Changed basic cost of store operation on X86

Store operation takes 2 UOps on X86 processors. The exact cost calculation affects several optimization passes including loop unroling.
This change compensates performance degradation caused by https://reviews.llvm.org/D34458 and shows improvements on some benchmarks.

Differential Revision: https://reviews.llvm.org/D35888

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@311285 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86TargetTransformInfo.cpp b/lib/Target/X86/X86TargetTransformInfo.cpp
index 2f44d610840913daf6880cfa51884f41ca1b23f0..6c73a6875c84f2b08a47b1cfffea7355f1e9e8c0 100644 (file)
--- a/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -2113,6 +2113,21 @@ int X86TTIImpl::getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
   return X86TTIImpl::getIntImmCost(Imm, Ty);
 }
 
+unsigned X86TTIImpl::getUserCost(const User *U,
+                                 ArrayRef<const Value *> Operands) {
+  if (isa<StoreInst>(U)) {
+    Value *Ptr = U->getOperand(1);
+    // Store instruction with index and scale costs 2 Uops.
+    // Check the preceding GEP to identify non-const indices.
+    if (auto GEP = dyn_cast<GetElementPtrInst>(Ptr)) {
+      if (!all_of(GEP->indices(), [](Value *V) { return isa<Constant>(V); }))
+        return TTI::TCC_Basic * 2;
+    }
+    return TTI::TCC_Basic;
+  }
+  return BaseT::getUserCost(U, Operands);
+}
+
 // Return an average cost of Gather / Scatter instruction, maybe improved later
 int X86TTIImpl::getGSVectorCost(unsigned Opcode, Type *SrcVTy, Value *Ptr,
                                 unsigned Alignment, unsigned AddressSpace) {

diff --git a/lib/Target/X86/X86TargetTransformInfo.h b/lib/Target/X86/X86TargetTransformInfo.h
index fc63eff049d64987ba1161dc101b690dc63e5443..dc184030dee63a4086c335f5ba0348ce56dcd529 100644 (file)
--- a/lib/Target/X86/X86TargetTransformInfo.h
+++ b/lib/Target/X86/X86TargetTransformInfo.h
@@ -102,6 +102,8 @@ public:
 
   int getIntImmCost(const APInt &Imm, Type *Ty);
 
+  unsigned getUserCost(const User *U, ArrayRef<const Value *> Operands);
+
   int getIntImmCost(unsigned Opcode, unsigned Idx, const APInt &Imm, Type *Ty);
   int getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm,
                     Type *Ty);

