diff mbox series

Re：[PATCH v5] RISC-V: Add support for xtheadvector-specific intrinsics.

Message ID fe6c4cd7-993d-43f2-a3c2-541f13bbbf1f.cooper.joshua@linux.alibaba.com
State Superseded
Headers
Series Re：[PATCH v5] RISC-V: Add support for xtheadvector-specific intrinsics. |

Checks

Context Check Description
rivoscibot/toolchain-ci-rivos-lint warning Lint failed
rivoscibot/toolchain-ci-rivos-apply-patch fail Patch failed to apply
linaro-tcwg-bot/tcwg_gcc_build--master-aarch64 fail Patch failed to apply
linaro-tcwg-bot/tcwg_gcc_build--master-arm fail Patch failed to apply

Commit Message

joshua Jan. 11, 2024, 9:54 a.m. UTC 
  The "Add support for xtheadvector-specific intrinsics" patch has been updated
according to the comments.
[PATCH v5] RISC-V: Add support for xtheadvector-specific intrinsics. (gnu.org) <https://gcc.gnu.org/pipermail/gcc-patches/2024-January/642627.html >
------------------------------------------------------------------
发件人：juzhe.zhong@rivai.ai <juzhe.zhong@rivai.ai>
发送时间：2024年1月11日(星期四) 17:07
收件人："cooper.joshua"<cooper.joshua@linux.alibaba.com>; "gcc-patches"<gcc-patches@gcc.gnu.org>
抄　送：Jim Wilson<jim.wilson.gcc@gmail.com>; palmer<palmer@dabbelt.com>; andrew<andrew@sifive.com>; "philipp.tomsich"<philipp.tomsich@vrull.eu>; jeffreyalaw<jeffreyalaw@gmail.com>; "christoph.muellner"<christoph.muellner@vrull.eu>; "cooper.joshua"<cooper.joshua@linux.alibaba.com>; jinma<jinma@linux.alibaba.com>; "cooper.qu"<cooper.qu@linux.alibaba.com>
主　题：Re: [PATCH v5] RISC-V: Add support for xtheadvector-specific intrinsics.
enum required_ext
{
 VECTOR_EXT, /* Vector extension */
+ XTHEADVECTOR_EXT, /* XTheadVector extension */
 ZVBB_EXT, /* Cryto vector Zvbb sub-ext */
 ZVBB_OR_ZVKB_EXT, /* Cryto vector Zvbb or zvkb sub-ext */
 ZVBC_EXT, /* Crypto vector Zvbc sub-ext */
Add theadvector to the end of the enum.
+ case XTHEADVECTOR_EXT:
+ return TARGET_XTHEADVECTOR;
Same.
+ "&& register_operand (operands[0], <MODE>mode)
+ && register_operand (operands[3], <MODE>mode)
+ && satisfies_constraint_vu (operands[2])
+ && INTVAL (operands[7]) == riscv_vector::VLMAX"
You can use whole_reg_to_reg_move_p
Btw, I review again : RISC-V: Handle differences between XTheadvector and Vector
 (any_extend:VWEXTI (match_operand:<V_DOUBLE_TRUNC> 3 "register_operand" "W21,W21,W21,W21,W42,W42,W42,W42,W84,W84,W84,W84, vr, vr")) (match_operand:VWEXTI 2 "vector_merge_operand" " vu, vu, 0, 0, vu, vu, 0, 0, vu, vu, 0, 0, vu, 0")))] - "TARGET_VECTOR" + "TARGET_VECTOR && !TARGET_XTHEADVECTOR" "v<sz>ext.vf2\t%0,%3%p1" [(set_attr "type" "vext") (set_attr "mode" "<MODE>") @@ -3713,7 +3744,7 @@ (any_extend:VQEXTI (match_operand:<V_QUAD_TRUNC> 3 "register_operand" "W43,W43,W43,W43,W86,W86,W86,W86, vr, vr")) (match_operand:VQEXTI 2 "vector_merge_operand" " vu, vu, 0, 0, vu, vu, 0, 0, vu, 0")))] - "TARGET_VECTOR" + "TARGET_VECTOR && !TARGET_XTHEADVECTOR" "v<sz>ext.vf4\t%0,%3%p1" [(set_attr "type" "vext") (set_attr "mode" "<MODE>") @@ -3734,7 +3765,7 @@ (any_extend:VOEXTI (match_operand:<V_OCT_TRUNC> 3 "register_operand" "W87,W87,W87,W87, vr, vr")) (match_operand:VOEXTI 2 "vector_merge_operand" " vu, vu, 0, 0, vu, 0")))] - "TARGET_VECTOR" + "TARGET_VECTOR && !TARGET_XTHEADVECTOR" "v<sz>ext.vf8\t%0,%3%p1" [(set_attr "type" "vext") (set_attr "mode" "<MODE>")
Why do you add these !TARGERT_XTHEADVECRTOR ?
juzhe.zhong@rivai.ai
From: Jun Sha (Joshua) <mailto:cooper.joshua@linux.alibaba.com >
Date: 2024-01-11 16:46
To: gcc-patches <mailto:gcc-patches@gcc.gnu.org >
CC: jim.wilson.gcc <mailto:jim.wilson.gcc@gmail.com >; palmer <mailto:palmer@dabbelt.com >; andrew <mailto:andrew@sifive.com >; philipp.tomsich <mailto:philipp.tomsich@vrull.eu >; jeffreyalaw <mailto:jeffreyalaw@gmail.com >; christoph.muellner <mailto:christoph.muellner@vrull.eu >; juzhe.zhong <mailto:juzhe.zhong@rivai.ai >; Jun Sha (Joshua) <mailto:cooper.joshua@linux.alibaba.com >; Jin Ma <mailto:jinma@linux.alibaba.com >; Xianmiao Qu <mailto:cooper.qu@linux.alibaba.com >
Subject: [PATCH v5] RISC-V: Add support for xtheadvector-specific intrinsics.
This patch only involves the generation of xtheadvector
special load/store instructions and vext instructions.
gcc/ChangeLog:
 * config/riscv/riscv-vector-builtins-bases.cc
 (class th_loadstore_width): Define new builtin bases.
 (class th_extract): Define new builtin bases.
 (BASE): Define new builtin bases.
 * config/riscv/riscv-vector-builtins-bases.h:
 Define new builtin class.
 * config/riscv/riscv-vector-builtins-shapes.cc
 (struct th_loadstore_width_def): Define new builtin shapes.
 (struct th_indexed_loadstore_width_def):
 Define new builtin shapes.
 (struct th_extract_def): Define new builtin shapes.
 (SHAPE): Define new builtin shapes.
 * config/riscv/riscv-vector-builtins-shapes.h:
 Define new builtin shapes.
 * config/riscv/riscv-vector-builtins.cc (DEF_RVV_FUNCTION):
 * config/riscv/riscv-vector-builtins.h (enum required_ext):
 (struct function_group_info):
 * config/riscv/t-riscv: Add thead-vector-builtins-functions.def
 * config/riscv/thead-vector.md
 (@pred_mov_width<vlmem_op_attr><mode>): Add new patterns.
 (*pred_mov_width<vlmem_op_attr><mode>): Likewise.
 (@pred_store_width<vlmem_op_attr><mode>): Likewise.
 (@pred_strided_load_width<vlmem_op_attr><mode>): Likewise.
 (@pred_strided_store_width<vlmem_op_attr><mode>): Likewise.
 (@pred_indexed_load_width<vlmem_op_attr><mode>): Likewise.
 (@pred_indexed_<vlmem_order_attr>store_width<vlmem_op_attr><mode>):
 (@pred_th_extract<mode>): Likewise.
 (*pred_th_extract<mode>): Likewise.
 * config/riscv/thead-vector-builtins-functions.def: New file.
gcc/testsuite/ChangeLog:
 * gcc.target/riscv/rvv/xtheadvector/vlb-vsb.c: New test.
 * gcc.target/riscv/rvv/xtheadvector/vlbu-vsb.c: New test.
 * gcc.target/riscv/rvv/xtheadvector/vlh-vsh.c: New test.
 * gcc.target/riscv/rvv/xtheadvector/vlhu-vsh.c: New test.
 * gcc.target/riscv/rvv/xtheadvector/vlw-vsw.c: New test.
 * gcc.target/riscv/rvv/xtheadvector/vlwu-vsw.c: New test.
Co-authored-by: Jin Ma <jinma@linux.alibaba.com>
Co-authored-by: Xianmiao Qu <cooper.qu@linux.alibaba.com>
Co-authored-by: Christoph Müllner <christoph.muellner@vrull.eu>
---
 .../riscv/riscv-vector-builtins-bases.cc | 139 ++++++++++
 .../riscv/riscv-vector-builtins-bases.h | 31 +++
 .../riscv/riscv-vector-builtins-shapes.cc | 160 +++++++++++
 .../riscv/riscv-vector-builtins-shapes.h | 3 +
 gcc/config/riscv/riscv-vector-builtins.cc | 70 +++++
 gcc/config/riscv/riscv-vector-builtins.h | 3 +
 gcc/config/riscv/t-riscv | 1 +
 .../riscv/thead-vector-builtins-functions.def | 39 +++
 gcc/config/riscv/thead-vector.md | 253 ++++++++++++++++++
 .../riscv/rvv/xtheadvector/vlb-vsb.c | 68 +++++
 .../riscv/rvv/xtheadvector/vlbu-vsb.c | 68 +++++
 .../riscv/rvv/xtheadvector/vlh-vsh.c | 68 +++++
 .../riscv/rvv/xtheadvector/vlhu-vsh.c | 68 +++++
 .../riscv/rvv/xtheadvector/vlw-vsw.c | 68 +++++
 .../riscv/rvv/xtheadvector/vlwu-vsw.c | 68 +++++
 15 files changed, 1107 insertions(+)
 create mode 100644 gcc/config/riscv/thead-vector-builtins-functions.def
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlb-vsb.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlbu-vsb.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlh-vsh.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlhu-vsh.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlw-vsw.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlwu-vsw.c
diff mbox series

Patch

diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index 46f1a1da33e..3eba7943757 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -2125,6 +2125,83 @@  public:
 }
 };
+/* Implements
+ * th.vl(b/h/w)[u].v/th.vs(b/h/w)[u].v/th.vls(b/h/w)[u].v/th.vss(b/h/w)[u].v/
+ * th.vlx(b/h/w)[u].v/th.vs[u]x(b/h/w).v
+ * codegen. */
+template<bool STORE_P, lst_type LST_TYPE, int UNSPEC>
+class th_loadstore_width : public function_base
+{
+public:
+ bool apply_tail_policy_p () const override { return !STORE_P; }
+ bool apply_mask_policy_p () const override { return !STORE_P; }
+
+ unsigned int call_properties (const function_instance &) const override
+ {
+ if (STORE_P)
+ return CP_WRITE_MEMORY;
+ else
+ return CP_READ_MEMORY;
+ }
+
+ bool can_be_overloaded_p (enum predication_type_index pred) const override
+ {
+ if (STORE_P || LST_TYPE == LST_INDEXED)
+ return true;
+ return pred != PRED_TYPE_none;
+ }
+
+ rtx expand (function_expander &e) const override
+ {
+ gcc_assert (TARGET_XTHEADVECTOR);
+ if (LST_TYPE == LST_INDEXED)
+ {
+ if (STORE_P)
+ return e.use_exact_insn (
+ code_for_pred_indexed_store_width (UNSPEC, UNSPEC,
+ e.vector_mode ()));
+ else
+ return e.use_exact_insn (
+ code_for_pred_indexed_load_width (UNSPEC, e.vector_mode ()));
+ }
+ else if (LST_TYPE == LST_STRIDED)
+ {
+ if (STORE_P)
+ return e.use_contiguous_store_insn (
+ code_for_pred_strided_store_width (UNSPEC, e.vector_mode ()));
