[PATCH] D92208: [AArch64][CostModel] Fixed costs for mul <2 x i64>

[Sjoerd Meijer via Phabricator via llvm-commits]

SjoerdMeijer created this revision.
SjoerdMeijer added reviewers: fhahn, dmgreen, sanwou01, NickGuy.
Herald added subscribers: danielkiss, hiraditya, kristof.beyls.
Herald added a project: LLVM.
SjoerdMeijer requested review of this revision.

This was modeled to have a cost of 1, but since we do not have a MUL.2d this is scalarized into 2 instructions. I precommitted `test/Analysis/CostModel/AArch64/mul.ll` in rGa3b1fcbc0cf5 <https://reviews.llvm.org/rGa3b1fcbc0cf5b70015d0f8aa983263d1ca84a8c8>.

The reason that regression test

  
  Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll


needs changing is documented in LoopVectorize.cpp:6855:

  
  // The cost of executing VF copies of the scalar instruction. This opcode
  // is unknown. Assume that it is the same as 'mul'.


https://reviews.llvm.org/D92208

Files:
  llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
  llvm/test/Analysis/CostModel/AArch64/mul.ll
  llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll


Index: llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll
+++ llvm/test/Transforms/LoopVectorize/AArch64/extractvalue-no-scalarization-required.ll
@@ -9,8 +9,8 @@
 ; leaving cost 3 for scalarizing the result + 2 for executing the op with VF 2.
 
 ; CM: LV: Scalar loop costs: 7.
-; CM: LV: Found an estimated cost of 5 for VF 2 For instruction:   %a = extractvalue { i64, i64 } %sv, 0
-; CM-NEXT: LV: Found an estimated cost of 5 for VF 2 For instruction:   %b = extractvalue { i64, i64 } %sv, 1
+; CM: LV: Found an estimated cost of 11 for VF 2 For instruction:   %a = extractvalue { i64, i64 } %sv, 0
+; CM-NEXT: LV: Found an estimated cost of 11 for VF 2 For instruction:   %b = extractvalue { i64, i64 } %sv, 1
 
 ; Check that the extractvalue operands are actually free in vector code.
 
Index: llvm/test/Analysis/CostModel/AArch64/mul.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/mul.ll
+++ llvm/test/Analysis/CostModel/AArch64/mul.ll
@@ -113,7 +113,7 @@
 
 define <2 x i64> @t13(<2 x i64> %a, <2 x i64> %b)  {
 ; THROUGHPUT-LABEL: 't13'
-; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = mul nsw <2 x i64> %a, %b
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %1 = mul nsw <2 x i64> %a, %b
 ; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %1
 ;
   %1 = mul nsw <2 x i64> %a, %b
@@ -122,7 +122,7 @@
 
 define <4 x i64> @t14(<4 x i64> %a, <4 x i64> %b)  {
 ; THROUGHPUT-LABEL: 't14'
-; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %1 = mul nsw <4 x i64> %a, %b
+; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %1 = mul nsw <4 x i64> %a, %b
 ; THROUGHPUT-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i64> %1
 ;
   %1 = mul nsw <4 x i64> %a, %b
Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -637,8 +637,17 @@
     }
     return Cost;
 
-  case ISD::ADD:
   case ISD::MUL:
+  {
+    // Since we do not have a MUL.2d instruction, a mul <2 x i64> is expensive
+    // as elements are extracted from the vectors and the muls scalarized.
+    auto *VecTy = dyn_cast<FixedVectorType>(Ty);
+    bool IsInt64 = Ty->getScalarType()->isIntegerTy(64);
+    if (VecTy && IsInt64)
+      return 1 * VecTy->getNumElements() + VecTy->getNumElements();
+    return (Cost + 1) * LT.first;
+  }
+  case ISD::ADD:
   case ISD::XOR:
   case ISD::OR:
   case ISD::AND:


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D92208.307970.patch
Type: text/x-patch
Size: 2913 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20201127/94807cf8/attachment.bin>