diff --git a/test/Transforms/LoopUnroll/X86/store_cost.ll b/test/Transforms/LoopUnroll/X86/store_cost.ll
new file mode 100644 (file)
index 0000000..f15b82d
--- /dev/null
+++ b/test/Transforms/LoopUnroll/X86/store_cost.ll
@@ -0,0 +1,104 @@
+; REQUIRES: asserts
+; RUN: opt -mcpu=core-avx2 -loop-unroll --debug-only=loop-unroll -S -unroll-allow-partial < %s 2>&1 | FileCheck %s
+
+target triple = "x86_64-unknown-linux-gnu"
+
+; CHECK: Loop Unroll: F[foo] Loop %loop.2.header
+; CHECK: Loop Size = 27
+; CHECK-NOT: UNROLLING loop %loop.2.header
+; CHECK: Loop Unroll: F[foo] Loop %loop.header
+; CHECK:   Loop Size = 25
+; CHECK: UNROLLING loop %loop.header by 2 
+
+define void @foo(i32 * %out) {
+entry:
+  %0 = alloca [1024 x i32]
+  %x0 = alloca [1024 x i32]
+  %x01 = alloca [1024 x i32]
+  %x02 = alloca [1024 x i32]
+  %x03 = alloca [1024 x i32]
+  %x04 = alloca [1024 x i32]
+  %x05 = alloca [1024 x i32]
+  %x06 = alloca [1024 x i32]
+  br label %loop.header
+
+loop.header:
+  %counter = phi i32 [0, %entry], [%inc, %loop.inc]
+  br label %loop.body
+
+loop.body:
+  %ptr = getelementptr [1024 x i32], [1024 x i32]* %0, i32 0, i32 %counter
+  store i32 %counter, i32* %ptr
+  %val = add i32 %counter, 5
+  %xptr = getelementptr [1024 x i32], [1024 x i32]* %x0, i32 0, i32 %counter
+  store i32 %val, i32* %xptr
+  %val1 = add i32 %counter, 6
+  %xptr1 = getelementptr [1024 x i32], [1024 x i32]* %x01, i32 0, i32 %counter
+  store i32 %val1, i32* %xptr1
+  %val2 = add i32 %counter, 7
+  %xptr2 = getelementptr [1024 x i32], [1024 x i32]* %x02, i32 0, i32 %counter
+  store i32 %val2, i32* %xptr2
+  %val3 = add i32 %counter, 8
+  %xptr3 = getelementptr [1024 x i32], [1024 x i32]* %x03, i32 0, i32 %counter
+  store i32 %val3, i32* %xptr3
+  %val4 = add i32 %counter, 9
+  %xptr4 = getelementptr [1024 x i32], [1024 x i32]* %x04, i32 0, i32 %counter
+  store i32 %val4, i32* %xptr4
+  %val5 = add i32 %counter, 10
+  %xptr5 = getelementptr [1024 x i32], [1024 x i32]* %x05, i32 0, i32 %counter
+  store i32 %val5, i32* %xptr5
+  br label %loop.inc
+
+loop.inc:
+  %inc = add i32 %counter, 2
+  %1 = icmp sge i32 %inc, 1023
+  br i1 %1, label  %exit.0, label %loop.header
+
+exit.0:
+  %2 = getelementptr [1024 x i32], [1024 x i32]* %0, i32 0, i32 5
+  %3 = load i32, i32* %2
+  store i32 %3, i32 * %out
+  br label %loop.2.header
+
+
+loop.2.header:
+  %counter.2 = phi i32 [0, %exit.0], [%inc.2, %loop.2.inc]
+  br label %loop.2.body
+
+loop.2.body:
+  %ptr.2 = getelementptr [1024 x i32], [1024 x i32]* %0, i32 0, i32 %counter.2
+  store i32 %counter.2, i32* %ptr.2
+  %val.2 = add i32 %counter.2, 5
+  %xptr.2 = getelementptr [1024 x i32], [1024 x i32]* %x0, i32 0, i32 %counter.2
+  store i32 %val.2, i32* %xptr.2
+  %val1.2 = add i32 %counter.2, 6
+  %xptr1.2 = getelementptr [1024 x i32], [1024 x i32]* %x01, i32 0, i32 %counter.2
+  store i32 %val1, i32* %xptr1.2
+  %val2.2 = add i32 %counter.2, 7
+  %xptr2.2 = getelementptr [1024 x i32], [1024 x i32]* %x02, i32 0, i32 %counter.2
+  store i32 %val2, i32* %xptr2.2
+  %val3.2 = add i32 %counter.2, 8
+  %xptr3.2 = getelementptr [1024 x i32], [1024 x i32]* %x03, i32 0, i32 %counter.2
+  store i32 %val3.2, i32* %xptr3.2
+  %val4.2 = add i32 %counter.2, 9
+  %xptr4.2 = getelementptr [1024 x i32], [1024 x i32]* %x04, i32 0, i32 %counter.2
+  store i32 %val4.2, i32* %xptr4.2
+  %val5.2 = add i32 %counter.2, 10
+  %xptr5.2 = getelementptr [1024 x i32], [1024 x i32]* %x05, i32 0, i32 %counter.2
+  store i32 %val5.2, i32* %xptr5.2
+  %xptr6.2 = getelementptr [1024 x i32], [1024 x i32]* %x06, i32 0, i32 %counter.2
+  store i32 %val5.2, i32* %xptr6.2
+  br label %loop.2.inc
+
+loop.2.inc:
+  %inc.2 = add i32 %counter.2, 2
+  %4 = icmp sge i32 %inc.2, 1023
+  br i1 %4, label  %exit.2, label %loop.2.header
+
+exit.2:
+  %x2 = getelementptr [1024 x i32], [1024 x i32]* %0, i32 0, i32 6
+  %x3 = load i32, i32* %x2
+  %out2 = getelementptr i32, i32 * %out, i32 1
+  store i32 %3, i32 * %out2
+  ret void
+}

diff --git a/test/Transforms/LoopVectorize/X86/metadata-enable.ll b/test/Transforms/LoopVectorize/X86/metadata-enable.ll
index e1793bcc3218498f37448bc5ecb9e12d654d68a1..24eb213c215119884e1c8bc829618852f55e0b26 100644 (file)
--- a/test/Transforms/LoopVectorize/X86/metadata-enable.ll
+++ b/test/Transforms/LoopVectorize/X86/metadata-enable.ll
@@ -172,7 +172,7 @@ for.body:                                         ; preds = %for.body, %entry
   %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
   store i32 %add, i32* %arrayidx2, align 4
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %exitcond = icmp eq i64 %indvars.iv.next, 64
+  %exitcond = icmp eq i64 %indvars.iv.next, 48
   br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !2
 
 for.end:                                          ; preds = %for.body