[PATCH] D85759: [SLPVectorizer] Fix regression from cost model refactoring

[Thomas Lively via Phabricator via llvm-commits]

tlively updated this revision to Diff 284834.
tlively added a comment.

- rebase on pre-committed test


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D85759/new/

https://reviews.llvm.org/D85759

Files:
  llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
  llvm/test/Transforms/SLPVectorizer/WebAssembly/no-vectorize-rotate.ll


Index: llvm/test/Transforms/SLPVectorizer/WebAssembly/no-vectorize-rotate.ll
===================================================================
--- llvm/test/Transforms/SLPVectorizer/WebAssembly/no-vectorize-rotate.ll
+++ llvm/test/Transforms/SLPVectorizer/WebAssembly/no-vectorize-rotate.ll
@@ -4,20 +4,22 @@
 ; Regression test for a bug in the SLP vectorizer that was causing
 ; these rotates to be incorrectly combined into a vector rotate.
 
-; The bug fix is at https://reviews.llvm.org/D85759. This test has
-; been pre-committed to demonstrate the regressed behavior and provide
-; a clear diff for the bug fix.
-
 target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
 target triple = "wasm32-unknown-unknown"
 
 define void @foo(<2 x i64> %x, <4 x i32> %y, i64* %out) #0 {
 ; CHECK-LABEL: @foo(
-; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i32> [[Y:%.*]], <4 x i32> undef, <2 x i32> <i32 2, i32 3>
-; CHECK-NEXT:    [[TMP2:%.*]] = zext <2 x i32> [[TMP1]] to <2 x i64>
-; CHECK-NEXT:    [[TMP3:%.*]] = call <2 x i64> @llvm.fshl.v2i64(<2 x i64> [[X:%.*]], <2 x i64> [[X]], <2 x i64> [[TMP2]])
-; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i64* [[OUT:%.*]] to <2 x i64>*
-; CHECK-NEXT:    store <2 x i64> [[TMP3]], <2 x i64>* [[TMP4]], align 8
+; CHECK-NEXT:    [[A:%.*]] = extractelement <2 x i64> [[X:%.*]], i32 0
+; CHECK-NEXT:    [[B:%.*]] = extractelement <4 x i32> [[Y:%.*]], i32 2
+; CHECK-NEXT:    [[CONV6:%.*]] = zext i32 [[B]] to i64
+; CHECK-NEXT:    [[C:%.*]] = tail call i64 @llvm.fshl.i64(i64 [[A]], i64 [[A]], i64 [[CONV6]])
+; CHECK-NEXT:    store i64 [[C]], i64* [[OUT:%.*]], align 8
+; CHECK-NEXT:    [[D:%.*]] = extractelement <2 x i64> [[X]], i32 1
+; CHECK-NEXT:    [[E:%.*]] = extractelement <4 x i32> [[Y]], i32 3
+; CHECK-NEXT:    [[CONV17:%.*]] = zext i32 [[E]] to i64
+; CHECK-NEXT:    [[F:%.*]] = tail call i64 @llvm.fshl.i64(i64 [[D]], i64 [[D]], i64 [[CONV17]])
+; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[OUT]], i32 1
+; CHECK-NEXT:    store i64 [[F]], i64* [[ARRAYIDX2]], align 8
 ; CHECK-NEXT:    ret void
 ;
   %a = extractelement <2 x i64> %x, i32 0
Index: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -3594,7 +3594,15 @@
       Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
 
       // Calculate the cost of the scalar and vector calls.
-      IntrinsicCostAttributes CostAttrs(ID, *CI, 1, 1);
+      SmallVector<Type *, 4> ScalarTys;
+      for (unsigned op = 0, opc = CI->getNumArgOperands(); op != opc; ++op)
+        ScalarTys.push_back(CI->getArgOperand(op)->getType());
+
+      FastMathFlags FMF;
+      if (auto *FPMO = dyn_cast<FPMathOperator>(CI))
+        FMF = FPMO->getFastMathFlags();
+
+      IntrinsicCostAttributes CostAttrs(ID, ScalarTy, ScalarTys, FMF, 1);
       int ScalarEltCost = TTI->getIntrinsicInstrCost(CostAttrs, CostKind);
       if (NeedToShuffleReuses) {
         ReuseShuffleCost -= (ReuseShuffleNumbers - VL.size()) * ScalarEltCost;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D85759.284834.patch
Type: text/x-patch
Size: 3129 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200811/52bb0683/attachment.bin>