+ else
+ return e.use_contiguous_load_insn (
+ code_for_pred_strided_load_width (UNSPEC, e.vector_mode ()));
+ }
+ else
+ {
+ if (STORE_P)
+ return e.use_contiguous_store_insn (
+ code_for_pred_store_width (UNSPEC, e.vector_mode ()));
+ else
+ return e.use_contiguous_load_insn (
+ code_for_pred_mov_width (UNSPEC, e.vector_mode ()));
+ }
+ }
+};
+
+/* Implements vext.x.v. */
+class th_extract : public function_base
+{
+public:
+ bool apply_vl_p () const override { return false; }
+ bool apply_tail_policy_p () const override { return false; }
+ bool apply_mask_policy_p () const override { return false; }
+ bool use_mask_predication_p () const override { return false; }
+ bool has_merge_operand_p () const override { return false; }
+
+ rtx expand (function_expander &e) const override
+ {
+ gcc_assert (TARGET_XTHEADVECTOR);
+ return e.use_exact_insn (code_for_pred_th_extract (e.vector_mode ()));
+ }
+};
+
 /* Below implements are vector crypto */
 /* Implements vandn.[vv,vx] */
 class vandn : public function_base
@@ -2587,6 +2664,37 @@  static CONSTEXPR const seg_indexed_load<UNSPEC_ORDERED> vloxseg_obj;
 static CONSTEXPR const seg_indexed_store<UNSPEC_UNORDERED> vsuxseg_obj;
 static CONSTEXPR const seg_indexed_store<UNSPEC_ORDERED> vsoxseg_obj;
 static CONSTEXPR const vlsegff vlsegff_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_UNIT_STRIDE, UNSPEC_TH_VLB> vlb_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_UNIT_STRIDE, UNSPEC_TH_VLBU> vlbu_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_UNIT_STRIDE, UNSPEC_TH_VLH> vlh_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_UNIT_STRIDE, UNSPEC_TH_VLHU> vlhu_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_UNIT_STRIDE, UNSPEC_TH_VLW> vlw_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_UNIT_STRIDE, UNSPEC_TH_VLWU> vlwu_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_UNIT_STRIDE, UNSPEC_TH_VLB> vsb_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_UNIT_STRIDE, UNSPEC_TH_VLH> vsh_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_UNIT_STRIDE, UNSPEC_TH_VLW> vsw_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_STRIDED, UNSPEC_TH_VLSB> vlsb_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_STRIDED, UNSPEC_TH_VLSBU> vlsbu_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_STRIDED, UNSPEC_TH_VLSH> vlsh_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_STRIDED, UNSPEC_TH_VLSHU> vlshu_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_STRIDED, UNSPEC_TH_VLSW> vlsw_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_STRIDED, UNSPEC_TH_VLSWU> vlswu_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_STRIDED, UNSPEC_TH_VLSB> vssb_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_STRIDED, UNSPEC_TH_VLSH> vssh_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_STRIDED, UNSPEC_TH_VLSW> vssw_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_INDEXED, UNSPEC_TH_VLXB> vlxb_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_INDEXED, UNSPEC_TH_VLXBU> vlxbu_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_INDEXED, UNSPEC_TH_VLXH> vlxh_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_INDEXED, UNSPEC_TH_VLXHU> vlxhu_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_INDEXED, UNSPEC_TH_VLXW> vlxw_obj;
+static CONSTEXPR const th_loadstore_width<false, LST_INDEXED, UNSPEC_TH_VLXWU> vlxwu_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_INDEXED, UNSPEC_TH_VLXB> vsxb_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_INDEXED, UNSPEC_TH_VLXH> vsxh_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_INDEXED, UNSPEC_TH_VLXW> vsxw_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_INDEXED, UNSPEC_TH_VSUXB> vsuxb_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_INDEXED, UNSPEC_TH_VSUXH> vsuxh_obj;
+static CONSTEXPR const th_loadstore_width<true, LST_INDEXED, UNSPEC_TH_VSUXW> vsuxw_obj;
+static CONSTEXPR const th_extract vext_x_v_obj;
 /* Crypto Vector */
 static CONSTEXPR const vandn vandn_obj;
@@ -2878,6 +2986,37 @@  BASE (vloxseg)
 BASE (vsuxseg)
 BASE (vsoxseg)
 BASE (vlsegff)
+BASE (vlb)
+BASE (vlh)
+BASE (vlw)
+BASE (vlbu)
+BASE (vlhu)
+BASE (vlwu)
+BASE (vsb)
+BASE (vsh)
+BASE (vsw)
+BASE (vlsb)
+BASE (vlsh)
+BASE (vlsw)
+BASE (vlsbu)
+BASE (vlshu)
+BASE (vlswu)
+BASE (vssb)
+BASE (vssh)
+BASE (vssw)
+BASE (vlxb)
+BASE (vlxh)
+BASE (vlxw)
+BASE (vlxbu)
+BASE (vlxhu)
+BASE (vlxwu)
+BASE (vsxb)
+BASE (vsxh)
+BASE (vsxw)
+BASE (vsuxb)
+BASE (vsuxh)
+BASE (vsuxw)
+BASE (vext_x_v)
