[AMDGPU] Tweak getTypeLegalizationCost()

Even though wide vectors are legal they still cost more as we
will have to eventually split them. Not all operations can
be uniformly done on vector types.

Conservatively add the cost of splitting at least to 8 dwords,
which is our widest possible load.

We are more or less lying to cost mode with this change but
this can prevent vectorizer from creation of wide vectors which
results in RA problems for us.

Differential Revision: https://reviews.llvm.org/D83078

lib/Target/AMDGPU/SIISelLowering.cpp

@@ -11690,3 +11690,18 @@ bool SITargetLowering::requiresUniformRegister(MachineFunction &MF,
   SmallPtrSet<const Value *, 16> Visited;
   return hasCFUser(V, Visited, Subtarget->getWavefrontSize());
 }
+
+std::pair<int, MVT>
+SITargetLowering::getTypeLegalizationCost(const DataLayout &DL,
+                                          Type *Ty) const {
+  auto Cost = TargetLoweringBase::getTypeLegalizationCost(DL, Ty);
+  auto Size = DL.getTypeSizeInBits(Ty);
+  // Maximum load or store can handle 8 dwords for scalar and 4 for
+  // vector ALU. Let's assume anything above 8 dwords is expensive
+  // even if legal.
+  if (Size <= 256)
+    return Cost;
+
+  Cost.first = (Size + 255) / 256;
+  return Cost;
+}

lib/Target/AMDGPU/SIISelLowering.h

@@ -464,6 +464,9 @@ public:
                                       MachineFunction &MF,
                                       const SIRegisterInfo &TRI,
                                       SIMachineFunctionInfo &Info) const;
+
+  std::pair<int, MVT> getTypeLegalizationCost(const DataLayout &DL,
+                                              Type *Ty) const;
 };
 
 } // End namespace llvm

test/Analysis/CostModel/AMDGPU/add-sub.ll

@@ -90,7 +90,7 @@ define amdgpu_kernel void @add_v4i64(<4 x i64> addrspace(1)* %out, <4 x i64> add
 }
 
 ; ALL: 'add_v16i64'
-; ALL: estimated cost of 32 for {{.*}} add <16 x i64>
+; ALL: estimated cost of 128 for {{.*}} add <16 x i64>
 define amdgpu_kernel void @add_v16i64(<16 x i64> addrspace(1)* %out, <16 x i64> addrspace(1)* %vaddr, <16 x i64> %b) #0 {
   %vec = load <16 x i64>, <16 x i64> addrspace(1)* %vaddr
   %add = add <16 x i64> %vec, %b

test/Analysis/CostModel/AMDGPU/mul.ll

@@ -90,7 +90,7 @@ define amdgpu_kernel void @mul_v4i64(<4 x i64> addrspace(1)* %out, <4 x i64> add
 
 
 ; ALL: 'mul_v8i64'
-; ALL: estimated cost of 128 for {{.*}} mul <8 x i64>
+; ALL: estimated cost of 256 for {{.*}} mul <8 x i64>
 define amdgpu_kernel void @mul_v8i64(<8 x i64> addrspace(1)* %out, <8 x i64> addrspace(1)* %vaddr, <8 x i64> %b) #0 {
   %vec = load <8 x i64>, <8 x i64> addrspace(1)* %vaddr
   %mul = mul <8 x i64> %vec, %b