diff --git a/clang/include/clang/Basic/arm_sve.td b/clang/include/clang/Basic/arm_sve.td
index a1ac926ab9577..cd4c09a3ad7a8 100644
--- a/clang/include/clang/Basic/arm_sve.td
+++ b/clang/include/clang/Basic/arm_sve.td
@@ -310,6 +310,9 @@ let TargetGuard = "sve2p1" in {
   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[_{d}]", "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">;
@@ -461,6 +464,9 @@ let TargetGuard = "sve2p1" in {
   def SVST1Q_SCATTER_U64BASE_OFFSET : MInst<"svst1q_scatter[_{2}base]_offset[_{d}]",  "vPgld", "cUcsUsiUilUlfhdb", [IsScatterStore, IsByteIndexed], MemEltTyDefault, "aarch64_sve_st1q_scatter_scalar_offset">;
   def SVST1Q_SCATTER_U64BASE : MInst<"svst1q_scatter[_{2}base][_{d}]",  "vPgd", "cUcsUsiUilUlfhdb", [IsScatterStore, IsByteIndexed], MemEltTyDefault, "aarch64_sve_st1q_scatter_scalar_offset">;
 
+  // Store one vector (scalar base + vector offset)
+  def SVST1Q_SCATTER_U64OFFSET : MInst<"svst1q_scatter_[{3}]offset[_{d}]", "vPpgd", "cUcsUsiUilUlfhdb", [IsScatterStore, IsByteIndexed], MemEltTyDefault, "aarch64_sve_st1q_scatter_vector_offset">;
+
   // Store N vectors into N-element structure (scalar base)
   defm SVST2Q : StructStore<"svst2q[_{d}]", "vPc2", "aarch64_sve_st2q">;
   defm SVST3Q : StructStore<"svst3q[_{d}]", "vPc3", "aarch64_sve_st3q">;
diff --git a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_loads.c b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_loads.c
index 44351347e4cf0..ae3ddd416f7ee 100644
--- a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_loads.c
+++ b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_loads.c
@@ -2868,3 +2868,195 @@ svfloat32_t test_svld1q_gather_u64base_index_f32(svbool_t pg, svuint64_t base, i
 svfloat64_t test_svld1q_gather_u64base_index_f64(svbool_t pg, svuint64_t base, int64_t idx) {
   return SVE_ACLE_FUNC(svld1q_gather,_u64base,_index_f64,)(pg, base, idx);
 }
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_s8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv16i8(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z31test_svdl1q_gather_u64offset_s8u10__SVBool_tPKau12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv16i8(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+//
+svint8_t test_svdl1q_gather_u64offset_s8(svbool_t pg, const int8_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_s8)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_u8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv16i8(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z31test_svdl1q_gather_u64offset_u8u10__SVBool_tPKhu12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv16i8(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 16 x i8> [[TMP1]]
+//
+svuint8_t test_svdl1q_gather_u64offset_u8(svbool_t pg, const uint8_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_u8)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_s16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8i16(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z32test_svdl1q_gather_u64offset_s16u10__SVBool_tPKsu12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8i16(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+//
+svint16_t test_svdl1q_gather_u64offset_s16(svbool_t pg, const int16_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_s16)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_u16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8i16(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z32test_svdl1q_gather_u64offset_u16u10__SVBool_tPKtu12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8i16(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 8 x i16> [[TMP1]]
+//
+svuint16_t test_svdl1q_gather_u64offset_u16(svbool_t pg, const uint16_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_u16)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_s32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z32test_svdl1q_gather_u64offset_s32u10__SVBool_tPKiu12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+//
+svint32_t test_svdl1q_gather_u64offset_s32(svbool_t pg, const int32_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_s32)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_u32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z32test_svdl1q_gather_u64offset_u32u10__SVBool_tPKju12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4i32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 4 x i32> [[TMP1]]
+//
+svuint32_t test_svdl1q_gather_u64offset_u32(svbool_t pg, const uint32_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_u32)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_s64(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2i64(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z32test_svdl1q_gather_u64offset_s64u10__SVBool_tPKlu12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2i64(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+//
+svint64_t test_svdl1q_gather_u64offset_s64(svbool_t pg, const int64_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_s64)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_u64(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2i64(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z32test_svdl1q_gather_u64offset_u64u10__SVBool_tPKmu12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2i64(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 2 x i64> [[TMP1]]