 /* Crypto vector */
 BASE (vandn)
 BASE (vbrev)
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.h b/gcc/config/riscv/riscv-vector-builtins-bases.h
index 1122e3801a7..565a0311d2b 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.h
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.h
@@ -299,6 +299,37 @@  extern const function_base *const vloxseg;
 extern const function_base *const vsuxseg;
 extern const function_base *const vsoxseg;
 extern const function_base *const vlsegff;
+extern const function_base *const vlb;
+extern const function_base *const vlh;
+extern const function_base *const vlw;
+extern const function_base *const vlbu;
+extern const function_base *const vlhu;
+extern const function_base *const vlwu;
+extern const function_base *const vsb;
+extern const function_base *const vsh;
+extern const function_base *const vsw;
+extern const function_base *const vlsb;
+extern const function_base *const vlsh;
+extern const function_base *const vlsw;
+extern const function_base *const vlsbu;
+extern const function_base *const vlshu;
+extern const function_base *const vlswu;
+extern const function_base *const vssb;
+extern const function_base *const vssh;
+extern const function_base *const vssw;
+extern const function_base *const vlxb;
+extern const function_base *const vlxh;
+extern const function_base *const vlxw;
+extern const function_base *const vlxbu;
+extern const function_base *const vlxhu;
+extern const function_base *const vlxwu;
+extern const function_base *const vsxb;
+extern const function_base *const vsxh;
+extern const function_base *const vsxw;
+extern const function_base *const vsuxb;
+extern const function_base *const vsuxh;
+extern const function_base *const vsuxw;
+extern const function_base *const vext_x_v;
 /* Below function_base are Vectro Crypto*/
 extern const function_base *const vandn;
 extern const function_base *const vbrev;
diff --git a/gcc/config/riscv/riscv-vector-builtins-shapes.cc b/gcc/config/riscv/riscv-vector-builtins-shapes.cc
index 1e4f4d53de6..8e90b17a94b 100644
--- a/gcc/config/riscv/riscv-vector-builtins-shapes.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-shapes.cc
@@ -211,6 +211,146 @@  struct indexed_loadstore_def : public function_shape
 }
 };
+/* Add one function instance for GROUP, using operand suffix at index OI,
+ mode suffix at index PAIR && bi and predication suffix at index pred_idx. */
+static void
+build_th_loadstore (function_builder &b, const function_group_info &group,
+ unsigned int pred_idx, unsigned int vec_type_idx)
+{
+ auto_vec<tree, 5> argument_types;
+ function_instance function_instance (group.base_name, *group.base,
+ *group.shape,
+ group.ops_infos.types[vec_type_idx],
+ group.preds[pred_idx], &group.ops_infos);
+ tree return_type = group.ops_infos.ret.get_tree_type (
+ group.ops_infos.types[vec_type_idx].index);
+ b.allocate_argument_types (function_instance, argument_types);
+ b.apply_predication (function_instance, return_type, argument_types);
+
+ if (TARGET_XTHEADVECTOR && !check_type (return_type, argument_types))
+ return;
+
+ tree type = builtin_types[group.ops_infos.types[vec_type_idx].index].vector;
+ if (strstr (group.base_name, "l")
+ && strstr (group.base_name, "u")
+ && !TYPE_UNSIGNED (TREE_TYPE (type)))
+ return;
+
+ if (strstr (group.base_name, "l")
+ && !strstr (group.base_name, "u")
+ && TYPE_UNSIGNED (TREE_TYPE (type)))
+ return;
+
+ machine_mode mode = TYPE_MODE (type);
+ int sew = GET_MODE_BITSIZE (GET_MODE_INNER (mode));
+ if (strstr (group.base_name, "h") && sew == 8)
+ return;
+
+ if (strstr (group.base_name, "w") && (sew == 8 || sew ==16))
+ return;
+
+ b.add_overloaded_function (function_instance, *group.shape);
+ b.add_unique_function (function_instance, (*group.shape), return_type,
+ argument_types);
+}
+
+/* th_loadstore_width_def class. */
+struct th_loadstore_width_def : public build_base
+{
+ void build (function_builder &b,
+ const function_group_info &group) const override
+ {
+ for (unsigned int pred_idx = 0; group.preds[pred_idx] != NUM_PRED_TYPES;
+ ++pred_idx)
+ {
+ for (unsigned int vec_type_idx = 0;
+ group.ops_infos.types[vec_type_idx].index != NUM_VECTOR_TYPES;
+ ++vec_type_idx)
+ {
+ build_th_loadstore (b, group, pred_idx, vec_type_idx);
+ }
+ }
+ }
+
+ char *get_name (function_builder &b, const function_instance &instance,
+ bool overloaded_p) const override
+ {
+ /* Return nullptr if it can not be overloaded. */
+ if (overloaded_p && !instance.base->can_be_overloaded_p (instance.pred))
