[TTI][X86] Add SSE2 sub-128bit vXi16/32 and v2i64 stride 2 interleave…

…d load costs

These cases use the same codegen as AVX2 (pshuflw/pshufd) for the sub-128bit vector deinterleaving, and unpcklqdq for v2i64.

It's going to take a while to add full interleaved cost coverage, but since these are the same for SSE2 -> AVX2 it should be an easy win.

Fixes PR47437

Differential Revision: https://reviews.llvm.org/D111938

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

@@ -5220,19 +5220,15 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCost(
       {2, MVT::v16i8, 4}, // (load 32i8 and) deinterleave into 2 x 16i8
       {2, MVT::v32i8, 6}, // (load 64i8 and) deinterleave into 2 x 32i8
 
-      {2, MVT::v2i16, 2},   // (load 4i16 and) deinterleave into 2 x 2i16
       {2, MVT::v4i16, 2},   // (load 8i16 and) deinterleave into 2 x 4i16
       {2, MVT::v8i16, 6},   // (load 16i16 and) deinterleave into 2 x 8i16
       {2, MVT::v16i16, 9},  // (load 32i16 and) deinterleave into 2 x 16i16
       {2, MVT::v32i16, 18}, // (load 64i16 and) deinterleave into 2 x 32i16
 
-      {2, MVT::v2i32, 2},   // (load 4i32 and) deinterleave into 2 x 2i32
-      {2, MVT::v4i32, 2},   // (load 8i32 and) deinterleave into 2 x 4i32
       {2, MVT::v8i32, 4},   // (load 16i32 and) deinterleave into 2 x 8i32
       {2, MVT::v16i32, 8},  // (load 32i32 and) deinterleave into 2 x 16i32
       {2, MVT::v32i32, 16}, // (load 64i32 and) deinterleave into 2 x 32i32
 
-      {2, MVT::v2i64, 2},   // (load 4i64 and) deinterleave into 2 x 2i64
       {2, MVT::v4i64, 4},   // (load 8i64 and) deinterleave into 2 x 4i64
       {2, MVT::v8i64, 8},   // (load 16i64 and) deinterleave into 2 x 8i64
       {2, MVT::v16i64, 16}, // (load 32i64 and) deinterleave into 2 x 16i64
@@ -5303,6 +5299,15 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCost(
       {8, MVT::v8i32, 40} // (load 64i32 and) deinterleave into 8 x 8i32
   };
 
+  static const CostTblEntry SSE2InterleavedLoadTbl[] = {
+      {2, MVT::v2i16, 2},   // (load 4i16 and) deinterleave into 2 x 2i16
+
+      {2, MVT::v2i32, 2},   // (load 4i32 and) deinterleave into 2 x 2i32
+      {2, MVT::v4i32, 2},   // (load 8i32 and) deinterleave into 2 x 4i32
+
+      {2, MVT::v2i64, 2},   // (load 4i64 and) deinterleave into 2 x 2i64
+  };
+
   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)
@@ -5398,6 +5403,11 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCost(
       if (const auto *Entry = CostTableLookup(AVX2InterleavedLoadTbl, Factor,
                                               ETy.getSimpleVT()))
         return MemOpCosts + Entry->Cost;
+
+    if (ST->hasSSE2())
+      if (const auto *Entry = CostTableLookup(SSE2InterleavedLoadTbl, Factor,
+                                              ETy.getSimpleVT()))
+        return MemOpCosts + Entry->Cost;
   } else {
     assert(Opcode == Instruction::Store &&
            "Expected Store Instruction at this point");

llvm/test/Analysis/CostModel/X86/interleaved-load-f32-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:   %v0 = load float, float* %in0, align 4
-; SSE2: LV: Found an estimated cost of 6 for VF 2 For instruction:   %v0 = load float, float* %in0, align 4
-; SSE2: LV: Found an estimated cost of 14 for VF 4 For instruction:   %v0 = load float, float* %in0, align 4
+; SSE2: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load float, float* %in0, align 4
+; SSE2: LV: Found an estimated cost of 4 for VF 4 For instruction:   %v0 = load float, float* %in0, align 4
 ; SSE2: LV: Found an estimated cost of 28 for VF 8 For instruction:   %v0 = load float, float* %in0, align 4
 ; SSE2: LV: Found an estimated cost of 56 for VF 16 For instruction:   %v0 = load float, float* %in0, align 4
 ;
 ; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction:   %v0 = load float, float* %in0, align 4
-; AVX1: LV: Found an estimated cost of 6 for VF 2 For instruction:   %v0 = load float, float* %in0, align 4
-; AVX1: LV: Found an estimated cost of 17 for VF 4 For instruction:   %v0 = load float, float* %in0, align 4
+; AVX1: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load float, float* %in0, align 4
+; AVX1: LV: Found an estimated cost of 3 for VF 4 For instruction:   %v0 = load float, float* %in0, align 4
 ; AVX1: LV: Found an estimated cost of 38 for VF 8 For instruction:   %v0 = load float, float* %in0, align 4
 ; AVX1: LV: Found an estimated cost of 76 for VF 16 For instruction:   %v0 = load float, float* %in0, align 4
 ; AVX1: LV: Found an estimated cost of 152 for VF 32 For instruction:   %v0 = load float, float* %in0, align 4