+//
+svuint64_t test_svdl1q_gather_u64offset_u64(svbool_t pg, const uint64_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_u64)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_bf16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8bf16(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z33test_svdl1q_gather_u64offset_bf16u10__SVBool_tPKu6__bf16u12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8bf16(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 8 x bfloat> [[TMP1]]
+//
+svbfloat16_t test_svdl1q_gather_u64offset_bf16(svbool_t pg, const bfloat16_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_bf16)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_f16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8f16(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z32test_svdl1q_gather_u64offset_f16u10__SVBool_tPKDhu12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 8 x half> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8f16(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 8 x half> [[TMP1]]
+//
+svfloat16_t test_svdl1q_gather_u64offset_f16(svbool_t pg, const float16_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_f16)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_f32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4f32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z32test_svdl1q_gather_u64offset_f32u10__SVBool_tPKfu12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 4 x float> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4f32(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 4 x float> [[TMP1]]
+//
+svfloat32_t test_svdl1q_gather_u64offset_f32(svbool_t pg, const float32_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_f32)(pg, base, off);
+}
+
+// CHECK-LABEL: @test_svdl1q_gather_u64offset_f64(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2f64(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+//
+// CPP-CHECK-LABEL: @_Z32test_svdl1q_gather_u64offset_f64u10__SVBool_tPKdu12__SVUint64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    [[TMP1:%.*]] = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2f64(<vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret <vscale x 2 x double> [[TMP1]]
+//
+svfloat64_t test_svdl1q_gather_u64offset_f64(svbool_t pg, const float64_t *base, svuint64_t off) {
+  return SVE_ACLE_FUNC(svld1q_gather_,u64,offset,_f64)(pg, base, off);
+}
diff --git a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_store.c b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_store.c
index 137801cc0814a..2cbea29d33904 100644
--- a/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_store.c
+++ b/clang/test/CodeGen/aarch64-sve2p1-intrinsics/acle_sve2p1_store.c
@@ -2470,3 +2470,195 @@ void test_svst1q_scatter_u64base_index_f32(svbool_t pg, svuint64_t base, int64_t
 void test_svst1q_scatter_u64base_index_f64(svbool_t pg, svuint64_t base, int64_t idx, svfloat64_t data) {
   SVE_ACLE_FUNC(svst1q_scatter,_u64base,_index,_f64)(pg, base, idx, data);
 }
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_s8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z32test_svst1q_scatter_u64offset_s8u10__SVBool_tPau12__SVUint64_tu10__SVInt8_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_s8(svbool_t pg, int8_t *base, svuint64_t off, svint8_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_s8)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_u8(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z32test_svst1q_scatter_u64offset_u8u10__SVBool_tPhu12__SVUint64_tu11__SVUint8_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv16i8(<vscale x 16 x i8> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_u8(svbool_t pg, uint8_t *base, svuint64_t off, svuint8_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_u8)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_s16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z33test_svst1q_scatter_u64offset_s16u10__SVBool_tPsu12__SVUint64_tu11__SVInt16_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_s16(svbool_t pg, int16_t *base, svuint64_t off, svint16_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_s16)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_u16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z33test_svst1q_scatter_u64offset_u16u10__SVBool_tPtu12__SVUint64_tu12__SVUint16_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8i16(<vscale x 8 x i16> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_u16(svbool_t pg, uint16_t *base, svuint64_t off, svuint16_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_u16)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_s32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z33test_svst1q_scatter_u64offset_s32u10__SVBool_tPiu12__SVUint64_tu11__SVInt32_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_s32(svbool_t pg, int32_t *base, svuint64_t off, svint32_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_s32)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_u32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z33test_svst1q_scatter_u64offset_u32u10__SVBool_tPju12__SVUint64_tu12__SVUint32_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4i32(<vscale