+ return nullptr;
+
+ b.append_name ("__riscv_th_");
+ b.append_name (instance.base_name);
+
+ /* vop_v --> vop_v_<type>. */
+ if (!overloaded_p)
+ {
+ /* vop --> vop_v. */
+ b.append_name (operand_suffixes[instance.op_info->op]);
+ /* vop_v --> vop_v_<type>. */
+ b.append_name (type_suffixes[instance.type.index].vector);
+ }
+
+ /* According to rvv-intrinsic-doc, it does not add "_m" suffix
+ for vop_m C++ overloaded API. */
+ if (overloaded_p && instance.pred == PRED_TYPE_m)
+ return b.finish_name ();
+ b.append_name (predication_suffixes[instance.pred]);
+ return b.finish_name ();
+ }
+};
+
+
+/* th_indexed_loadstore_width_def class. */
+struct th_indexed_loadstore_width_def : public function_shape
+{
+ void build (function_builder &b,
+ const function_group_info &group) const override
+ {
+ for (unsigned int pred_idx = 0; group.preds[pred_idx] != NUM_PRED_TYPES;
+ ++pred_idx)
+ {
+ for (unsigned int vec_type_idx = 0;
+ group.ops_infos.types[vec_type_idx].index != NUM_VECTOR_TYPES;
+ ++vec_type_idx)
+ {
+ tree index_type = group.ops_infos.args[1].get_tree_type (
+ group.ops_infos.types[vec_type_idx].index);
+ if (!index_type)
+ continue;
+ build_th_loadstore (b, group, pred_idx, vec_type_idx);
+ }
+ }
+ }
+
+ char *get_name (function_builder &b, const function_instance &instance,
+ bool overloaded_p) const override
+ {
+
+ /* Return nullptr if it can not be overloaded. */
+ if (overloaded_p && !instance.base->can_be_overloaded_p (instance.pred))
+ return nullptr;
+
+ b.append_name ("__riscv_th_");
+ b.append_name (instance.base_name);
+ /* vop_v --> vop_v_<type>. */
+ if (!overloaded_p)
+ {
+ /* vop --> vop_v. */
+ b.append_name (operand_suffixes[instance.op_info->op]);
+ /* vop_v --> vop_v_<type>. */
+ b.append_name (type_suffixes[instance.type.index].vector);
+ }
+
+ /* According to rvv-intrinsic-doc, it does not add "_m" suffix
+ for vop_m C++ overloaded API. */
+ if (overloaded_p && instance.pred == PRED_TYPE_m)
+ return b.finish_name ();
+ b.append_name (predication_suffixes[instance.pred]);
+ return b.finish_name ();
+ }
+};
+
 /* alu_def class. */
 struct alu_def : public build_base
 {
@@ -632,6 +772,23 @@  struct reduc_alu_def : public build_base
 }
 };
+/* th_extract_def class. */
+struct th_extract_def : public build_base
+{
+ char *get_name (function_builder &b, const function_instance &instance,
+ bool overloaded_p) const override
+ {
+ b.append_name ("__riscv_th_");
+ b.append_name (instance.base_name);
+
+ if (overloaded_p)
+ return b.finish_name ();
+ b.append_name (type_suffixes[instance.type.index].vector);
+ b.append_name (type_suffixes[instance.type.index].scalar);
+ return b.finish_name ();
+ }
+};
+
 /* scalar_move_def class. */
 struct scalar_move_def : public build_base
 {
@@ -1094,6 +1251,8 @@  SHAPE(vsetvl, vsetvl)
 SHAPE(vsetvl, vsetvlmax)
 SHAPE(loadstore, loadstore)
 SHAPE(indexed_loadstore, indexed_loadstore)
+SHAPE(th_loadstore_width, th_loadstore_width)
+SHAPE(th_indexed_loadstore_width, th_indexed_loadstore_width)
 SHAPE(alu, alu)
 SHAPE(alu_frm, alu_frm)
 SHAPE(widen_alu, widen_alu)
@@ -1106,6 +1265,7 @@  SHAPE(move, move)
 SHAPE(mask_alu, mask_alu)
 SHAPE(reduc_alu, reduc_alu)
 SHAPE(reduc_alu_frm, reduc_alu_frm)
+SHAPE(th_extract, th_extract)
 SHAPE(scalar_move, scalar_move)
 SHAPE(vundefined, vundefined)
 SHAPE(misc, misc)
diff --git a/gcc/config/riscv/riscv-vector-builtins-shapes.h b/gcc/config/riscv/riscv-vector-builtins-shapes.h
index ac2a28ce017..a7624d0fabd 100644
--- a/gcc/config/riscv/riscv-vector-builtins-shapes.h
+++ b/gcc/config/riscv/riscv-vector-builtins-shapes.h
@@ -28,6 +28,8 @@  extern const function_shape *const vsetvl;
 extern const function_shape *const vsetvlmax;
 extern const function_shape *const loadstore;
 extern const function_shape *const indexed_loadstore;
+extern const function_shape *const th_loadstore_width;
+extern const function_shape *const th_indexed_loadstore_width;
 extern const function_shape *const alu;
 extern const function_shape *const alu_frm;
 extern const function_shape *const widen_alu;
@@ -41,6 +43,7 @@  extern const function_shape *const mask_alu;
 extern const function_shape *const reduc_alu;
 extern const function_shape *const reduc_alu_frm;
 extern const function_shape *const scalar_move;
+extern const function_shape *const th_extract;
 extern const function_shape *const vundefined;
 extern const function_shape *const misc;
 extern const function_shape *const vset;
diff --git a/gcc/config/riscv/riscv-vector-builtins.cc b/gcc/config/riscv/riscv-vector-builtins.cc
