[SimplifyCFG] Relax cttz cost check in simplifySwitchOfPowersOfTwo

We should be able to allow `simplifySwitchOfPowersOfTwo` transform
to take place, as, on recent X86 targets, the weighted latency-size
appears to be 2. This favours computing trailing zeroes and indexing
into a smaller value table, over generating a jump table with an
indirect branch, which overall should be more efficient.

Author: antoniofrighetto

llvm/lib/Transforms/Utils/SimplifyCFG.cpp

@@ -7198,8 +7198,10 @@ static bool reduceSwitchRange(SwitchInst *SI, IRBuilder<> &Builder,
 /// will be transformed to:
 /// switch (count_trailing_zeros(C)) { case 0: case 1: case 6: case 7: }
 ///
-/// This transformation allows better lowering and could allow transforming into
-/// a lookup table.
+/// This transformation allows better lowering and may transform the switch
+/// instruction into a sequence of bit manipulation and a smaller
+/// log2(C)-indexed value table (instead of traditionally emitting a load of the
+/// address of the jump target, and indirectly jump to it).
 static bool simplifySwitchOfPowersOfTwo(SwitchInst *SI, IRBuilder<> &Builder,
                                         const DataLayout &DL,
                                         const TargetTransformInfo &TTI) {
@@ -7211,17 +7213,15 @@ static bool simplifySwitchOfPowersOfTwo(SwitchInst *SI, IRBuilder<> &Builder,
       !DL.fitsInLegalInteger(CondTy->getIntegerBitWidth()))
     return false;
 
-  const auto CttzIntrinsicCost = TTI.getIntrinsicInstrCost(
-      IntrinsicCostAttributes(Intrinsic::cttz, CondTy,
-                              {Condition, ConstantInt::getTrue(Context)}),
-      TTI::TCK_SizeAndLatency);
-
-  if (CttzIntrinsicCost > TTI::TCC_Basic)
-    // Inserting intrinsic is too expensive.
+  // Ensure trailing zeroes count intrinsic emission is not too expensive.
+  IntrinsicCostAttributes Attrs(Intrinsic::cttz, CondTy,
+                                {Condition, ConstantInt::getTrue(Context)});
+  if (TTI.getIntrinsicInstrCost(Attrs, TTI::TCK_SizeAndLatency) >
+      TTI::TCC_Basic * 2)
     return false;
 
   // Only bother with this optimization if there are more than 3 switch cases.
-  // SDAG will only bother creating jump tables for 4 or more cases.
+  // SDAG will start emitting jump tables for 4 or more cases.
   if (SI->getNumCases() < 4)
     return false;
 

llvm/test/Transforms/SimplifyCFG/X86/switch-of-powers-of-two.ll

@@ -0,0 +1,35 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -passes='simplifycfg<switch-to-lookup>' -simplifycfg-require-and-preserve-domtree=1 -S < %s | FileCheck %s
+
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @switch_of_powers_two(i32 %arg) {
+; CHECK-LABEL: define i32 @switch_of_powers_two(
+; CHECK-SAME: i32 [[ARG:%.*]]) {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.cttz.i32(i32 [[ARG]], i1 true)
+; CHECK-NEXT:    [[SWITCH_GEP:%.*]] = getelementptr inbounds [7 x i32], ptr @switch.table.switch_of_powers_two, i32 0, i32 [[TMP0]]
+; CHECK-NEXT:    [[SWITCH_LOAD:%.*]] = load i32, ptr [[SWITCH_GEP]], align 4
+; CHECK-NEXT:    ret i32 [[SWITCH_LOAD]]
+;
+entry:
+  switch i32 %arg, label %default_case [
+  i32 1,  label %bb1
+  i32 8,  label %bb2
+  i32 16, label %bb3
+  i32 32, label %bb4
+  i32 64, label %bb5
+  ]
+
+
+default_case: unreachable
+bb1: br label %return
+bb2: br label %return
+bb3: br label %return
+bb4: br label %return
+bb5: br label %return
+
+return:
+  %phi = phi i32 [ 3, %bb1 ], [ 2, %bb2 ], [ 1, %bb3 ], [ 0, %bb4 ], [ 42, %bb5 ]
+  ret i32 %phi
+}