x 4 x i32> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_u32(svbool_t pg, uint32_t *base, svuint64_t off, svuint32_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_u32)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_s64(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z33test_svst1q_scatter_u64offset_s64u10__SVBool_tPlu12__SVUint64_tu11__SVInt64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_s64(svbool_t pg, int64_t *base, svuint64_t off, svint64_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_s64)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_u64(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z33test_svst1q_scatter_u64offset_u64u10__SVBool_tPmu12__SVUint64_tS1_(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2i64(<vscale x 2 x i64> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_u64(svbool_t pg, uint64_t *base, svuint64_t off, svuint64_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_u64)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_bf16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8bf16(<vscale x 8 x bfloat> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z34test_svst1q_scatter_u64offset_bf16u10__SVBool_tPu6__bf16u12__SVUint64_tu14__SVBfloat16_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8bf16(<vscale x 8 x bfloat> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_bf16(svbool_t pg, bfloat16_t *base, svuint64_t off, svbfloat16_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_bf16)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_f16(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8f16(<vscale x 8 x half> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z33test_svst1q_scatter_u64offset_f16u10__SVBool_tPDhu12__SVUint64_tu13__SVFloat16_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8f16(<vscale x 8 x half> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_f16(svbool_t pg, float16_t *base, svuint64_t off, svfloat16_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_f16)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_f32(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4f32(<vscale x 4 x float> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z33test_svst1q_scatter_u64offset_f32u10__SVBool_tPfu12__SVUint64_tu13__SVFloat32_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4f32(<vscale x 4 x float> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_f32(svbool_t pg, float32_t *base, svuint64_t off, svfloat32_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_f32)(pg, base, off, data);
+}
+
+// CHECK-LABEL: @test_svst1q_scatter_u64offset_f64(
+// CHECK-NEXT:  entry:
+// CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2f64(<vscale x 2 x double> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CHECK-NEXT:    ret void
+//
+// CPP-CHECK-LABEL: @_Z33test_svst1q_scatter_u64offset_f64u10__SVBool_tPdu12__SVUint64_tu13__SVFloat64_t(
+// CPP-CHECK-NEXT:  entry:
+// CPP-CHECK-NEXT:    [[TMP0:%.*]] = tail call <vscale x 1 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv1i1(<vscale x 16 x i1> [[PG:%.*]])
+// CPP-CHECK-NEXT:    tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2f64(<vscale x 2 x double> [[DATA:%.*]], <vscale x 1 x i1> [[TMP0]], ptr [[BASE:%.*]], <vscale x 2 x i64> [[OFF:%.*]])
+// CPP-CHECK-NEXT:    ret void
+//
+void test_svst1q_scatter_u64offset_f64(svbool_t pg, float64_t *base, svuint64_t off, svfloat64_t data) {
+  SVE_ACLE_FUNC(svst1q_scatter_,u64,offset,_f64)(pg, base, off, data);
+}
diff --git a/llvm/include/llvm/IR/IntrinsicsAArch64.td b/llvm/include/llvm/IR/IntrinsicsAArch64.td
index a558a1eca84af..60a8d98f3bc0d 100644
--- a/llvm/include/llvm/IR/IntrinsicsAArch64.td
+++ b/llvm/include/llvm/IR/IntrinsicsAArch64.td
@@ -2166,6 +2166,9 @@ def int_aarch64_sve_ld1_gather_uxtw_index : AdvSIMD_GatherLoad_SV_32b_Offsets_In
 // 128-bit loads, scaled offsets (indices)
 def int_aarch64_sve_ld1q_gather_index : AdvSIMD_GatherLoadQ_SV_Intrinsic;
 
+// 128-bit loads, unscaled offsets
+def int_aarch64_sve_ld1q_gather_vector_offset : AdvSIMD_GatherLoadQ_SV_Intrinsic;
+
 //
 // Gather loads: vector base + scalar offset
 //
@@ -2247,6 +2250,9 @@ def int_aarch64_sve_st1_scatter_uxtw_index
 // 128-bit stores, scaled offsets (indices)
 def int_aarch64_sve_st1q_scatter_index : AdvSIMD_ScatterStoreQ_SV_Intrinsic;
 
+// 128-bit stores, unscaled offsets
+def int_aarch64_sve_st1q_scatter_vector_offset : AdvSIMD_ScatterStoreQ_SV_Intrinsic;
+
 //
 // Scatter stores: vector base + scalar offset
 //
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index c48e8a5610142..28e038abcecfc 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -23748,6 +23748,7 @@ SDValue AArch64TargetLowering::PerformDAGCombine(SDNode *N,
     case Intrinsic::aarch64_sve_ld1_gather:
       return performGatherLoadCombine(N, DAG, AArch64ISD::GLD1_MERGE_ZERO);
     case Intrinsic::aarch64_sve_ld1q_gather_scalar_offset:
+    case Intrinsic::aarch64_sve_ld1q_gather_vector_offset:
       return performGatherLoadCombine(N, DAG, AArch64ISD::GLD1Q_MERGE_ZERO);
     case Intrinsic::aarch64_sve_ld1q_gather_index:
       return performGatherLoadCombine(N, DAG,