index 25e0b6e56de..44b9fec1898 100644
--- a/gcc/config/riscv/riscv-vector-builtins.cc
+++ b/gcc/config/riscv/riscv-vector-builtins.cc
@@ -934,6 +934,32 @@  static CONSTEXPR const rvv_arg_type_info ext_vcreate_args[]
 = {rvv_arg_type_info (RVV_BASE_vector),
 rvv_arg_type_info_end};
+/* A list of args for vector_type func (const scalar_type *, size_t)
+ * function. */
+static CONSTEXPR const rvv_arg_type_info scalar_const_ptr_size_args[]
+ = {rvv_arg_type_info (RVV_BASE_scalar_const_ptr),
+ rvv_arg_type_info (RVV_BASE_size), rvv_arg_type_info_end};
+
+/* A list of args for vector_type func (const scalar_type *, eew8_index_type)
+ * function. */
+static CONSTEXPR const rvv_arg_type_info scalar_const_ptr_index_args[]
+ = {rvv_arg_type_info (RVV_BASE_scalar_const_ptr),
+ rvv_arg_type_info (RVV_BASE_unsigned_vector), rvv_arg_type_info_end};
+
+/* A list of args for void func (scalar_type *, eew8_index_type, vector_type)
+ * function. */
+static CONSTEXPR const rvv_arg_type_info scalar_ptr_index_args[]
+ = {rvv_arg_type_info (RVV_BASE_scalar_ptr),
+ rvv_arg_type_info (RVV_BASE_unsigned_vector),
+ rvv_arg_type_info (RVV_BASE_vector), rvv_arg_type_info_end};
+
+/* A list of args for void func (scalar_type *, size_t, vector_type)
+ * function. */
+static CONSTEXPR const rvv_arg_type_info scalar_ptr_size_args[]
+ = {rvv_arg_type_info (RVV_BASE_scalar_ptr),
+ rvv_arg_type_info (RVV_BASE_size), rvv_arg_type_info (RVV_BASE_vector),
+ rvv_arg_type_info_end};
+
 /* A list of none preds that will be registered for intrinsic functions. */
 static CONSTEXPR const predication_type_index none_preds[]
 = {PRED_TYPE_none, NUM_PRED_TYPES};
@@ -1455,6 +1481,14 @@  static CONSTEXPR const rvv_op_info iu_shift_vvv_ops
 rvv_arg_type_info (RVV_BASE_vector), /* Return type */
 shift_vv_args /* Args */};
+/* A static operand information for scalar_type func (vector_type, size_t)
+ * function registration. */
+static CONSTEXPR const rvv_op_info iu_x_s_u_ops
+ = {iu_ops, /* Types */
+ OP_TYPE_vx, /* Suffix */
+ rvv_arg_type_info (RVV_BASE_scalar), /* Return type */
+ v_size_args /* Args */};
+
 /* A static operand information for vector_type func (vector_type, size_t)
 * function registration. */
 static CONSTEXPR const rvv_op_info iu_shift_vvx_ops
@@ -2638,6 +2672,38 @@  static CONSTEXPR const rvv_op_info all_v_vcreate_lmul4_x2_ops
 rvv_arg_type_info (RVV_BASE_vlmul_ext_x2), /* Return type */
 ext_vcreate_args /* Args */};
+/* A static operand information for vector_type func (const scalar_type *,
+ * size_t) function registration. */
+static CONSTEXPR const rvv_op_info all_v_scalar_const_ptr_size_ops
+ = {all_ops, /* Types */
+ OP_TYPE_v, /* Suffix */
+ rvv_arg_type_info (RVV_BASE_vector), /* Return type */
+ scalar_const_ptr_size_args /* Args */};
+
+/* A static operand information for void func (scalar_type *, size_t,
+ * vector_type) function registration. */
+static CONSTEXPR const rvv_op_info all_v_scalar_ptr_size_ops
+ = {all_ops, /* Types */
+ OP_TYPE_v, /* Suffix */
+ rvv_arg_type_info (RVV_BASE_void), /* Return type */
+ scalar_ptr_size_args /* Args */};
+
+/* A static operand information for vector_type func (const scalar_type *,
+ * index_type) function registration. */
+static CONSTEXPR const rvv_op_info all_v_scalar_const_ptr_index_ops
+ = {all_ops, /* Types */
+ OP_TYPE_v, /* Suffix */
+ rvv_arg_type_info (RVV_BASE_vector), /* Return type */
+ scalar_const_ptr_index_args /* Args */};
+
+/* A static operand information for void func (scalar_type *, index_type,
+ * vector_type) function registration. */
+static CONSTEXPR const rvv_op_info all_v_scalar_ptr_index_ops
+ = {all_ops, /* Types */
+ OP_TYPE_v, /* Suffix */
+ rvv_arg_type_info (RVV_BASE_void), /* Return type */
+ scalar_ptr_index_args /* Args */};
+
 /* A static operand information for vector_type func (vector_type).
 Some ins just supports SEW=32, such as crypto vectol Zvkg extension.
 * function registration. */
@@ -2816,6 +2882,10 @@  static function_group_info function_groups[] = {
 #define DEF_RVV_FUNCTION(NAME, SHAPE, PREDS, OPS_INFO) \
 {#NAME, &bases::NAME, &shapes::SHAPE, PREDS, OPS_INFO, REQUIRED_EXTENSIONS},
 #include "riscv-vector-builtins-functions.def"
+#undef DEF_RVV_FUNCTION
+#define DEF_RVV_FUNCTION(NAME, SHAPE, PREDS, OPS_INFO) \
+ {#NAME, &bases::NAME, &shapes::SHAPE, PREDS, OPS_INFO, REQUIRED_EXTENSIONS},
+#include "thead-vector-builtins-functions.def"
 };
 /* The RVV types, with their built-in
diff --git a/gcc/config/riscv/riscv-vector-builtins.h b/gcc/config/riscv/riscv-vector-builtins.h
