[GISel][CombinerHelper] Combine shuffle_vector scalar to build_vector

Teach the combiner helper how to replace shuffle_vector of scalars
into build_vector.
I am not particularly happy about having to add this combine, but we
currently get those from <1 x iN> from the IR.

Bonus: This fixes an assert in the shuffle_vector combines since before
this patch, we were expecting vector types.

2 files changed, 65 insertions, 2 deletions

diff --git a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
index 854769d283f..bb7f751de90 100644
--- a/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
+++ b/llvm/lib/CodeGen/GlobalISel/CombinerHelper.cpp
@@ -190,7 +190,7 @@ bool CombinerHelper::matchCombineShuffleVector(MachineInstr &MI,
   Register Src1 = MI.getOperand(1).getReg();
   LLT SrcType = MRI.getType(Src1);
   unsigned DstNumElts = DstType.getNumElements();
-  unsigned SrcNumElts = SrcType.getNumElements();
+  unsigned SrcNumElts = SrcType.isVector() ? SrcType.getNumElements() : 1;
 
   // If the resulting vector is smaller than the size of the source
   // vectors being concatenated, we won't be able to replace the
@@ -254,7 +254,7 @@ void CombinerHelper::applyCombineShuffleVector(MachineInstr &MI,
   Builder.setInsertPt(*MI.getParent(), MI);
   Register NewDstReg = MRI.cloneVirtualRegister(DstReg);
 
-  Builder.buildConcatVectors(NewDstReg, Ops);
+  Builder.buildMerge(NewDstReg, Ops);
 
   MI.eraseFromParent();
   replaceRegWith(MRI, DstReg, NewDstReg);
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-shuffle-vector.mir b/llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-shuffle-vector.mir
index e3a27aa2b16..8694bff4746 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-shuffle-vector.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-shuffle-vector.mir
@@ -351,3 +351,66 @@ body:             |
     %6:_(<4 x p0>) = G_SHUFFLE_VECTOR %4(<2 x p0>), %5(<2 x p0>), shufflemask(0,1,2,3)
     RET_ReallyLR implicit %6
 ...
+
+# Check that shuffle_vector on scalars gets combined into build_vector.
+---
+name: shuffle_vector_on_scalars_to_build_vector_ptr
+tracksRegLiveness: true
+body:             |
+  bb.1:
+    liveins: $x0, $x1
+
+    ; CHECK-LABEL: name: shuffle_vector_on_scalars_to_build_vector_ptr
+    ; CHECK: liveins: $x0, $x1
+    ; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
+    ; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x p0>) = G_BUILD_VECTOR [[COPY]](p0), [[COPY1]](p0), [[COPY]](p0), [[COPY1]](p0)
+    ; CHECK: RET_ReallyLR implicit [[BUILD_VECTOR]](<4 x p0>)
+    %0:_(p0) = COPY $x0
+    %1:_(p0) = COPY $x1
+    %6:_(<4 x p0>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(0,1,0,1)
+    RET_ReallyLR implicit %6
+...
+
+# Check that shuffle_vector on scalars gets combined into build_vector,
+# even if we swap the order of the operands.
+---
+name: shuffle_vector_on_scalars_to_build_vector_swap_ptr
+tracksRegLiveness: true
+body:             |
+  bb.1:
+    liveins: $x0, $x1
+
+    ; CHECK-LABEL: name: shuffle_vector_on_scalars_to_build_vector_swap_ptr
+    ; CHECK: liveins: $x0, $x1
+    ; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
+    ; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p0>) = G_BUILD_VECTOR [[COPY1]](p0), [[COPY]](p0)
+    ; CHECK: RET_ReallyLR implicit [[BUILD_VECTOR]](<2 x p0>)
+    %0:_(p0) = COPY $x0
+    %1:_(p0) = COPY $x1
+    %6:_(<2 x p0>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(1,0)
+    RET_ReallyLR implicit %6
+...
+
+# Check that we properly use undef values when shuffle_vector
+# on scalars gets lowered to build_vector.
+---
+name: shuffle_vector_on_scalars_to_build_vector_with_undef
+tracksRegLiveness: true
+body:             |
+  bb.1:
+    liveins: $x0, $x1
+
+    ; CHECK-LABEL: name: shuffle_vector_on_scalars_to_build_vector_with_undef
+    ; CHECK: liveins: $x0, $x1
+    ; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $x0
+    ; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $x1
+    ; CHECK: [[DEF:%[0-9]+]]:_(s64) = G_IMPLICIT_DEF
+    ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s64>) = G_BUILD_VECTOR [[COPY]](s64), [[DEF]](s64), [[DEF]](s64), [[COPY1]](s64)
+    ; CHECK: RET_ReallyLR implicit [[BUILD_VECTOR]](<4 x s64>)
+    %0:_(s64) = COPY $x0
+    %1:_(s64) = COPY $x1
+    %6:_(<4 x s64>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(0,-1,-1,1)
+    RET_ReallyLR implicit %6
+...