{6, MVT::v16i16, 106}, // (load 96i16 and) deinterleave into 6 x 16i16
{6, MVT::v2i32, 6}, // (load 12i32 and) deinterleave into 6 x 2i32
+ {6, MVT::v4i32, 15}, // (load 24i32 and) deinterleave into 6 x 4i32
{8, MVT::v8i32, 40} // (load 64i32 and) deinterleave into 8 x 8i32
};
{6, MVT::v16i16, 58}, // interleave 6 x 16i16 into 96i16 (and store)
{6, MVT::v2i32, 9}, // interleave 6 x 2i32 into 12i32 (and store)
+ {6, MVT::v4i32, 12}, // interleave 6 x 4i32 into 24i32 (and store)
};
if (Opcode == Instruction::Load) {
;
; 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 8 for VF 2 For instruction: %v0 = load float, float* %in0, align 4
-; AVX2: LV: Found an estimated cost of 51 for VF 4 For instruction: %v0 = load float, float* %in0, align 4
+; AVX2: LV: Found an estimated cost of 18 for VF 4 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 114 for VF 8 For instruction: %v0 = load float, float* %in0, align 4
; AVX2: LV: Found an estimated cost of 228 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 i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
-; AVX2: LV: Found an estimated cost of 63 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
+; AVX2: LV: Found an estimated cost of 18 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 138 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
; AVX2: LV: Found an estimated cost of 276 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: store float %v5, float* %out5, align 4
; AVX2: LV: Found an estimated cost of 11 for VF 2 For instruction: store float %v5, float* %out5, align 4
-; AVX2: LV: Found an estimated cost of 45 for VF 4 For instruction: store float %v5, float* %out5, align 4
+; AVX2: LV: Found an estimated cost of 15 for VF 4 For instruction: store float %v5, float* %out5, align 4
; AVX2: LV: Found an estimated cost of 114 for VF 8 For instruction: store float %v5, float* %out5, align 4
; AVX2: LV: Found an estimated cost of 228 for VF 16 For instruction: store float %v5, float* %out5, align 4
;
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %v5, i32* %out5, align 4
; AVX2: LV: Found an estimated cost of 11 for VF 2 For instruction: store i32 %v5, i32* %out5, align 4
-; AVX2: LV: Found an estimated cost of 57 for VF 4 For instruction: store i32 %v5, i32* %out5, align 4
+; AVX2: LV: Found an estimated cost of 15 for VF 4 For instruction: store i32 %v5, i32* %out5, align 4
; AVX2: LV: Found an estimated cost of 138 for VF 8 For instruction: store i32 %v5, i32* %out5, align 4
; AVX2: LV: Found an estimated cost of 276 for VF 16 For instruction: store i32 %v5, i32* %out5, align 4
;