[AArch64][GlobalISel] Lower shuffle vector with scalar destinations.

I believe these are usually canonicalized to vector extracts in most
situations, but under -O0 we might trigger failures in the widening code if we
do not handle scalar destinations correctly. The simplest solution should be to
lower the shuffle to an extract.

Author: davemgreen

llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp

@@ -1062,10 +1062,11 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
         return llvm::is_contained(
             {v2s64, v2s32, v4s32, v4s16, v16s8, v8s8, v8s16}, DstTy);
       })
-      // G_SHUFFLE_VECTOR can have scalar sources (from 1 x s vectors), we
-      // just want those lowered into G_BUILD_VECTOR
+      // G_SHUFFLE_VECTOR can have scalar sources (from 1 x s vectors) or scalar
+      // destinations, we just want those lowered into G_BUILD_VECTOR or
+      // G_EXTRACT_ELEMENT.
       .lowerIf([=](const LegalityQuery &Query) {
-        return !Query.Types[1].isVector();
+        return !Query.Types[0].isVector() || !Query.Types[1].isVector();
       })
       .moreElementsIf(
           [](const LegalityQuery &Query) {

llvm/test/CodeGen/AArch64/GlobalISel/legalize-shuffle-1x.ll

@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple aarch64 -O0 -global-isel -o - %s | FileCheck %s
+
+define <1 x i1> @shuffle_extract_4(<8 x i1> %a, <8 x i1> %b) {
+; CHECK-LABEL: shuffle_extract_4:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ushll v0.8h, v0.8b, #0
+; CHECK-NEXT:    umov w8, v0.h[4]
+; CHECK-NEXT:    and w0, w8, #0x1
+; CHECK-NEXT:    ret
+  %extractvec60 = shufflevector <8 x i1> %a, <8 x i1> %b, <1 x i32> <i32 4>
+  ret <1 x i1> %extractvec60
+}
+
+define <1 x i1> @shuffle_extract_12(<8 x i1> %a, <8 x i1> %b) {
+; CHECK-LABEL: shuffle_extract_12:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    ushll v0.8h, v1.8b, #0
+; CHECK-NEXT:    umov w8, v0.h[4]
+; CHECK-NEXT:    and w0, w8, #0x1
+; CHECK-NEXT:    ret
+  %extractvec60 = shufflevector <8 x i1> %a, <8 x i1> %b, <1 x i32> <i32 12>
+  ret <1 x i1> %extractvec60
+}
+
+define <1 x i1> @shuffle_extract_p(<8 x i1> %a, <8 x i1> %b) {
+; CHECK-LABEL: shuffle_extract_p:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    // implicit-def: $w8
+; CHECK-NEXT:    and w0, w8, #0x1
+; CHECK-NEXT:    ret
+  %extractvec60 = shufflevector <8 x i1> %a, <8 x i1> %b, <1 x i32> <i32 poison>
+  ret <1 x i1> %extractvec60
+}
+
+define <1 x i32> @shufflevector_v1i32(<1 x i32> %a, <1 x i32> %b) {
+; CHECK-LABEL: shufflevector_v1i32:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    fmov d0, d1
+; CHECK-NEXT:    ret
+    %c = shufflevector <1 x i32> %a, <1 x i32> %b, <1 x i32> <i32 1>
+    ret <1 x i32> %c
+}

llvm/test/CodeGen/AArch64/GlobalISel/legalize-shuffle-vector.mir

@@ -618,3 +618,32 @@ body:             |
     RET_ReallyLR implicit $q0
 
 ...
+---
+name:            shuffle_v8i1_v1i8
+alignment:       4
+tracksRegLiveness: true
+body:             |
+  bb.1:
+    liveins: $d0, $d1
+    ; CHECK-LABEL: name: shuffle_v8i1_v1i8
+    ; CHECK: liveins: $d0, $d1
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: [[COPY:%[0-9]+]]:_(<8 x s8>) = COPY $d1
+    ; CHECK-NEXT: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 4
+    ; CHECK-NEXT: [[ANYEXT:%[0-9]+]]:_(<8 x s16>) = G_ANYEXT [[COPY]](<8 x s8>)
+    ; CHECK-NEXT: [[EVEC:%[0-9]+]]:_(s16) = G_EXTRACT_VECTOR_ELT [[ANYEXT]](<8 x s16>), [[C]](s64)
+    ; CHECK-NEXT: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[EVEC]](s16)
+    ; CHECK-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+    ; CHECK-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[ANYEXT1]], [[C1]]
+    ; CHECK-NEXT: $w0 = COPY [[AND]](s32)
+    ; CHECK-NEXT: RET_ReallyLR implicit $w0
+    %2:_(<8 x s8>) = COPY $d0
+    %0:_(<8 x s1>) = G_TRUNC %2:_(<8 x s8>)
+    %3:_(<8 x s8>) = COPY $d1
+    %1:_(<8 x s1>) = G_TRUNC %3:_(<8 x s8>)
+    %4:_(s1) = G_SHUFFLE_VECTOR %0:_(<8 x s1>), %1:_, shufflemask(12)
+    %5:_(s8) = G_ZEXT %4:_(s1)
+    %6:_(s32) = G_ANYEXT %5:_(s8)
+    $w0 = COPY %6:_(s32)
+    RET_ReallyLR implicit $w0
+...