[PATCH] D116362: [TTI] Support ScalableVectorType in getShuffleCost with SK_Broadcast kind

[JunMa via Phabricator via llvm-commits]

junparser updated this revision to Diff 397185.
junparser added a comment.

address paul's comment.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D116362/new/

https://reviews.llvm.org/D116362

Files:
  llvm/include/llvm/CodeGen/BasicTTIImpl.h
  llvm/test/Analysis/CostModel/RISCV/rvv-shuffle-broadcast.ll


Index: llvm/test/Analysis/CostModel/RISCV/rvv-shuffle-broadcast.ll
===================================================================
--- /dev/null
+++ llvm/test/Analysis/CostModel/RISCV/rvv-shuffle-broadcast.ll
@@ -0,0 +1,36 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; Check getShuffleCost for SK_BroadCast with scalable vector
+
+; RUN: opt -cost-model -analyze -mtriple=riscv64 -mattr=+m,+experimental-v -scalable-vectorization=on  < %s | FileCheck %s
+
+define void  @broadcast() {
+; CHECK-LABEL: 'broadcast'
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %zero = shufflevector <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %1 = shufflevector <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %2 = shufflevector <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %3 = shufflevector <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %4 = shufflevector <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %5 = shufflevector <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %6 = shufflevector <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %7 = shufflevector <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %8 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %9 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %10 = shufflevector <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %11 = shufflevector <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  %zero = shufflevector <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i32> zeroinitializer
+  %1 = shufflevector <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer
+  %2 = shufflevector <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i32> zeroinitializer
+  %3 = shufflevector <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer
+  %4 = shufflevector <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> zeroinitializer
+  %5 = shufflevector <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer
+  %6 = shufflevector <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i32> zeroinitializer
+  %7 = shufflevector <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer
+  %8 = shufflevector <vscale x 16 x i1> undef, <vscale x 16 x i1> undef, <vscale x 16 x i32> zeroinitializer
+  %9 = shufflevector <vscale x 8 x i1> undef, <vscale x 8 x i1> undef, <vscale x 8 x i32> zeroinitializer
+  %10 = shufflevector <vscale x 4 x i1> undef, <vscale x 4 x i1> undef, <vscale x 4 x i32> zeroinitializer
+  %11 = shufflevector <vscale x 2 x i1> undef, <vscale x 2 x i1> undef, <vscale x 2 x i32> zeroinitializer
+  ret void
+}
+
Index: llvm/include/llvm/CodeGen/BasicTTIImpl.h
===================================================================
--- llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -875,6 +875,8 @@
 
     switch (improveShuffleKindFromMask(Kind, Mask)) {
     case TTI::SK_Broadcast:
+      if (!isa<FixedVectorType>(Tp))
+        return InstructionCost::getInvalid();
       return getBroadcastShuffleOverhead(cast<FixedVectorType>(Tp));
     case TTI::SK_Select:
     case TTI::SK_Splice:
@@ -882,11 +884,17 @@
     case TTI::SK_Transpose:
     case TTI::SK_PermuteSingleSrc:
     case TTI::SK_PermuteTwoSrc:
+      if (!isa<FixedVectorType>(Tp))
+        return InstructionCost::getInvalid();
       return getPermuteShuffleOverhead(cast<FixedVectorType>(Tp));
     case TTI::SK_ExtractSubvector:
+      if (!isa<FixedVectorType>(SubTp))
+        return InstructionCost::getInvalid();
       return getExtractSubvectorOverhead(Tp, Index,
                                          cast<FixedVectorType>(SubTp));
     case TTI::SK_InsertSubvector:
+      if (!isa<FixedVectorType>(SubTp))
+        return InstructionCost::getInvalid();
       return getInsertSubvectorOverhead(Tp, Index,
                                         cast<FixedVectorType>(SubTp));
     }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D116362.397185.patch
Type: text/x-patch
Size: 5249 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220104/e9e3dace/attachment.bin>