[ARM] MVE sext costs

This adds some sext costs for MVE, taken from the length of assembly sequences
that we currently generate.

Differential Revision: https://reviews.llvm.org/D66010

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369244 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/ARM/ARMTargetTransformInfo.cpp b/lib/Target/ARM/ARMTargetTransformInfo.cpp
index e94b9bd9b9e3b4f6612a2eaf4e1cb7b3b9d22a7d..6a128e8530170380ad71309f71b4ec802fc65f6f 100644 (file)
--- a/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -349,6 +349,31 @@ int ARMTTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src,
       return Entry->Cost;
   }
 
+  // MVE extend costs, taken from codegen tests. i8->i16 or i16->i32 is one
+  // instruction, i8->i32 is two. i64 zexts are an VAND with a constant, sext
+  // are linearised so take more.
+  static const TypeConversionCostTblEntry MVEVectorConversionTbl[] = {
+    { ISD::SIGN_EXTEND, MVT::v8i16, MVT::v8i8, 1 },
+    { ISD::ZERO_EXTEND, MVT::v8i16, MVT::v8i8, 1 },
+    { ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i8, 2 },
+    { ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i8, 2 },
+    { ISD::SIGN_EXTEND, MVT::v2i64, MVT::v2i8, 10 },
+    { ISD::ZERO_EXTEND, MVT::v2i64, MVT::v2i8, 2 },
+    { ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i16, 1 },
+    { ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i16, 1 },
+    { ISD::SIGN_EXTEND, MVT::v2i64, MVT::v2i16, 10 },
+    { ISD::ZERO_EXTEND, MVT::v2i64, MVT::v2i16, 2 },
+    { ISD::SIGN_EXTEND, MVT::v2i64, MVT::v2i32, 8 },
+    { ISD::ZERO_EXTEND, MVT::v2i64, MVT::v2i32, 2 },
+  };
+
+  if (SrcTy.isVector() && ST->hasMVEIntegerOps()) {
+    if (const auto *Entry = ConvertCostTableLookup(MVEVectorConversionTbl,
+                                                   ISD, DstTy.getSimpleVT(),
+                                                   SrcTy.getSimpleVT()))
+      return Entry->Cost * ST->getMVEVectorCostFactor();
+  }
+
   // Scalar integer conversion costs.
   static const TypeConversionCostTblEntry ARMIntegerConversionTbl[] = {
     // i16 -> i64 requires two dependent operations.

