[InlineCost] Improve the cost heuristic for Switch

Summary:
The motivation example is like below which has 13 cases but only 2 distinct targets

```
lor.lhs.false2:                                   ; preds = %if.then
  switch i32 %Status, label %if.then27 [
    i32 -7012, label %if.end35
    i32 -10008, label %if.end35
    i32 -10016, label %if.end35
    i32 15000, label %if.end35
    i32 14013, label %if.end35
    i32 10114, label %if.end35
    i32 10107, label %if.end35
    i32 10105, label %if.end35
    i32 10013, label %if.end35
    i32 10011, label %if.end35
    i32 7008, label %if.end35
    i32 7007, label %if.end35
    i32 5002, label %if.end35
  ]
```
which is compiled into a balanced binary tree like this on AArch64 (similar on X86)

```
.LBB853_9:                              // %lor.lhs.false2
        mov     w8, #10012
        cmp             w19, w8
        b.gt    .LBB853_14
// BB#10:                               // %lor.lhs.false2
        mov     w8, #5001
        cmp             w19, w8
        b.gt    .LBB853_18
// BB#11:                               // %lor.lhs.false2
        mov     w8, #-10016
        cmp             w19, w8
        b.eq    .LBB853_23
// BB#12:                               // %lor.lhs.false2
        mov     w8, #-10008
        cmp             w19, w8
        b.eq    .LBB853_23
// BB#13:                               // %lor.lhs.false2
        mov     w8, #-7012
        cmp             w19, w8
        b.eq    .LBB853_23
        b       .LBB853_3
.LBB853_14:                             // %lor.lhs.false2
        mov     w8, #14012
        cmp             w19, w8
        b.gt    .LBB853_21
// BB#15:                               // %lor.lhs.false2
        mov     w8, #-10105
        add             w8, w19, w8
        cmp             w8, #9          // =9
        b.hi    .LBB853_17
// BB#16:                               // %lor.lhs.false2
        orr     w9, wzr, #0x1
        lsl     w8, w9, w8
        mov     w9, #517
        and             w8, w8, w9
        cbnz    w8, .LBB853_23
.LBB853_17:                             // %lor.lhs.false2
        mov     w8, #10013
        cmp             w19, w8
        b.eq    .LBB853_23
        b       .LBB853_3
.LBB853_18:                             // %lor.lhs.false2
        mov     w8, #-7007
        add             w8, w19, w8
        cmp             w8, #2          // =2
        b.lo    .LBB853_23
// BB#19:                               // %lor.lhs.false2
        mov     w8, #5002
        cmp             w19, w8
        b.eq    .LBB853_23
// BB#20:                               // %lor.lhs.false2
        mov     w8, #10011
        cmp             w19, w8
        b.eq    .LBB853_23
        b       .LBB853_3
.LBB853_21:                             // %lor.lhs.false2
        mov     w8, #14013
        cmp             w19, w8
        b.eq    .LBB853_23
// BB#22:                               // %lor.lhs.false2
        mov     w8, #15000
        cmp             w19, w8
        b.ne    .LBB853_3
```
However, the inline cost model estimates the cost to be linear with the number
of distinct targets and the cost of the above switch is just 2 InstrCosts.
The function containing this switch is then inlined about 900 times.

This change use the general way of switch lowering for the inline heuristic. It
etimate the number of case clusters with the suitability check for a jump table
or bit test. Considering the binary search tree built for the clusters, this
change modifies the model to be linear with the size of the balanced binary
tree. The model is off by default for now :
  -inline-generic-switch-cost=false

This change was originally proposed by Haicheng in D29870.

Reviewers: hans, bmakam, chandlerc, eraman, haicheng, mcrosier

Reviewed By: hans

Subscribers: joerg, aemerson, llvm-commits, rengolin

Differential Revision: https://reviews.llvm.org/D31085

llvm-svn: 301649
diff --git a/llvm/lib/CodeGen/TargetLoweringBase.cpp b/llvm/lib/CodeGen/TargetLoweringBase.cpp
index e579922..9b9f45f 100644
--- a/llvm/lib/CodeGen/TargetLoweringBase.cpp
+++ b/llvm/lib/CodeGen/TargetLoweringBase.cpp
@@ -53,6 +53,18 @@
   ("max-jump-table-size", cl::init(0), cl::Hidden,
    cl::desc("Set maximum size of jump tables; zero for no limit."));
 
+/// Minimum jump table density for normal functions.
+static cl::opt<unsigned>
+    JumpTableDensity("jump-table-density", cl::init(10), cl::Hidden,
+                     cl::desc("Minimum density for building a jump table in "
+                              "a normal function"));
+
+/// Minimum jump table density for -Os or -Oz functions.
+static cl::opt<unsigned> OptsizeJumpTableDensity(
+    "optsize-jump-table-density", cl::init(40), cl::Hidden,
+    cl::desc("Minimum density for building a jump table in "
+             "an optsize function"));
+
 // Although this default value is arbitrary, it is not random. It is assumed
 // that a condition that evaluates the same way by a higher percentage than this
 // is best represented as control flow. Therefore, the default value N should be
@@ -1901,6 +1913,10 @@
   MinimumJumpTableEntries = Val;
 }
 
+unsigned TargetLoweringBase::getMinimumJumpTableDensity(bool OptForSize) const {
+  return OptForSize ? OptsizeJumpTableDensity : JumpTableDensity;
+}
+
 unsigned TargetLoweringBase::getMaximumJumpTableSize() const {
   return MaximumJumpTableSize;
 }