVX1: LV: Found an estimated cost of 184 for VF 16 For instruction: store i32 %v3, i32* %out3, align 4
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v3, i32* %out3, align 4
-; AVX2: LV: Found an estimated cost of 19 for VF 2 For instruction: store i32 %v3, i32* %out3, align 4
+; AVX2: LV: Found an estimated cost of 6 for VF 2 For instruction: store i32 %v3, i32* %out3, align 4
; AVX2: LV: Found an estimated cost of 38 for VF 4 For instruction: store i32 %v3, i32* %out3, align 4
; AVX2: LV: Found an estimated cost of 92 for VF 8 For instruction: store i32 %v3, i32* %out3, align 4
; AVX2: LV: Found an estimated cost of 184 for VF 16 For instruction: store i32 %v3, i32* %out3, align 4