[Inliner] Make the CallPenalty configurable

Tests with multiple benchmarks, like Embench [1], showed that the
CallPenalty magic number has the most influence on inlining decisions
when optimizing for size.

On the other hand, there was no good default value for this parameter.
Some benchmarks profited strongly from a reduced call penalty. On
example is the picojpeg benchmark compiled for RISC-V, which got 6%
smaller with a CallPenalty of 10 instead of 12. Other benchmarks
increased in size, like matmult.

This commit makes the compromise of turning the magic number constant of
CallPenalty into a configurable value. This introduces the flag
`--inline-call-penalty`. With that flag users can fine tune the inliner
to their needs.

The CallPenalty constant was also used for loops. This commit replaces
the CallPenalty constant with a new LoopPenalty constant that is now
used instead.

This is a slimmed down version of https://reviews.llvm.org/D30899

[1]: https://github.com/embench/embench-iot

Differential Revision: https://reviews.llvm.org/D105976

llvm/include/llvm/Analysis/InlineCost.h

@@ -44,7 +44,7 @@ const int OptAggressiveThreshold = 250;
 // Various magic constants used to adjust heuristics.
 const int InstrCost = 5;
 const int IndirectCallThreshold = 100;
-const int CallPenalty = 25;
+const int LoopPenalty = 25;
 const int LastCallToStaticBonus = 15000;
 const int ColdccPenalty = 2000;
 /// Do not inline functions which allocate this many bytes on the stack

llvm/lib/Analysis/InlineCost.cpp

@@ -113,6 +113,10 @@ static cl::opt<int> HotCallSiteRelFreq(
              "entry frequency, for a callsite to be hot in the absence of "
              "profile information."));
 
+static cl::opt<int> CallPenalty(
+    "inline-call-penalty", cl::Hidden, cl::init(25),
+    cl::desc("Call penalty that is applied per callsite when inlining"));
+
 static cl::opt<bool> OptComputeFullInlineCost(
     "inline-cost-full", cl::Hidden, cl::init(false), cl::ZeroOrMore,
     cl::desc("Compute the full inline cost of a call site even when the cost "
@@ -554,7 +558,7 @@ class InlineCostCallAnalyzer final : public CallAnalyzer {
     addCost(LoadEliminationCost);
     LoadEliminationCost = 0;
   }
-  void onCallPenalty() override { addCost(InlineConstants::CallPenalty); }
+  void onCallPenalty() override { addCost(CallPenalty); }
   void onCallArgumentSetup(const CallBase &Call) override {
     // Pay the price of the argument setup. We account for the average 1
     // instruction per call argument setup here.
@@ -589,7 +593,7 @@ class InlineCostCallAnalyzer final : public CallAnalyzer {
       }
     } else
       // Otherwise simply add the cost for merely making the call.
-      addCost(InlineConstants::CallPenalty);
+      addCost(CallPenalty);
   }
 
   void onFinalizeSwitch(unsigned JumpTableSize,
@@ -832,7 +836,7 @@ class InlineCostCallAnalyzer final : public CallAnalyzer {
           continue;
         NumLoops++;
       }
-      addCost(NumLoops * InlineConstants::CallPenalty);
+      addCost(NumLoops * InlineConstants::LoopPenalty);
     }
 
     // We applied the maximum possible vector bonus at the beginning. Now,
@@ -993,8 +997,7 @@ private:
   }
 
   void onCallPenalty() override {
-    increment(InlineCostFeatureIndex::CallPenalty,
-              InlineConstants::CallPenalty);
+    increment(InlineCostFeatureIndex::CallPenalty, CallPenalty);
   }
 
   void onCallArgumentSetup(const CallBase &Call) override {
@@ -1092,7 +1095,7 @@ private:
         if (DeadBlocks.count(L->getHeader()))
           continue;
         increment(InlineCostFeatureIndex::NumLoops,
-                  InlineConstants::CallPenalty);
+                  InlineConstants::LoopPenalty);
       }
     }
     set(InlineCostFeatureIndex::DeadBlocks, DeadBlocks.size());
@@ -2679,7 +2682,7 @@ int llvm::getCallsiteCost(CallBase &Call, const DataLayout &DL) {
     }
   }
   // The call instruction also disappears after inlining.
-  Cost += InlineConstants::InstrCost + InlineConstants::CallPenalty;
+  Cost += InlineConstants::InstrCost + CallPenalty;
   return Cost;
 }
 

llvm/test/Transforms/Inline/inline-call-penalty-option.ll

@@ -0,0 +1,28 @@
+; Check that calls are not inlined if the call penalty is low. The value of the
+; call penalty is provided with the '--inline-call-penalty' option.
+;
+; RUN: opt < %s -inline --inline-call-penalty=0 --inline-threshold=5 -S | FileCheck %s
+; RUN: opt < %s -inline --inline-threshold=5 -S | FileCheck %s -check-prefix=DEFAULT_CALL_PENALTY
+
+define i32 @X9(i32 %x) nounwind {
+  %x2 = add i32 %x, %x
+  %x3 = add i32 %x2, %x
+  %x4 = add i32 %x3, %x
+  %x5 = add i32 %x4, %x
+  %x6 = add i32 %x5, %x
+  %x7 = add i32 %x6, %x
+  %x8 = add i32 %x7, %x
+  %x9 = add i32 %x8, %x
+
+  ret i32 %x9
+}
+
+define i32 @f1(i32 %x) nounwind {
+  %res = call i32 @X9(i32 %x)
+  ret i32 %res
+; CHECK-LABEL: @f1(
+; CHECK: %res = call i32 @X9
+
+; DEFAULT_CALL_PENALTY-LABEL: @f1(
+; DEFAULT_CALL_PENALTY-NOT: call
+}