diff --git a/test/Analysis/CostModel/ARM/cast.ll b/test/Analysis/CostModel/ARM/cast.ll
index 26bc5ec9850f59d4b3f03ad6a31da03c16b2b708..0b068b5e0e9b9c4e1dfc3861a6efec1d4190fb05 100644 (file)
--- a/test/Analysis/CostModel/ARM/cast.ll
+++ b/test/Analysis/CostModel/ARM/cast.ll
@@ -74,8 +74,14 @@ define i32 @casts() {
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r67 = uitofp i64 undef to float
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r68 = sitofp i64 undef to double
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r69 = uitofp i64 undef to double
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q70 = sext <4 x i8> undef to <4 x i32>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q71 = sext <8 x i8> undef to <8 x i16>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s70 = sext <4 x i8> undef to <4 x i32>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r70 = sext <8 x i8> undef to <8 x i32>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r71 = sext <16 x i8> undef to <16 x i32>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q72 = zext <4 x i8> undef to <4 x i32>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %q73 = zext <8 x i8> undef to <8 x i16>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %s72 = zext <4 x i8> undef to <4 x i32>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r72 = zext <8 x i8> undef to <8 x i32>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r73 = zext <16 x i8> undef to <16 x i32>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %rext_0 = sext <8 x i8> undef to <8 x i64>
@@ -84,6 +90,12 @@ define i32 @casts() {
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %rext_3 = zext <8 x i16> undef to <8 x i64>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %rext_4 = sext <4 x i16> undef to <4 x i64>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %rext_5 = zext <4 x i16> undef to <4 x i64>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_6 = sext <2 x i8> undef to <2 x i64>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_7 = zext <2 x i8> undef to <2 x i64>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_8 = sext <2 x i16> undef to <2 x i64>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_9 = zext <2 x i16> undef to <2 x i64>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_a = sext <2 x i32> undef to <2 x i64>
+; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %rext_b = zext <2 x i32> undef to <2 x i64>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r74 = trunc <8 x i32> undef to <8 x i8>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r75 = trunc <16 x i32> undef to <16 x i8>
 ; CHECK-NEON-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r80 = fptrunc double undef to float
@@ -329,16 +341,28 @@ define i32 @casts() {
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r67 = uitofp i64 undef to float
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r68 = sitofp i64 undef to double
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r69 = uitofp i64 undef to double
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r70 = sext <8 x i8> undef to <8 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r71 = sext <16 x i8> undef to <16 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r72 = zext <8 x i8> undef to <8 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %r73 = zext <16 x i8> undef to <16 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %rext_0 = sext <8 x i8> undef to <8 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %rext_1 = zext <8 x i8> undef to <8 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %rext_2 = sext <8 x i16> undef to <8 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 42 for instruction: %rext_3 = zext <8 x i16> undef to <8 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %rext_4 = sext <4 x i16> undef to <4 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %rext_5 = zext <4 x i16> undef to <4 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %q70 = sext <4 x i8> undef to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %q71 = sext <8 x i8> undef to <8 x i16>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %s70 = sext <4 x i8> undef to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %r70 = sext <8 x i8> undef to <8 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %r71 = sext <16 x i8> undef to <16 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %q72 = zext <4 x i8> undef to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %q73 = zext <8 x i8> undef to <8 x i16>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %s72 = zext <4 x i8> undef to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %r72 = zext <8 x i8> undef to <8 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %r73 = zext <16 x i8> undef to <16 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %rext_0 = sext <8 x i8> undef to <8 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %rext_1 = zext <8 x i8> undef to <8 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 330 for instruction: %rext_2 = sext <8 x i16> undef to <8 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %rext_3 = zext <8 x i16> undef to <8 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 82 for instruction: %rext_4 = sext <4 x i16> undef to <4 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %rext_5 = zext <4 x i16> undef to <4 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %rext_6 = sext <2 x i8> undef to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rext_7 = zext <2 x i8> undef to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %rext_8 = sext <2 x i16> undef to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rext_9 = zext <2 x i16> undef to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %rext_a = sext <2 x i32> undef to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %rext_b = zext <2 x i32> undef to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r74 = trunc <8 x i32> undef to <8 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r75 = trunc <16 x i32> undef to <16 x i8>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r80 = fptrunc double undef to float
@@ -591,8 +615,14 @@ define i32 @casts() {
   %r68 = sitofp i64 undef to double
   %r69 = uitofp i64 undef to double
 
+  %q70 = sext <4 x i8> undef to <4 x i32>
+  %q71 = sext <8 x i8> undef to <8 x i16>
+  %s70 = sext <4 x i8> undef to <4 x i32>
   %r70 = sext <8 x i8> undef to <8 x i32>
   %r71 = sext <16 x i8> undef to <16 x i32>
+  %q72 = zext <4 x i8> undef to <4 x i32>
+  %q73 = zext <8 x i8> undef to <8 x i16>
+  %s72 = zext <4 x i8> undef to <4 x i32>
   %r72 = zext <8 x i8> undef to <8 x i32>
   %r73 = zext <16 x i8> undef to <16 x i32>
 
@@ -602,6 +632,12 @@ define i32 @casts() {
   %rext_3 = zext <8 x i16> undef to <8 x i64>
   %rext_4 = sext <4 x i16> undef to <4 x i64>
   %rext_5 = zext <4 x i16> undef to <4 x i64>
+  %rext_6 = sext <2 x i8> undef to <2 x i64>
+  %rext_7 = zext <2 x i8> undef to <2 x i64>
+  %rext_8 = sext <2 x i16> undef to <2 x i64>
+  %rext_9 = zext <2 x i16> undef to <2 x i64>
+  %rext_a = sext <2 x i32> undef to <2 x i64>
+  %rext_b = zext <2 x i32> undef to <2 x i64>
 
   ; Vector cast cost of instructions lowering the cast to the stack.
   %r74 = trunc <8 x i32> undef to <8 x i8>
@@ -866,14 +902,14 @@ define i32 @load_extends() {
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v4 = sext <2 x i8> %loadv2i8 to <2 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v5 = zext <2 x i8> %loadv2i8 to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v4 = sext <2 x i8> %loadv2i8 to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v5 = zext <2 x i8> %loadv2i8 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v7 = zext <4 x i16> %loadv4i16 to <4 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v8 = sext <2 x i16> %loadv2i16 to <2 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v9 = zext <2 x i16> %loadv2i16 to <2 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v10 = sext <2 x i32> %loadv2i32 to <2 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v11 = zext <2 x i32> %loadv2i32 to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %v8 = sext <2 x i16> %loadv2i16 to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v9 = zext <2 x i16> %loadv2i16 to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v10 = sext <2 x i32> %loadv2i32 to <2 x i64>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v11 = zext <2 x i32> %loadv2i32 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;