@@ -23796,6 +23797,7 @@ SDValue AArch64TargetLowering::PerformDAGCombine(SDNode *N,
       return performGatherLoadCombine(N, DAG,
                                       AArch64ISD::GLDFF1_IMM_MERGE_ZERO);
     case Intrinsic::aarch64_sve_st1q_scatter_scalar_offset:
+    case Intrinsic::aarch64_sve_st1q_scatter_vector_offset:
       return performScatterStoreCombine(N, DAG, AArch64ISD::SST1Q_PRED);
     case Intrinsic::aarch64_sve_st1q_scatter_index:
       return performScatterStoreCombine(N, DAG, AArch64ISD::SST1Q_INDEX_PRED);
diff --git a/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-gather-loads-128bit-unscaled-offset.ll b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-gather-loads-128bit-unscaled-offset.ll
index 64f15897ebb9a..8bee44be9f0cd 100644
--- a/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-gather-loads-128bit-unscaled-offset.ll
+++ b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-gather-loads-128bit-unscaled-offset.ll
@@ -94,6 +94,126 @@ define <vscale x 8 x bfloat> @ld1q_gather_u64base_bf16(<vscale x 1 x i1> %pg, <v
   ret <vscale x 8 x bfloat> %load
 }
 
+define <vscale x 16 x i8> @test_svdl1q_gather_u64offset_s8(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_s8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv16i8(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 16 x i8> %0
+}
+
+define <vscale x 16 x i8> @test_svdl1q_gather_u64offset_u8(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_u8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 16 x i8> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv16i8(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 16 x i8> %0
+}
+
+define <vscale x 8 x i16> @test_svdl1q_gather_u64offset_s16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_s16:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8i16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 8 x i16> %0
+}
+
+define <vscale x 8 x i16> @test_svdl1q_gather_u64offset_u16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_u16:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 8 x i16> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8i16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 8 x i16> %0
+}
+
+define <vscale x 4 x i32> @test_svdl1q_gather_u64offset_s32(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_s32:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4i32(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 4 x i32> %0
+}
+
+define <vscale x 4 x i32> @test_svdl1q_gather_u64offset_u32(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_u32:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 4 x i32> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4i32(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 4 x i32> %0
+}
+
+define <vscale x 2 x i64> @test_svdl1q_gather_u64offset_s64(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_s64:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2i64(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 2 x i64> %0
+}
+
+define <vscale x 2 x i64> @test_svdl1q_gather_u64offset_u64(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_u64:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 2 x i64> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2i64(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 2 x i64> %0
+}
+
+define <vscale x 8 x bfloat> @test_svdl1q_gather_u64offset_bf16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_bf16:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 8 x bfloat> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8bf16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 8 x bfloat> %0
+}
+
+define <vscale x 8 x half> @test_svdl1q_gather_u64offset_f16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_f16:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 8 x half> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8f16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 8 x half> %0
+}
+
+define <vscale x 4 x float> @test_svdl1q_gather_u64offset_f32(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_f32:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 4 x float> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4f32(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 4 x float> %0
+}
+
+define <vscale x 2 x double> @test_svdl1q_gather_u64offset_f64(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off) {
+; CHECK-LABEL: test_svdl1q_gather_u64offset_f64:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    ld1q { z0.q }, p0/z, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 2 x double> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2f64(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret <vscale x 2 x double> %0
+}
+
 declare <vscale x 16 x i8> @llvm.aarch64.sve.ld1q.gather.scalar.offset.nxv16i8.nxv2i64(<vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare <vscale x 8 x i16> @llvm.aarch64.sve.ld1q.gather.scalar.offset.nxv8i16.nxv2i64(<vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare <vscale x 4 x i32> @llvm.aarch64.sve.ld1q.gather.scalar.offset.nxv4i32.nxv2i64(<vscale x 1 x i1>, <vscale x 2 x i64>, i64)
@@ -102,4 +222,11 @@ declare <vscale x 8 x half> @llvm.aarch64.sve.ld1q.gather.scalar.offset.nxv8f16.
