From 6851623c54b35673f6e9a0ed0fd12378c93f48c4 Mon Sep 17 00:00:00 2001
From: Arnold Schwaighofer <aschwaighofer@apple.com>
Date: Tue, 12 Feb 2013 02:40:39 +0000
Subject: [PATCH] ARM cost model: Add vector reverse shuffle costs

A reverse shuffle is lowered to a vrev and possibly a vext instruction (quad
word).

radar://13171406

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174933 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/ARM/ARMTargetTransformInfo.cpp | 33 +++++++++++++++++++
 test/Analysis/CostModel/ARM/shuffle.ll    | 40 +++++++++++++++++++++++
 2 files changed, 73 insertions(+)
 create mode 100644 test/Analysis/CostModel/ARM/shuffle.ll

diff --git a/lib/Target/ARM/ARMTargetTransformInfo.cpp b/lib/Target/ARM/ARMTargetTransformInfo.cpp
index f6fa3199709..01c04b48cfc 100644
--- a/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -114,6 +114,9 @@ public:
     return 1;
   }
 
+  unsigned getShuffleCost(ShuffleKind Kind, Type *Tp,
+                          int Index, Type *SubTp) const;
+
   unsigned getCastInstrCost(unsigned Opcode, Type *Dst,
                                       Type *Src) const;
 
@@ -335,3 +338,33 @@ unsigned ARMTTI::getAddressComputationCost(Type *Ty) const {
   // addressing mode.
   return 1;
 }
+
+unsigned ARMTTI::getShuffleCost(ShuffleKind Kind, Type *Tp, int Index,
+                                Type *SubTp) const {
+  // We only handle costs of reverse shuffles for now.
+  if (Kind != SK_Reverse)
+    return TargetTransformInfo::getShuffleCost(Kind, Tp, Index, SubTp);
+
+  static const CostTblEntry<MVT> NEONShuffleTbl[] = {
+    // Reverse shuffle cost one instruction if we are shuffling within a double
+    // word (vrev) or two if we shuffle a quad word (vrev, vext).
+    { ISD::VECTOR_SHUFFLE, MVT::v2i32, 1 },
+    { ISD::VECTOR_SHUFFLE, MVT::v2f32, 1 },
+    { ISD::VECTOR_SHUFFLE, MVT::v2i64, 1 },
+    { ISD::VECTOR_SHUFFLE, MVT::v2f64, 1 },
+
+    { ISD::VECTOR_SHUFFLE, MVT::v4i32, 2 },
+    { ISD::VECTOR_SHUFFLE, MVT::v4f32, 2 },
+    { ISD::VECTOR_SHUFFLE, MVT::v8i16, 2 },
+    { ISD::VECTOR_SHUFFLE, MVT::v16i8, 2 }
+  };
+
+  std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Tp);
+
+  int Idx = CostTableLookup<MVT>(NEONShuffleTbl, array_lengthof(NEONShuffleTbl),
+                                 ISD::VECTOR_SHUFFLE, LT.second);
+  if (Idx == -1)
+    return TargetTransformInfo::getShuffleCost(Kind, Tp, Index, SubTp);
+
+  return LT.first * NEONShuffleTbl[Idx].Cost;
+}
diff --git a/test/Analysis/CostModel/ARM/shuffle.ll b/test/Analysis/CostModel/ARM/shuffle.ll
new file mode 100644
index 00000000000..c92d6688046
--- /dev/null
+++ b/test/Analysis/CostModel/ARM/shuffle.ll
@@ -0,0 +1,40 @@
+; RUN: opt < %s  -cost-model -analyze -mtriple=thumbv7-apple-ios6.0.0 -mcpu=swift | FileCheck %s
+target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
+target triple = "thumbv7-apple-ios6.0.0"
+
+; CHECK: shuffle
+define void @shuffle() {
+
+
+  ;; Reverse shuffles should be lowered to vrev and possibly a vext (for
+  ;; quadwords)
+
+    ; Vector values
+  ; CHECK: cost of 1 {{.*}} shuffle
+  %v7 = shufflevector <2 x i8> undef, <2 x i8>undef, <2 x i32> <i32 1, i32 0>
+  ; CHECK: cost of 1 {{.*}} shuffle
+  %v8 = shufflevector <4 x i8> undef, <4 x i8>undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+  ; CHECK: cost of 1 {{.*}} shuffle
+  %v9 = shufflevector <8 x i8> undef, <8 x i8>undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+  ; CHECK: cost of 2 {{.*}} shuffle
+  %v10 = shufflevector <16 x i8> undef, <16 x i8>undef, <16 x i32> <i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+
+  ; CHECK: cost of 1 {{.*}} shuffle
+  %v11 = shufflevector <2 x i16> undef, <2 x i16>undef, <2 x i32> <i32 1, i32 0>
+  ; CHECK: cost of 1 {{.*}} shuffle
+  %v12 = shufflevector <4 x i16> undef, <4 x i16>undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+  ; CHECK: cost of 2 {{.*}} shuffle
+  %v13 = shufflevector <8 x i16> undef, <8 x i16>undef, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+
+  ; CHECK: cost of 1 {{.*}} shuffle
+  %v14 = shufflevector <2 x i32> undef, <2 x i32>undef, <2 x i32> <i32 1, i32 0>
+  ; CHECK: cost of 2 {{.*}} shuffle
+  %v15 = shufflevector <4 x i32> undef, <4 x i32>undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+
+  ; CHECK: cost of 1 {{.*}} shuffle
+  %v16 = shufflevector <2 x float> undef, <2 x float>undef, <2 x i32> <i32 1, i32 0>
+  ; CHECK: cost of 2 {{.*}} shuffle
+  %v17 = shufflevector <4 x float> undef, <4 x float>undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+
+  ret void
+}
-- 
2.34.1