// The cost of the loads/stores is accounted for separately.
//
static const CostTblEntry AVX2InterleavedLoadTbl[] = {
+ {2, MVT::v2i16, 2}, // (load 4i16 and) deinterleave into 2 x 2i16
+
{2, MVT::v4i64, 6}, // (load 8i64 and) deinterleave into 2 x 4i64
{3, MVT::v2i8, 10}, // (load 6i8 and) deinterleave into 3 x 2i8
};
static const CostTblEntry AVX2InterleavedStoreTbl[] = {
+ {2, MVT::v2i16, 1}, // interleave 2 x 2i16 into 4i16 (and store)
+
{2, MVT::v4i64, 6}, // interleave 2 x 4i64 into 8i64 (and store)
{3, MVT::v2i8, 7}, // interleave 3 x 2i8 into 6i8 (and store)
; CHECK: LV: Checking a loop in "test"
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
-; CHECK: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
+; CHECK: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 17 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 41 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 114 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Checking a loop in "test"
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v1, i16* %out1, align 2
-; CHECK: LV: Found an estimated cost of 9 for VF 2 For instruction: store i16 %v1, i16* %out1, align 2
+; CHECK: LV: Found an estimated cost of 2 for VF 2 For instruction: store i16 %v1, i16* %out1, align 2
; CHECK: LV: Found an estimated cost of 17 for VF 4 For instruction: store i16 %v1, i16* %out1, align 2
; CHECK: LV: Found an estimated cost of 49 for VF 8 For instruction: store i16 %v1, i16* %out1, align 2
; CHECK: LV: Found an estimated cost of 114 for VF 16 For instruction: store i16 %v1, i16* %out1, align 2