 declare <vscale x 4 x float> @llvm.aarch64.sve.ld1q.gather.scalar.offset.nxv4f32.nxv2i64(<vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare <vscale x 2 x double> @llvm.aarch64.sve.ld1q.gather.scalar.offset.nxv2f64.nxv2i64(<vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare <vscale x 8 x bfloat> @llvm.aarch64.sve.ld1q.gather.scalar.offset.nxv8bf16.nxv2i64(<vscale x 1 x i1>, <vscale x 2 x i64>, i64)
-
+declare <vscale x 16 x i8> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv16i8(<vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8i16(<vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4i32(<vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2i64(<vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare <vscale x 8 x bfloat> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8bf16(<vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare <vscale x 8 x half> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv8f16(<vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare <vscale x 4 x float> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv4f32(<vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare <vscale x 2 x double> @llvm.aarch64.sve.ld1q.gather.vector.offset.nxv2f64(<vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
diff --git a/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-scatter-stores-128bit-unscaled-offset.ll b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-scatter-stores-128bit-unscaled-offset.ll
index c62df1d8d254c..6493640c06abd 100644
--- a/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-scatter-stores-128bit-unscaled-offset.ll
+++ b/llvm/test/CodeGen/AArch64/sve2p1-intrinsics-scatter-stores-128bit-unscaled-offset.ll
@@ -102,12 +102,139 @@ define void @sst1_scatter_u64base_offset_bf16(<vscale x 8 x bfloat> %data, <vsca
   ret void
 }
 
+define void @test_svst1q_scatter_u64offset_s8(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 16 x i8> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_s8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv16i8(<vscale x 16 x i8> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_u8(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 16 x i8> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_u8:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv16i8(<vscale x 16 x i8> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_s16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 8 x i16> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_s16:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8i16(<vscale x 8 x i16> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_u16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 8 x i16> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_u16:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8i16(<vscale x 8 x i16> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_s32(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 4 x i32> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_s32:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4i32(<vscale x 4 x i32> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_u32(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 4 x i32> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_u32:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4i32(<vscale x 4 x i32> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_s64(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 2 x i64> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_s64:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2i64(<vscale x 2 x i64> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_u64(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 2 x i64> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_u64:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2i64(<vscale x 2 x i64> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_bf16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 8 x bfloat> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_bf16:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8bf16(<vscale x 8 x bfloat> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_f16(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 8 x half> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_f16:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8f16(<vscale x 8 x half> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_f32(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 4 x float> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_f32:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4f32(<vscale x 4 x float> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
+define void @test_svst1q_scatter_u64offset_f64(<vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off, <vscale x 2 x double> %data) {
+; CHECK-LABEL: test_svst1q_scatter_u64offset_f64:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    st1q { z1.q }, p0, [z0.d, x0]
+; CHECK-NEXT:    ret
+entry:
+  tail call void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2f64(<vscale x 2 x double> %data, <vscale x 1 x i1> %pg, ptr %base, <vscale x 2 x i64> %off)
+  ret void
+}
+
 declare void @llvm.aarch64.sve.st1q.scatter.scalar.offset.nxv16i8.nxv2i64(<vscale x 16 x i8>, <vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare void @llvm.aarch64.sve.st1q.scatter.scalar.offset.nxv8i16.nxv2i64(<vscale x 8 x i16>, <vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare void @llvm.aarch64.sve.st1q.scatter.scalar.offset.nxv4i32.nxv2i64(<vscale x 4 x i32>, <vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare void @llvm.aarch64.sve.st1q.scatter.scalar.offset.nxv2i64.nxv2i64(<vscale x 2 x i64>, <vscale x 1 x i1>, <vscale x 2 x i64>, i64)
-
 declare void @llvm.aarch64.sve.st1q.scatter.scalar.offset.nxv8f16.nxv2i64(<vscale x 8 x half>, <vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare void @llvm.aarch64.sve.st1q.scatter.scalar.offset.nxv4f32.nxv2i64(<vscale x 4 x float>, <vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare void @llvm.aarch64.sve.st1q.scatter.scalar.offset.nxv2f64.nxv2i64(<vscale x 2 x double>, <vscale x 1 x i1>, <vscale x 2 x i64>, i64)
 declare void @llvm.aarch64.sve.st1q.scatter.scalar.offset.nxv8bf16.nxv2i64(<vscale x 8 x bfloat>, <vscale x 1 x i1>, <vscale x 2 x i64>, i64)
+declare void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv16i8(<vscale x 16 x i8>, <vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8i16(<vscale x 8 x i16>, <vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4i32(<vscale x 4 x i32>, <vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2i64(<vscale x 2 x i64>, <vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv8f16(<vscale x 8 x half>, <vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv4f32(<vscale x 4 x float>, <vscale x 1 x i1>, ptr, <vscale x 2 x i64>)
+declare void @llvm.aarch64.sve.st1q.scatter.vector.offset.nxv2f64(<vscale x 2 x double>, <vscale x 1 x i1>, ptr, <vscale x 2 x i64>)