llvm/test/Analysis/CostModel/X86/interleaved-load-f64-stride-2.ll

@@ -13,13 +13,13 @@ 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:   %v0 = load double, double* %in0, align 8
-; SSE2: LV: Found an estimated cost of 6 for VF 2 For instruction:   %v0 = load double, double* %in0, align 8
+; SSE2: LV: Found an estimated cost of 4 for VF 2 For instruction:   %v0 = load double, double* %in0, align 8
 ; SSE2: LV: Found an estimated cost of 12 for VF 4 For instruction:   %v0 = load double, double* %in0, align 8
 ; SSE2: LV: Found an estimated cost of 24 for VF 8 For instruction:   %v0 = load double, double* %in0, align 8
 ; SSE2: LV: Found an estimated cost of 48 for VF 16 For instruction:   %v0 = load double, double* %in0, align 8
 ;
 ; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction:   %v0 = load double, double* %in0, align 8
-; AVX1: LV: Found an estimated cost of 7 for VF 2 For instruction:   %v0 = load double, double* %in0, align 8
+; AVX1: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load double, double* %in0, align 8
 ; AVX1: LV: Found an estimated cost of 16 for VF 4 For instruction:   %v0 = load double, double* %in0, align 8
 ; AVX1: LV: Found an estimated cost of 32 for VF 8 For instruction:   %v0 = load double, double* %in0, align 8
 ; AVX1: LV: Found an estimated cost of 64 for VF 16 For instruction:   %v0 = load double, double* %in0, align 8

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

@@ -13,13 +13,13 @@ 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:   %v0 = load i16, i16* %in0, align 2
-; SSE2: LV: Found an estimated cost of 9 for VF 2 For instruction:   %v0 = load i16, i16* %in0, align 2
+; SSE2: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load i16, i16* %in0, align 2
 ; SSE2: LV: Found an estimated cost of 17 for VF 4 For instruction:   %v0 = load i16, i16* %in0, align 2
 ; SSE2: LV: Found an estimated cost of 34 for VF 8 For instruction:   %v0 = load i16, i16* %in0, align 2
 ; SSE2: LV: Found an estimated cost of 68 for VF 16 For instruction:   %v0 = load i16, i16* %in0, align 2
 ;
 ; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction:   %v0 = load i16, i16* %in0, align 2
-; AVX1: LV: Found an estimated cost of 9 for VF 2 For instruction:   %v0 = load i16, i16* %in0, align 2
+; AVX1: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load i16, i16* %in0, align 2
 ; AVX1: LV: Found an estimated cost of 17 for VF 4 For instruction:   %v0 = load i16, i16* %in0, align 2
 ; AVX1: LV: Found an estimated cost of 41 for VF 8 For instruction:   %v0 = load i16, i16* %in0, align 2
 ; AVX1: LV: Found an estimated cost of 86 for VF 16 For instruction:   %v0 = load i16, i16* %in0, align 2

llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.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:   %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 7 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 15 for VF 4 For instruction:   %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 4 for VF 4 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; SSE2: LV: Found an estimated cost of 30 for VF 8 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; SSE2: LV: Found an estimated cost of 60 for VF 16 For instruction:   %v0 = load i32, i32* %in0, align 4
 ;
 ; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction:   %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 5 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 11 for VF 4 For instruction:   %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 3 for VF 4 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; AVX1: LV: Found an estimated cost of 24 for VF 8 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; AVX1: LV: Found an estimated cost of 48 for VF 16 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; AVX1: LV: Found an estimated cost of 96 for VF 32 For instruction:   %v0 = load i32, i32* %in0, align 4

llvm/test/Analysis/CostModel/X86/interleaved-load-i32-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:   %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
-; SSE2: LV: Found an estimated cost of 30 for VF 4 For instruction:   %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
+; SSE2: LV: Found an estimated cost of 4 for VF 4 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; SSE2: LV: Found an estimated cost of 60 for VF 8 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; SSE2: LV: Found an estimated cost of 120 for VF 16 For instruction:   %v0 = load i32, i32* %in0, align 4
 ;
 ; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction:   %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 9 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
-; AVX1: LV: Found an estimated cost of 21 for VF 4 For instruction:   %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load i32, i32* %in0, align 4
+; AVX1: LV: Found an estimated cost of 3 for VF 4 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; AVX1: LV: Found an estimated cost of 46 for VF 8 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; AVX1: LV: Found an estimated cost of 92 for VF 16 For instruction:   %v0 = load i32, i32* %in0, align 4
 ; AVX1: LV: Found an estimated cost of 184 for VF 32 For instruction:   %v0 = load i32, i32* %in0, align 4

llvm/test/Analysis/CostModel/X86/interleaved-load-i64-stride-2.ll

@@ -13,13 +13,13 @@ 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:   %v0 = load i64, i64* %in0, align 8
-; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction:   %v0 = load i64, i64* %in0, align 8
+; SSE2: LV: Found an estimated cost of 4 for VF 2 For instruction:   %v0 = load i64, i64* %in0, align 8
 ; SSE2: LV: Found an estimated cost of 28 for VF 4 For instruction:   %v0 = load i64, i64* %in0, align 8
 ; SSE2: LV: Found an estimated cost of 56 for VF 8 For instruction:   %v0 = load i64, i64* %in0, align 8
 ; SSE2: LV: Found an estimated cost of 112 for VF 16 For instruction:   %v0 = load i64, i64* %in0, align 8
 ;
 ; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction:   %v0 = load i64, i64* %in0, align 8
-; AVX1: LV: Found an estimated cost of 11 for VF 2 For instruction:   %v0 = load i64, i64* %in0, align 8
+; AVX1: LV: Found an estimated cost of 3 for VF 2 For instruction:   %v0 = load i64, i64* %in0, align 8
 ; AVX1: LV: Found an estimated cost of 26 for VF 4 For instruction:   %v0 = load i64, i64* %in0, align 8
 ; AVX1: LV: Found an estimated cost of 52 for VF 8 For instruction:   %v0 = load i64, i64* %in0, align 8
 ; AVX1: LV: Found an estimated cost of 104 for VF 16 For instruction:   %v0 = load i64, i64* %in0, align 8