index 54c8824ff92..a8ee39a3cb2 100644
--- a/gcc/config/riscv/riscv-vector-builtins.h
+++ b/gcc/config/riscv/riscv-vector-builtins.h
@@ -114,6 +114,7 @@  static const unsigned int CP_WRITE_CSR = 1U << 5;
 enum required_ext
 {
 VECTOR_EXT, /* Vector extension */
+ XTHEADVECTOR_EXT, /* XTheadVector extension */
 ZVBB_EXT, /* Cryto vector Zvbb sub-ext */
 ZVBB_OR_ZVKB_EXT, /* Cryto vector Zvbb or zvkb sub-ext */
 ZVBC_EXT, /* Crypto vector Zvbc sub-ext */
@@ -234,6 +235,8 @@  struct function_group_info
 {
 case VECTOR_EXT:
 return TARGET_VECTOR;
+ case XTHEADVECTOR_EXT:
+ return TARGET_XTHEADVECTOR;
 case ZVBB_EXT:
 return TARGET_ZVBB;
 case ZVBB_OR_ZVKB_EXT:
diff --git a/gcc/config/riscv/t-riscv b/gcc/config/riscv/t-riscv
index 32de6b851c1..38494320d8b 100644
--- a/gcc/config/riscv/t-riscv
+++ b/gcc/config/riscv/t-riscv
@@ -1,6 +1,7 @@ 
 RISCV_BUILTINS_H = $(srcdir)/config/riscv/riscv-vector-builtins.h \
 $(srcdir)/config/riscv/riscv-vector-builtins.def \
 $(srcdir)/config/riscv/riscv-vector-builtins-functions.def \
+ $(srcdir)/config/riscv/thead-vector-builtins-functions.def \
 riscv-vector-type-indexer.gen.def
 riscv-builtins.o: $(srcdir)/config/riscv/riscv-builtins.cc $(CONFIG_H) \
diff --git a/gcc/config/riscv/thead-vector-builtins-functions.def b/gcc/config/riscv/thead-vector-builtins-functions.def
new file mode 100644
index 00000000000..fd3ba29bae9
--- /dev/null
+++ b/gcc/config/riscv/thead-vector-builtins-functions.def
@@ -0,0 +1,39 @@ 
+#ifndef DEF_RVV_FUNCTION
+#define DEF_RVV_FUNCTION(NAME, SHAPE, PREDS, OPS_INFO)
+#endif
+
+#define REQUIRED_EXTENSIONS XTHEADVECTOR_EXT
+DEF_RVV_FUNCTION (vlb, th_loadstore_width, full_preds, all_v_scalar_const_ptr_ops)
+DEF_RVV_FUNCTION (vlh, th_loadstore_width, full_preds, all_v_scalar_const_ptr_ops)
+DEF_RVV_FUNCTION (vlw, th_loadstore_width, full_preds, all_v_scalar_const_ptr_ops)
+DEF_RVV_FUNCTION (vlbu, th_loadstore_width, full_preds, all_v_scalar_const_ptr_ops)
+DEF_RVV_FUNCTION (vlhu, th_loadstore_width, full_preds, all_v_scalar_const_ptr_ops)
+DEF_RVV_FUNCTION (vlwu, th_loadstore_width, full_preds, all_v_scalar_const_ptr_ops)
+DEF_RVV_FUNCTION (vsb, th_loadstore_width, none_m_preds, all_v_scalar_ptr_ops)
+DEF_RVV_FUNCTION (vsh, th_loadstore_width, none_m_preds, all_v_scalar_ptr_ops)
+DEF_RVV_FUNCTION (vsw, th_loadstore_width, none_m_preds, all_v_scalar_ptr_ops)
+DEF_RVV_FUNCTION (vlsb, th_loadstore_width, full_preds, all_v_scalar_const_ptr_size_ops)
+DEF_RVV_FUNCTION (vlsh, th_loadstore_width, full_preds, all_v_scalar_const_ptr_size_ops)
+DEF_RVV_FUNCTION (vlsw, th_loadstore_width, full_preds, all_v_scalar_const_ptr_size_ops)
+DEF_RVV_FUNCTION (vlsbu, th_loadstore_width, full_preds, all_v_scalar_const_ptr_size_ops)
+DEF_RVV_FUNCTION (vlshu, th_loadstore_width, full_preds, all_v_scalar_const_ptr_size_ops)
+DEF_RVV_FUNCTION (vlswu, th_loadstore_width, full_preds, all_v_scalar_const_ptr_size_ops)
+DEF_RVV_FUNCTION (vssb, th_loadstore_width, none_m_preds, all_v_scalar_ptr_size_ops)
+DEF_RVV_FUNCTION (vssh, th_loadstore_width, none_m_preds, all_v_scalar_ptr_size_ops)
+DEF_RVV_FUNCTION (vssw, th_loadstore_width, none_m_preds, all_v_scalar_ptr_size_ops)
+DEF_RVV_FUNCTION (vlxb, th_indexed_loadstore_width, full_preds, all_v_scalar_const_ptr_index_ops)
+DEF_RVV_FUNCTION (vlxh, th_indexed_loadstore_width, full_preds, all_v_scalar_const_ptr_index_ops)
+DEF_RVV_FUNCTION (vlxw, th_indexed_loadstore_width, full_preds, all_v_scalar_const_ptr_index_ops)
+DEF_RVV_FUNCTION (vlxbu, th_indexed_loadstore_width, full_preds, all_v_scalar_const_ptr_index_ops)
+DEF_RVV_FUNCTION (vlxhu, th_indexed_loadstore_width, full_preds, all_v_scalar_const_ptr_index_ops)
+DEF_RVV_FUNCTION (vlxwu, th_indexed_loadstore_width, full_preds, all_v_scalar_const_ptr_index_ops)
+DEF_RVV_FUNCTION (vsxb, th_indexed_loadstore_width, none_m_preds, all_v_scalar_ptr_index_ops)
+DEF_RVV_FUNCTION (vsxh, th_indexed_loadstore_width, none_m_preds, all_v_scalar_ptr_index_ops)
+DEF_RVV_FUNCTION (vsxw, th_indexed_loadstore_width, none_m_preds, all_v_scalar_ptr_index_ops)
+DEF_RVV_FUNCTION (vsuxb, th_indexed_loadstore_width, none_m_preds, all_v_scalar_ptr_index_ops)
+DEF_RVV_FUNCTION (vsuxh, th_indexed_loadstore_width, none_m_preds, all_v_scalar_ptr_index_ops)
+DEF_RVV_FUNCTION (vsuxw, th_indexed_loadstore_width, none_m_preds, all_v_scalar_ptr_index_ops)
+DEF_RVV_FUNCTION (vext_x_v, th_extract, none_preds, iu_x_s_u_ops)
+#undef REQUIRED_EXTENSIONS
+
+#undef DEF_RVV_FUNCTION
