[llvm] 6b95fd1 - Revert "[X86] X86TTIImpl::getInterleavedMemoryOpCostAVX2(): use getMemoryOpCost()"

[Roman Lebedev via llvm-commits]

Author: Roman Lebedev
Date: 2021-05-14T00:03:36+03:00
New Revision: 6b95fd199d96e3ba5c28a23b17b74203522bdaa8

URL: https://github.com/llvm/llvm-project/commit/6b95fd199d96e3ba5c28a23b17b74203522bdaa8
DIFF: https://github.com/llvm/llvm-project/commit/6b95fd199d96e3ba5c28a23b17b74203522bdaa8.diff

LOG: Revert "[X86] X86TTIImpl::getInterleavedMemoryOpCostAVX2(): use getMemoryOpCost()"

Depends on a commit that is about to be reverted.

This reverts commit 69ed93a4355123a45c1d7216aea7cd53d07a361b.

Added: 
    

Modified: 
    llvm/lib/Target/X86/X86TargetTransformInfo.cpp
    llvm/test/Analysis/CostModel/X86/interleaved-load-i8.ll
    llvm/test/Analysis/CostModel/X86/interleaved-store-i8.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index 66a7b10617aa7..924d76af762c2 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -4691,9 +4691,17 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2(
     ScalarTy =
         Type::getIntNTy(ScalarTy->getContext(), DL.getTypeSizeInBits(ScalarTy));
 
-  // Get the cost of all the memory operations.
-  InstructionCost MemOpCosts = getMemoryOpCost(
-      Opcode, VecTy, MaybeAlign(Alignment), AddressSpace, CostKind);
+  // Calculate the number of memory operations (NumOfMemOps), required
+  // for load/store the VecTy.
+  unsigned VecTySize = DL.getTypeStoreSize(VecTy);
+  unsigned LegalVTSize = LegalVT.getStoreSize();
+  unsigned NumOfMemOps = (VecTySize + LegalVTSize - 1) / LegalVTSize;
+
+  // Get the cost of one memory operation.
+  auto *SingleMemOpTy = FixedVectorType::get(VecTy->getElementType(),
+                                             LegalVT.getVectorNumElements());
+  InstructionCost MemOpCost = getMemoryOpCost(
+      Opcode, SingleMemOpTy, MaybeAlign(Alignment), AddressSpace, CostKind);
 
   auto *VT = FixedVectorType::get(ScalarTy, VF);
   EVT ETy = TLI->getValueType(DL, VT);
@@ -4748,13 +4756,13 @@ InstructionCost X86TTIImpl::getInterleavedMemoryOpCostAVX2(
   if (Opcode == Instruction::Load) {
     if (const auto *Entry =
             CostTableLookup(AVX2InterleavedLoadTbl, Factor, ETy.getSimpleVT()))
-      return MemOpCosts + Entry->Cost;
+      return NumOfMemOps * MemOpCost + Entry->Cost;
   } else {
     assert(Opcode == Instruction::Store &&
            "Expected Store Instruction at this  point");
     if (const auto *Entry =
             CostTableLookup(AVX2InterleavedStoreTbl, Factor, ETy.getSimpleVT()))
-      return MemOpCosts + Entry->Cost;
+      return NumOfMemOps * MemOpCost + Entry->Cost;
   }
 
   return BaseT::getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices,

diff  --git a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8.ll
index d20745080981a..f43d73e646528 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-load-i8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-load-i8.ll
@@ -7,9 +7,9 @@ target triple = "x86_64-unknown-linux-gnu"
 ; Function Attrs: norecurse nounwind readonly uwtable
 define i32 @doit_stride3(i8* nocapture readonly %Ptr, i32 %Nels)  {
 ;CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction:   %0 = load i8
-;CHECK: LV: Found an estimated cost of 13 for VF 2 For instruction:   %0 = load i8
-;CHECK: LV: Found an estimated cost of 7 for VF 4 For instruction:   %0 = load i8
-;CHECK: LV: Found an estimated cost of 12 for VF 8 For instruction:   %0 = load i8
+;CHECK: LV: Found an estimated cost of 11 for VF 2 For instruction:   %0 = load i8
+;CHECK: LV: Found an estimated cost of 5 for VF 4 For instruction:   %0 = load i8
+;CHECK: LV: Found an estimated cost of 10 for VF 8 For instruction:   %0 = load i8
 ;CHECK: LV: Found an estimated cost of 13 for VF 16 For instruction:   %0 = load i8
 ;CHECK: LV: Found an estimated cost of 16 for VF 32 For instruction:   %0 = load i8
 entry:

diff  --git a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8.ll b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8.ll
index 349f5ad21a6f4..0923f131c004f 100644
--- a/llvm/test/Analysis/CostModel/X86/interleaved-store-i8.ll
+++ b/llvm/test/Analysis/CostModel/X86/interleaved-store-i8.ll
@@ -7,9 +7,9 @@ target triple = "x86_64-unknown-linux-gnu"
 ; Function Attrs: norecurse nounwind uwtable
 define void @doit_stride3(i8* nocapture %Ptr, i32 %Nels) local_unnamed_addr {
 ;CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction:   store i8 %conv4
-;CHECK: LV: Found an estimated cost of 10 for VF 2 For instruction:   store i8 %conv4
-;CHECK: LV: Found an estimated cost of 11 for VF 4 For instruction:   store i8 %conv4
-;CHECK: LV: Found an estimated cost of 14 for VF 8 For instruction:   store i8 %conv4
+;CHECK: LV: Found an estimated cost of 8 for VF 2 For instruction:   store i8 %conv4
+;CHECK: LV: Found an estimated cost of 9 for VF 4 For instruction:   store i8 %conv4
+;CHECK: LV: Found an estimated cost of 12 for VF 8 For instruction:   store i8 %conv4
 ;CHECK: LV: Found an estimated cost of 13 for VF 16 For instruction:   store i8 %conv4
 ;CHECK: LV: Found an estimated cost of 16 for VF 32 For instruction:   store i8 %conv4
 entry: