[llvm] [clang] [AArch64] Add quadword gather load/scatter store intrinsics with unscaled vector offset (PR #71290)

[via cfe-commits]

================
@@ -298,6 +298,38 @@ let TargetGuard = "sve,bf16" in {
   def SVBFMLALT_LANE : SInst<"svbfmlalt_lane[_{0}]", "MMddi", "b", MergeNone, "aarch64_sve_bfmlalt_lane_v2", [IsOverloadNone], [ImmCheck<3, ImmCheck0_7>]>;
 }
 
+let TargetGuard = "sve2p1" in {
+  // Contiguous zero-extending load to quadword (single vector).
+  def SVLD1UWQ      : MInst<"svld1uwq[_{d}]", "dPc",  "iUif", [IsLoad], MemEltTyInt32, "aarch64_sve_ld1uwq">;
+  def SVLD1UWQ_VNUM : MInst<"svld1uwq_vnum[_{d}]", "dPcl", "iUif", [IsLoad], MemEltTyInt32, "aarch64_sve_ld1uwq">;
+
+  def SVLD1UDQ      : MInst<"svld1udq[_{d}]", "dPc",  "lUld", [IsLoad], MemEltTyInt64, "aarch64_sve_ld1udq">;
+  def SVLD1UDQ_VNUM : MInst<"svld1udq_vnum[_{d}]", "dPcl", "lUld", [IsLoad], MemEltTyInt64, "aarch64_sve_ld1udq">;
+
+  // Load one vector (vector base + scalar offset)
+  def SVLD1Q_GATHER_U64BASE_OFFSET : MInst<"svld1q_gather[_{2}base]_offset_{d}", "dPgl", "cUcsUsiUilUlfhdb", [IsGatherLoad, IsByteIndexed], MemEltTyDefault, "aarch64_sve_ld1q_gather_scalar_offset">;
+  def SVLD1Q_GATHER_U64BASE : MInst<"svld1q_gather[_{2}base]_{d}", "dPg", "cUcsUsiUilUlfhdb", [IsGatherLoad, IsByteIndexed], MemEltTyDefault, "aarch64_sve_ld1q_gather_scalar_offset">;
+
+  // Load one vector (scalar base + vector offset)
+  def SVLD1Q_GATHER_U64OFFSET : MInst<"svld1q_gather_[{3}]offset[_{0}]", "dPcg", "cUcsUsiUilUlfhdb", [IsGatherLoad, IsByteIndexed], MemEltTyDefault, "aarch64_sve_ld1q_gather_vector_offset">;
+
+  // Load N-element structure into N vectors (scalar base)
+  defm SVLD2Q : StructLoad<"svld2q[_{2}]", "2Pc", "aarch64_sve_ld2q_sret">;
+  defm SVLD3Q : StructLoad<"svld3q[_{2}]", "3Pc", "aarch64_sve_ld3q_sret">;
+  defm SVLD4Q : StructLoad<"svld4q[_{2}]", "4Pc", "aarch64_sve_ld4q_sret">;
+
+  // Load N-element structure into N vectors (scalar base, VL displacement)
+  defm SVLD2Q_VNUM : StructLoad<"svld2q_vnum[_{2}]", "2Pcl", "aarch64_sve_ld2q_sret">;
+  defm SVLD3Q_VNUM : StructLoad<"svld3q_vnum[_{2}]", "3Pcl", "aarch64_sve_ld3q_sret">;
+  defm SVLD4Q_VNUM : StructLoad<"svld4q_vnum[_{2}]", "4Pcl", "aarch64_sve_ld4q_sret">;
+
+  // Load quadwords (scalar base + vector index)
+  def SVLD1Q_GATHER_INDICES_U : MInst<"svld1q_gather_[{3}]index[_{0}]",    "dPcg", "sUsiUilUlbhfd", [IsGatherLoad], MemEltTyDefault, "aarch64_sve_ld1q_gather_index">;
+
+  // Load quadwords (vector base + scalar index)
+  def SVLD1Q_GATHER_INDEX_S   : MInst<"svld1q_gather[_{2}base]_index_{0}", "dPgl", "sUsiUilUlbhfd", [IsGatherLoad], MemEltTyDefault, "aarch64_sve_ld1q_gather_scalar_offset">;
----------------
CarolineConcatto wrote:

s/svld1q_gather[_{2}base]_index_{0}/svld1q_gather[_{2}base]_index_{d}

https://github.com/llvm/llvm-project/pull/71290