[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

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

@@ -2647,6 +2647,9 @@ int X86TTIImpl::getInterleavedMemoryOpCostAVX2(unsigned Opcode, Type *VecTy,
   // 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 @@ int X86TTIImpl::getInterleavedMemoryOpCostAVX2(unsigned Opcode, Type *VecTy,
   };
 
   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)

llvm/test/Analysis/CostModel/X86/interleaved-load-store-double.ll

@@ -0,0 +1,40 @@
+; REQUIRES: asserts
+; RUN: opt -S -loop-vectorize -debug-only=loop-vectorize -mcpu=skylake %s 2>&1 | FileCheck %s
+target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
+target triple = "i386-unknown-linux-gnu"
+
+@doublesrc = common local_unnamed_addr global [120 x double] zeroinitializer, align 4
+@doubledst = common local_unnamed_addr global [120 x double] zeroinitializer, align 4
+
+; Function Attrs: norecurse nounwind
+define void @stride2double(double %k, i32 %width_) {
+entry:
+
+; CHECK: Found an estimated cost of 8 for VF 4 For instruction:   %0 = load double
+; CHECK: Found an estimated cost of 8 for VF 4 For instruction:   store double
+
+  %cmp27 = icmp sgt i32 %width_, 0
+  br i1 %cmp27, label %for.body.lr.ph, label %for.cond.cleanup
+
+for.body.lr.ph:                                   ; preds = %entry
+  br label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.body, %entry
+  ret void
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.body
+  %i.028 = phi i32 [ 0, %for.body.lr.ph ], [ %add16, %for.body ]
+  %arrayidx = getelementptr inbounds [120 x double], [120 x double]* @doublesrc, i32 0, i32 %i.028
+  %0 = load double, double* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [120 x double], [120 x double]* @doubledst, i32 0, i32 %i.028
+  store double %0, double* %arrayidx2, align 4
+  %add4 = add nuw nsw i32 %i.028, 1
+  %arrayidx5 = getelementptr inbounds [120 x double], [120 x double]* @doublesrc, i32 0, i32 %add4
+  %1 = load double, double* %arrayidx5, align 4
+  %arrayidx8 = getelementptr inbounds [120 x double], [120 x double]* @doubledst, i32 0, i32 %add4
+  store double %1, double* %arrayidx8, align 4
+  %add16 = add nuw nsw i32 %i.028, 2
+  %cmp = icmp slt i32 %add16, %width_
+  br i1 %cmp, label %for.body, label %for.cond.cleanup
+}
+

llvm/test/Analysis/CostModel/X86/interleaved-load-store-i64.ll

@@ -0,0 +1,40 @@
+; REQUIRES: asserts
+; RUN: opt -S -loop-vectorize -debug-only=loop-vectorize -mcpu=core-avx2 %s 2>&1 | FileCheck %s
+target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
+target triple = "i386-unknown-linux-gnu"
+
+@i64src = common local_unnamed_addr global [120 x i64] zeroinitializer, align 4
+@i64dst = common local_unnamed_addr global [120 x i64] zeroinitializer, align 4
+
+; Function Attrs: norecurse nounwind
+define void @stride2i64(i64 %k, i32 %width_) {
+entry:
+
+; CHECK: Found an estimated cost of 8 for VF 4 For instruction:   %0 = load i64
+; CHECK: Found an estimated cost of 8 for VF 4 For instruction:   store i64
+
+  %cmp27 = icmp sgt i32 %width_, 0
+  br i1 %cmp27, label %for.body.lr.ph, label %for.cond.cleanup
+
+for.body.lr.ph:                                   ; preds = %entry
+  br label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.body, %entry
+  ret void
+
+for.body:
+  %i.028 = phi i32 [ 0, %for.body.lr.ph ], [ %add16, %for.body ]
+  %arrayidx = getelementptr inbounds [120 x i64], [120 x i64]* @i64src, i32 0, i32 %i.028
+  %0 = load i64, i64* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds [120 x i64], [120 x i64]* @i64dst, i32 0, i32 %i.028
+  store i64 %0, i64* %arrayidx2, align 4
+  %add4 = add nuw nsw i32 %i.028, 1
+  %arrayidx5 = getelementptr inbounds [120 x i64], [120 x i64]* @i64src, i32 0, i32 %add4
+  %1 = load i64, i64* %arrayidx5, align 4
+  %arrayidx8 = getelementptr inbounds [120 x i64], [120 x i64]* @i64dst, i32 0, i32 %add4
+  store i64 %1, i64* %arrayidx8, align 4
+  %add16 = add nuw nsw i32 %i.028, 2
+  %cmp = icmp slt i32 %add16, %width_
+  br i1 %cmp, label %for.body, label %for.cond.cleanup
+}
+