[AMDGPU] Tune inlining parameters for AMDGPU target (part 2)

[dfukalov]

Summary

Most of IR instructions got better code size estimations after commit 47a5c36b.
So default parameters values should be updated to improve inlining and
unrolling for the target.

[rampitec]

LGTM

llvm/lib/Target/AMDGPU/AMDGPUInline.cpp

 #include "llvm/Transforms/IPO.h"
 #include "llvm/Transforms/IPO/Inliner.h"
 
 using namespace llvm;
 
 #define DEBUG_TYPE "inline"
 
 static cl::opt<int>
-ArgAllocaCost("amdgpu-inline-arg-alloca-cost", cl::Hidden, cl::init(1500),
+ArgAllocaCost("amdgpu-inline-arg-alloca-cost", cl::Hidden, cl::init(4000),
               cl::desc("Cost of alloca argument"));
 
 // If the amount of scratch memory to eliminate exceeds our ability to allocate
 // it into registers we gain nothing by aggressively inlining functions for that
 // heuristic.
 static cl::opt<unsigned>
 ArgAllocaCutoff("amdgpu-inline-arg-alloca-cutoff", cl::Hidden, cl::init(256),
                 cl::desc("Maximum alloca size to use for inline cost"));

llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h

public:
   unsigned getVectorSplitCost() { return 0; }
 
   unsigned getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index,
                           Type *SubTp);
 
   bool areInlineCompatible(const Function *Caller,
                            const Function *Callee) const;
 
-  unsigned getInliningThresholdMultiplier() { return 9; }
+  unsigned getInliningThresholdMultiplier() { return 11; }
 
   int getInlinerVectorBonusPercent() { return 0; }
 
   int getArithmeticReductionCost(unsigned Opcode,
                                  Type *Ty,
                                  bool IsPairwise);
   int getMinMaxReductionCost(Type *Ty, Type *CondTy,
                              bool IsPairwiseForm,

llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp

 
 using namespace llvm;
 
 #define DEBUG_TYPE "AMDGPUtti"
 
 static cl::opt<unsigned> UnrollThresholdPrivate(
   "amdgpu-unroll-threshold-private",
   cl::desc("Unroll threshold for AMDGPU if private memory used in a loop"),
-  cl::init(2000), cl::Hidden);
+  cl::init(2700), cl::Hidden);
 
 static cl::opt<unsigned> UnrollThresholdLocal(
   "amdgpu-unroll-threshold-local",
   cl::desc("Unroll threshold for AMDGPU if local memory used in a loop"),
   cl::init(1000), cl::Hidden);
 
 static cl::opt<unsigned> UnrollThresholdIf(
   "amdgpu-unroll-threshold-if",

llvm/test/CodeGen/AMDGPU/amdgpu-inline.ll

 
 if.end:                                           ; preds = %if.then, %entry
   ret void
 }
 
 define coldcc void @foo_private_ptr2(float addrspace(5)* nocapture %p1, float addrspace(5)* nocapture %p2) {
 entry:
   %tmp1 = load float, float addrspace(5)* %p1, align 4
+  %cmp = fcmp ogt float %tmp1, 1.000000e+00
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:
   %div = fdiv float 2.000000e+00, %tmp1
   store float %div, float addrspace(5)* %p2, align 4
+  br label %if.end
+
+if.end:
   ret void
 }
 
 define coldcc float @sin_wrapper(float %x) {
 bb:
   %call = tail call float @_Z3sinf(float %x)
   ret float %call
 }

llvm/test/Transforms/LoopUnroll/AMDGPU/unroll-for-private.ll

-; RUN: opt -data-layout=A5 -mtriple=amdgcn-unknown-amdhsa -loop-unroll -S -amdgpu-unroll-threshold-private=12000 %s | FileCheck %s
+; RUN: opt -data-layout=A5 -mtriple=amdgcn-unknown-amdhsa -loop-unroll -S %s | FileCheck %s
 
 ; Check that we full unroll loop to be able to eliminate alloca
 ; CHECK-LABEL: @non_invariant_ind
 ; CHECK:       for.body:
 ; CHECK-NOT:   br
 ; CHECK:       store i32 %tmp15, i32 addrspace(1)* %arrayidx7, align 4
 ; CHECK:       ret void