[X86][Costmodel] Add SSE2 sub-128bit vXi8/16 stride 2 interleaved store costs

Differential Revision: https://reviews.llvm.org/D111941

Author: RKSimon

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

@@ -5318,14 +5318,9 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCost(
   };
 
   static const CostTblEntry AVX2InterleavedStoreTbl[] = {
-      {2, MVT::v2i8, 1},  // interleave 2 x 2i8 into 4i8 (and store)
-      {2, MVT::v4i8, 1},  // interleave 2 x 4i8 into 8i8 (and store)
-      {2, MVT::v8i8, 1},  // interleave 2 x 8i8 into 16i8 (and store)
       {2, MVT::v16i8, 3}, // interleave 2 x 16i8 into 32i8 (and store)
       {2, MVT::v32i8, 4}, // interleave 2 x 32i8 into 64i8 (and store)
 
-      {2, MVT::v2i16, 1},  // interleave 2 x 2i16 into 4i16 (and store)
-      {2, MVT::v4i16, 1},  // interleave 2 x 4i16 into 8i16 (and store)
       {2, MVT::v8i16, 3},  // interleave 2 x 8i16 into 16i16 (and store)
       {2, MVT::v16i16, 4}, // interleave 2 x 16i16 into 32i16 (and store)
       {2, MVT::v32i16, 8}, // interleave 2 x 32i16 into 64i16 (and store)
@@ -5410,6 +5405,15 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCost(
       {6, MVT::v8i64, 30}, // interleave 6 x 8i64 into 48i64 (and store)
   };
 
+  static const CostTblEntry SSE2InterleavedStoreTbl[] = {
+      {2, MVT::v2i8, 1},   // interleave 2 x 2i8 into 4i8 (and store)
+      {2, MVT::v4i8, 1},   // interleave 2 x 4i8 into 8i8 (and store)
+      {2, MVT::v8i8, 1},   // interleave 2 x 8i8 into 16i8 (and store)
+
+      {2, MVT::v2i16, 1},  // interleave 2 x 2i16 into 4i16 (and store)
+      {2, MVT::v4i16, 1},  // interleave 2 x 4i16 into 8i16 (and store)
+  };
+
   if (Opcode == Instruction::Load) {
     // FIXME: if we have a partially-interleaved groups, with gaps,
     //        should we discount the not-demanded indicies?
@@ -5436,6 +5440,11 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCost(
       if (const auto *Entry = CostTableLookup(AVX2InterleavedStoreTbl, Factor,
                                               ETy.getSimpleVT()))
         return MemOpCosts + Entry->Cost;
+
+    if (ST->hasSSE2())
+      if (const auto *Entry = CostTableLookup(SSE2InterleavedStoreTbl, Factor,
+                                              ETy.getSimpleVT()))
+        return MemOpCosts + Entry->Cost;
   }
 
   return BaseT::getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices,

llvm/test/Analysis/CostModel/X86/interleaved-store-i16-stride-2.ll

@@ -13,14 +13,14 @@ target triple = "x86_64-unknown-linux-gnu"
 ; CHECK: LV: Checking a loop in "test"
 ;
 ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i16 %v1, i16* %out1, align 2
-; SSE2: LV: Found an estimated cost of 9 for VF 2 For instruction:   store i16 %v1, i16* %out1, align 2
-; SSE2: LV: Found an estimated cost of 17 for VF 4 For instruction:   store i16 %v1, i16* %out1, align 2
+; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction:   store i16 %v1, i16* %out1, align 2
+; SSE2: LV: Found an estimated cost of 2 for VF 4 For instruction:   store i16 %v1, i16* %out1, align 2
 ; SSE2: LV: Found an estimated cost of 34 for VF 8 For instruction:   store i16 %v1, i16* %out1, align 2
 ; SSE2: LV: Found an estimated cost of 68 for VF 16 For instruction:   store i16 %v1, i16* %out1, align 2
 ;
 ; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i16 %v1, i16* %out1, align 2
-; AVX1: LV: Found an estimated cost of 9 for VF 2 For instruction:   store i16 %v1, i16* %out1, align 2
-; AVX1: LV: Found an estimated cost of 17 for VF 4 For instruction:   store i16 %v1, i16* %out1, align 2
+; AVX1: LV: Found an estimated cost of 2 for VF 2 For instruction:   store i16 %v1, i16* %out1, align 2
+; AVX1: LV: Found an estimated cost of 2 for VF 4 For instruction:   store i16 %v1, i16* %out1, align 2
 ; AVX1: LV: Found an estimated cost of 35 for VF 8 For instruction:   store i16 %v1, i16* %out1, align 2
 ; AVX1: LV: Found an estimated cost of 86 for VF 16 For instruction:   store i16 %v1, i16* %out1, align 2
 ; AVX1: LV: Found an estimated cost of 172 for VF 32 For instruction:   store i16 %v1, i16* %out1, align 2

llvm/test/Analysis/CostModel/X86/interleaved-store-i8-stride-2.ll

@@ -13,15 +13,15 @@ target triple = "x86_64-unknown-linux-gnu"
 ; CHECK: LV: Checking a loop in "test"
 ;
 ; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i8 %v1, i8* %out1, align 1
-; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction:   store i8 %v1, i8* %out1, align 1
-; SSE2: LV: Found an estimated cost of 30 for VF 4 For instruction:   store i8 %v1, i8* %out1, align 1
-; SSE2: LV: Found an estimated cost of 62 for VF 8 For instruction:   store i8 %v1, i8* %out1, align 1
+; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction:   store i8 %v1, i8* %out1, align 1
+; SSE2: LV: Found an estimated cost of 2 for VF 4 For instruction:   store i8 %v1, i8* %out1, align 1
+; SSE2: LV: Found an estimated cost of 2 for VF 8 For instruction:   store i8 %v1, i8* %out1, align 1
 ; SSE2: LV: Found an estimated cost of 126 for VF 16 For instruction:   store i8 %v1, i8* %out1, align 1
 ;
 ; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i8 %v1, i8* %out1, align 1
-; AVX1: LV: Found an estimated cost of 9 for VF 2 For instruction:   store i8 %v1, i8* %out1, align 1
-; AVX1: LV: Found an estimated cost of 17 for VF 4 For instruction:   store i8 %v1, i8* %out1, align 1
-; AVX1: LV: Found an estimated cost of 33 for VF 8 For instruction:   store i8 %v1, i8* %out1, align 1
+; AVX1: LV: Found an estimated cost of 2 for VF 2 For instruction:   store i8 %v1, i8* %out1, align 1
+; AVX1: LV: Found an estimated cost of 2 for VF 4 For instruction:   store i8 %v1, i8* %out1, align 1
+; AVX1: LV: Found an estimated cost of 2 for VF 8 For instruction:   store i8 %v1, i8* %out1, align 1
 ; AVX1: LV: Found an estimated cost of 67 for VF 16 For instruction:   store i8 %v1, i8* %out1, align 1
 ; AVX1: LV: Found an estimated cost of 166 for VF 32 For instruction:   store i8 %v1, i8* %out1, align 1