[PATCH] D83078: [AMDGPU] Tweak getTypeLegalizationCost()

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

This revision was not accepted when it landed; it landed in state "Needs Review".
This revision was automatically updated to reflect the committed changes.
Closed by commit rGf7a7efbf88b7: [AMDGPU] Tweak getTypeLegalizationCost() (authored by rampitec).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D83078/new/

https://reviews.llvm.org/D83078

Files:
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/lib/Target/AMDGPU/SIISelLowering.h
  llvm/test/Analysis/CostModel/AMDGPU/add-sub.ll
  llvm/test/Analysis/CostModel/AMDGPU/mul.ll


Index: llvm/test/Analysis/CostModel/AMDGPU/mul.ll
===================================================================
--- llvm/test/Analysis/CostModel/AMDGPU/mul.ll
+++ llvm/test/Analysis/CostModel/AMDGPU/mul.ll
@@ -90,7 +90,7 @@
 
 
 ; 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
Index: llvm/test/Analysis/CostModel/AMDGPU/add-sub.ll
===================================================================
--- llvm/test/Analysis/CostModel/AMDGPU/add-sub.ll
+++ llvm/test/Analysis/CostModel/AMDGPU/add-sub.ll
@@ -90,7 +90,7 @@
 }
 
 ; 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
Index: llvm/lib/Target/AMDGPU/SIISelLowering.h
===================================================================
--- llvm/lib/Target/AMDGPU/SIISelLowering.h
+++ llvm/lib/Target/AMDGPU/SIISelLowering.h
@@ -464,6 +464,9 @@
                                       MachineFunction &MF,
                                       const SIRegisterInfo &TRI,
                                       SIMachineFunctionInfo &Info) const;
+
+  std::pair<int, MVT> getTypeLegalizationCost(const DataLayout &DL,
+                                              Type *Ty) const;
 };
 
 } // End namespace llvm
Index: llvm/lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -11690,3 +11690,18 @@
   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;
+}


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D83078.275634.patch
Type: text/x-patch
Size: 2613 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200707/b0f92347/attachment.bin>