[LoongArch] Enable interleaved vectorization (llvm#92629)

This PR enables interleaved vectorization for LoongArch, with a default
interleaving factor of `2`.

Author: heiher

llvm/lib/Target/LoongArch/LoongArchSubtarget.h

@@ -37,6 +37,10 @@ class LoongArchSubtarget : public LoongArchGenSubtargetInfo {
 #include "LoongArchGenSubtargetInfo.inc"
 
   unsigned GRLen = 32;
+  // TODO: The default value is empirical and conservative. Override the
+  // default in initializeProperties once we support optimizing for more
+  // uarches.
+  uint8_t MaxInterleaveFactor = 2;
   MVT GRLenVT = MVT::i32;
   LoongArchABI::ABI TargetABI = LoongArchABI::ABI_Unknown;
   LoongArchFrameLowering FrameLowering;
@@ -99,6 +103,7 @@ class LoongArchSubtarget : public LoongArchGenSubtargetInfo {
   Align getPrefFunctionAlignment() const { return PrefFunctionAlignment; }
   Align getPrefLoopAlignment() const { return PrefLoopAlignment; }
   unsigned getMaxBytesForAlignment() const { return MaxBytesForAlignment; }
+  unsigned getMaxInterleaveFactor() const { return MaxInterleaveFactor; }
   bool enableMachineScheduler() const override { return true; }
 };
 } // end namespace llvm

llvm/lib/Target/LoongArch/LoongArchTargetTransformInfo.cpp

@@ -69,6 +69,10 @@ unsigned LoongArchTTIImpl::getRegisterClassForType(bool Vector,
   return LoongArchRegisterClass::GPRRC;
 }
 
+unsigned LoongArchTTIImpl::getMaxInterleaveFactor(ElementCount VF) {
+  return ST->getMaxInterleaveFactor();
+}
+
 const char *LoongArchTTIImpl::getRegisterClassName(unsigned ClassID) const {
   switch (ClassID) {
   case LoongArchRegisterClass::GPRRC:

llvm/lib/Target/LoongArch/LoongArchTargetTransformInfo.h

@@ -43,6 +43,7 @@ class LoongArchTTIImpl : public BasicTTIImplBase<LoongArchTTIImpl> {
   TypeSize getRegisterBitWidth(TargetTransformInfo::RegisterKind K) const;
   unsigned getNumberOfRegisters(unsigned ClassID) const;
   unsigned getRegisterClassForType(bool Vector, Type *Ty = nullptr) const;
+  unsigned getMaxInterleaveFactor(ElementCount VF);
   const char *getRegisterClassName(unsigned ClassID) const;
 
   // TODO: Implement more hooks to provide TTI machinery for LoongArch.

llvm/test/Transforms/LoopVectorize/LoongArch/defaults.ll

@@ -22,14 +22,20 @@ define void @vector_add(ptr noalias nocapture %a, i64 %v) {
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[TMP0]]
-; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[TMP1]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i64>, ptr [[TMP2]], align 8
-; CHECK-NEXT:    [[TMP3:%.*]] = add <4 x i64> [[WIDE_LOAD]], [[BROADCAST_SPLAT]]
-; CHECK-NEXT:    store <4 x i64> [[TMP3]], ptr [[TMP2]], align 8
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[TMP0]]
+; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[TMP1]]
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i64, ptr [[TMP2]], i32 0
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i64, ptr [[TMP2]], i32 4
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i64>, ptr [[TMP4]], align 8
+; CHECK-NEXT:    [[WIDE_LOAD1:%.*]] = load <4 x i64>, ptr [[TMP5]], align 8
+; CHECK-NEXT:    [[TMP6:%.*]] = add <4 x i64> [[WIDE_LOAD]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[TMP7:%.*]] = add <4 x i64> [[WIDE_LOAD1]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    store <4 x i64> [[TMP6]], ptr [[TMP4]], align 8
+; CHECK-NEXT:    store <4 x i64> [[TMP7]], ptr [[TMP5]], align 8
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
+; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
+; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:

llvm/test/Transforms/LoopVectorize/LoongArch/loongarch-interleaved.ll

@@ -0,0 +1,39 @@
+; REQUIRES: asserts
+; RUN: opt --passes=loop-vectorize,dce,instcombine --mtriple loongarch64 \
+; RUN:   -S < %s 2>&1 | FileCheck %s
+
+; CHECK-LABEL: foo
+; CHECK: %{{.*}} = add {{.*}}, 2
+
+; Function Attrs: nofree norecurse nosync nounwind writeonly
+define dso_local void @foo(i32 signext %n, ptr nocapture %A) local_unnamed_addr #0 {
+entry:
+  %cmp5 = icmp sgt i32 %n, 0
+  br i1 %cmp5, label %for.body.preheader, label %for.cond.cleanup
+
+for.body.preheader:                               ; preds = %entry
+  %wide.trip.count = zext i32 %n to i64
+  br label %for.body
+
+for.cond.cleanup.loopexit:                        ; preds = %for.body
+  br label %for.cond.cleanup
+
+for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
+  ret void
+
+for.body:                                         ; preds = %for.body.preheader, %for.body
+  %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32, ptr %A, i64 %indvars.iv
+  %0 = trunc i64 %indvars.iv to i32
+  store i32 %0, ptr %arrayidx, align 4, !tbaa !4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
+  br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body, !llvm.loop !8
+}
+
+!4 = !{!5, !5, i64 0}
+!5 = !{!"int", !6, i64 0}
+!6 = !{!"omnipotent char", !7, i64 0}
+!7 = !{!"Simple C/C++ TBAA"}
+!8 = distinct !{!8, !9}
+!9 = !{!"llvm.loop.mustprogress"}