ARM64: nick some AArch64 patterns for extract/insert -> INS.

Tests will be committed shortly when all optimisations needed to
support AArch64's neon-copy.ll file are supported.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@206571 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/ARM64/ARM64InstrInfo.td b/lib/Target/ARM64/ARM64InstrInfo.td
index a126cb8d7c057607d77e682462aa8f7fdad0ef55..509e215f82347254ac457a3291b57f48b141800c 100644 (file)
--- a/lib/Target/ARM64/ARM64InstrInfo.td
+++ b/lib/Target/ARM64/ARM64InstrInfo.td
@@ -3137,6 +3137,43 @@ def : Pat<(v2i64 (int_arm64_neon_vcopy_lane
                    V128:$Vd, VectorIndexD:$idx, V128:$Vs, VectorIndexD:$idx2)
           )>;
 
+multiclass Neon_INS_elt_pattern<ValueType VT128, ValueType VT64,
+                                ValueType VTScal, Instruction INS> {
+  def : Pat<(VT128 (vector_insert V128:$src,
+                        (VTScal (vector_extract (VT128 V128:$Rn), imm:$Immn)),
+                        imm:$Immd)),
+            (INS V128:$src, imm:$Immd, V128:$Rn, imm:$Immn)>;
+
+  def : Pat<(VT128 (vector_insert V128:$src,
+                        (VTScal (vector_extract (VT64 V64:$Rn), imm:$Immn)),
+                        imm:$Immd)),
+            (INS V128:$src, imm:$Immd,
+                 (SUBREG_TO_REG (i64 0), V64:$Rn, dsub), imm:$Immn)>;
+
+  def : Pat<(VT64 (vector_insert V64:$src,
+                        (VTScal (vector_extract (VT128 V128:$Rn), imm:$Immn)),
+                        imm:$Immd)),
+            (EXTRACT_SUBREG (INS (SUBREG_TO_REG (i64 0), V64:$src, dsub),
+                                 imm:$Immd, V128:$Rn, imm:$Immn),
+                            dsub)>;
+
+  def : Pat<(VT64 (vector_insert V64:$src,
+                        (VTScal (vector_extract (VT64 V64:$Rn), imm:$Immn)),
+                        imm:$Immd)),
+            (EXTRACT_SUBREG
+                (INS (SUBREG_TO_REG (i64 0), V64:$src, dsub), imm:$Immd,
+                     (SUBREG_TO_REG (i64 0), V64:$Rn, dsub), imm:$Immn),
+                dsub)>;
+}
+
+defm : Neon_INS_elt_pattern<v4f32, v2f32, f32, INSvi32lane>;
+defm : Neon_INS_elt_pattern<v2f64, v1f64, f64, INSvi64lane>;
+defm : Neon_INS_elt_pattern<v16i8, v8i8,  i32, INSvi8lane>;
+defm : Neon_INS_elt_pattern<v8i16, v4i16, i32, INSvi16lane>;
+defm : Neon_INS_elt_pattern<v4i32, v2i32, i32, INSvi32lane>;
+defm : Neon_INS_elt_pattern<v2i64, v1i64, i64, INSvi32lane>;
+
+
 // Floating point vector extractions are codegen'd as either a sequence of
 // subregister extractions, possibly fed by an INS if the lane number is
 // anything other than zero.