[TTI][X86] update costs of interleaved load\store of i64\double
This patch contains more accurate cost of interelaved load\store of stride 2 for the types int64\double on AVX2.
Reviewers: delena, RKSimon, craig.topper, dorit
Reviewed By: dorit
Differential Revision: https://reviews.llvm.org/D40008
llvm-svn: 318385
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 28c5d04..7903332 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -2647,6 +2647,9 @@
// The cost of the loads/stores is accounted for separately.
//
static const CostTblEntry AVX2InterleavedLoadTbl[] = {
+ { 2, MVT::v4i64, 6 }, //(load 8i64 and) deinterleave into 2 x 4i64
+ { 2, MVT::v4f64, 6 }, //(load 8f64 and) deinterleave into 2 x 4f64
+
{ 3, MVT::v2i8, 10 }, //(load 6i8 and) deinterleave into 3 x 2i8
{ 3, MVT::v4i8, 4 }, //(load 12i8 and) deinterleave into 3 x 4i8
{ 3, MVT::v8i8, 9 }, //(load 24i8 and) deinterleave into 3 x 8i8
@@ -2664,6 +2667,9 @@
};
static const CostTblEntry AVX2InterleavedStoreTbl[] = {
+ { 2, MVT::v4i64, 6 }, //interleave into 2 x 4i64 into 8i64 (and store)
+ { 2, MVT::v4f64, 6 }, //interleave into 2 x 4f64 into 8f64 (and store)
+
{ 3, MVT::v2i8, 7 }, //interleave 3 x 2i8 into 6i8 (and store)
{ 3, MVT::v4i8, 8 }, //interleave 3 x 4i8 into 12i8 (and store)
{ 3, MVT::v8i8, 11 }, //interleave 3 x 8i8 into 24i8 (and store)