diff --git a/gcc/config/riscv/thead-vector.md b/gcc/config/riscv/thead-vector.md
index 696b815252d..0f3700d9269 100644
--- a/gcc/config/riscv/thead-vector.md
+++ b/gcc/config/riscv/thead-vector.md
@@ -1,7 +1,95 @@ 
 (define_c_enum "unspec" [
+ UNSPEC_TH_VLB
+ UNSPEC_TH_VLBU
+ UNSPEC_TH_VLH
+ UNSPEC_TH_VLHU
+ UNSPEC_TH_VLW
+ UNSPEC_TH_VLWU
+
+ UNSPEC_TH_VLSB
+ UNSPEC_TH_VLSBU
+ UNSPEC_TH_VLSH
+ UNSPEC_TH_VLSHU
+ UNSPEC_TH_VLSW
+ UNSPEC_TH_VLSWU
+
+ UNSPEC_TH_VLXB
+ UNSPEC_TH_VLXBU
+ UNSPEC_TH_VLXH
+ UNSPEC_TH_VLXHU
+ UNSPEC_TH_VLXW
+ UNSPEC_TH_VLXWU
+
+ UNSPEC_TH_VSUXB
+ UNSPEC_TH_VSUXH
+ UNSPEC_TH_VSUXW
+
 UNSPEC_TH_VWLDST
 ])
+(define_int_iterator UNSPEC_TH_VLMEM_OP [
+ UNSPEC_TH_VLB UNSPEC_TH_VLBU
+ UNSPEC_TH_VLH UNSPEC_TH_VLHU
+ UNSPEC_TH_VLW UNSPEC_TH_VLWU
+])
+
+(define_int_iterator UNSPEC_TH_VLSMEM_OP [
+ UNSPEC_TH_VLSB UNSPEC_TH_VLSBU
+ UNSPEC_TH_VLSH UNSPEC_TH_VLSHU
+ UNSPEC_TH_VLSW UNSPEC_TH_VLSWU
+])
+
+(define_int_iterator UNSPEC_TH_VLXMEM_OP [
+ UNSPEC_TH_VLXB UNSPEC_TH_VLXBU
+ UNSPEC_TH_VLXH UNSPEC_TH_VLXHU
+ UNSPEC_TH_VLXW UNSPEC_TH_VLXWU
+])
+
+(define_int_attr vlmem_op_attr [
+ (UNSPEC_TH_VLB "b") (UNSPEC_TH_VLBU "bu")
+ (UNSPEC_TH_VLH "h") (UNSPEC_TH_VLHU "hu")
+ (UNSPEC_TH_VLW "w") (UNSPEC_TH_VLWU "wu")
+ (UNSPEC_TH_VLSB "b") (UNSPEC_TH_VLSBU "bu")
+ (UNSPEC_TH_VLSH "h") (UNSPEC_TH_VLSHU "hu")
+ (UNSPEC_TH_VLSW "w") (UNSPEC_TH_VLSWU "wu")
+ (UNSPEC_TH_VLXB "b") (UNSPEC_TH_VLXBU "bu")
+ (UNSPEC_TH_VLXH "h") (UNSPEC_TH_VLXHU "hu")
+ (UNSPEC_TH_VLXW "w") (UNSPEC_TH_VLXWU "wu")
+ (UNSPEC_TH_VSUXB "b")
+ (UNSPEC_TH_VSUXH "h")
+ (UNSPEC_TH_VSUXW "w")
+])
+
+(define_int_attr vlmem_order_attr [
+ (UNSPEC_TH_VLXB "")
+ (UNSPEC_TH_VLXH "")
+ (UNSPEC_TH_VLXW "")
+ (UNSPEC_TH_VSUXB "u")
+ (UNSPEC_TH_VSUXH "u")
+ (UNSPEC_TH_VSUXW "u")
+])
+
+(define_int_iterator UNSPEC_TH_VSMEM_OP [
+ UNSPEC_TH_VLB
+ UNSPEC_TH_VLH
+ UNSPEC_TH_VLW
+])
+
+(define_int_iterator UNSPEC_TH_VSSMEM_OP [
+ UNSPEC_TH_VLSB
+ UNSPEC_TH_VLSH
+ UNSPEC_TH_VLSW
+])
+
+(define_int_iterator UNSPEC_TH_VSXMEM_OP [
+ UNSPEC_TH_VLXB
+ UNSPEC_TH_VLXH
+ UNSPEC_TH_VLXW
+ UNSPEC_TH_VSUXB
+ UNSPEC_TH_VSUXH
+ UNSPEC_TH_VSUXW
+])
+
 (define_mode_iterator V_VLS_VT [V VLS VT])
 (define_mode_iterator V_VB_VLS_VT [V VB VLS VT])
@@ -100,3 +188,168 @@ 
 }
 [(set_attr "type" "vldm,vstm,vmalu,vmalu,vmalu")
 (set_attr "mode" "<MODE>")])
+
+(define_expand "@pred_mov_width<vlmem_op_attr><mode>"
+ [(set (match_operand:V_VLS 0 "nonimmediate_operand")
+ (if_then_else:V_VLS
+ (unspec:<VM>
+ [(match_operand:<VM> 1 "vector_mask_operand")
+ (match_operand 4 "vector_length_operand")
+ (match_operand 5 "const_int_operand")
+ (match_operand 6 "const_int_operand")
+ (match_operand 7 "const_int_operand")
+ (reg:SI VL_REGNUM)
+ (reg:SI VTYPE_REGNUM)] UNSPEC_TH_VLMEM_OP)
+ (match_operand:V_VLS 3 "vector_move_operand")
+ (match_operand:V_VLS 2 "vector_merge_operand")))]
+ "TARGET_XTHEADVECTOR"
+ {})
+
+(define_insn_and_split "*pred_mov_width<vlmem_op_attr><mode>"
+ [(set (match_operand:V_VLS 0 "nonimmediate_operand" "=vr, vr, vd, m, vr, vr")
+ (if_then_else:V_VLS
+ (unspec:<VM>
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1, Wc1, vm, vmWc1, Wc1, Wc1")
+ (match_operand 4 "vector_length_operand" " rK, rK, rK, rK, rK, rK")
+ (match_operand 5 "const_int_operand" " i, i, i, i, i, i")
+ (match_operand 6 "const_int_operand" " i, i, i, i, i, i")
+ (match_operand 7 "const_int_operand" " i, i, i, i, i, i")
+ (reg:SI VL_REGNUM)
+ (reg:SI VTYPE_REGNUM)] UNSPEC_TH_VLMEM_OP)
+ (match_operand:V_VLS 3 "reg_or_mem_operand" " m, m, m, vr, vr, vr")
+ (match_operand:V_VLS 2 "vector_merge_operand" " 0, vu, vu, vu, vu, 0")))]
+ "(TARGET_XTHEADVECTOR
+ && (register_operand (operands[0], <MODE>mode)
+ || register_operand (operands[3], <MODE>mode)))"
+ "@
+ vl<vlmem_op_attr>.v\t%0,%3%p1
+ vl<vlmem_op_attr>.v\t%0,%3
+ vl<vlmem_op_attr>.v\t%0,%3,%1.t
+ vs<vlmem_op_attr>.v\t%3,%0%p1
+ vmv.v.v\t%0,%3
+ vmv.v.v\t%0,%3"
+ "&& register_operand (operands[0], <MODE>mode)
+ && register_operand (operands[3], <MODE>mode)
+ && satisfies_constraint_vu (operands[2])
+ && INTVAL (operands[7]) == riscv_vector::VLMAX"
+ [(set (match_dup 0) (match_dup 3))]
+ ""
+ [(set_attr "type" "vlde,vlde,vlde,vste,vimov,vimov")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "@pred_store_width<vlmem_op_attr><mode>"
+ [(set (match_operand:VI 0 "memory_operand" "+m")
+ (if_then_else:VI
+ (unspec:<VM>
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1")
+ (match_operand 3 "vector_length_operand" " rK")
+ (match_operand 4 "const_int_operand" " i")
+ (reg:SI VL_REGNUM)
+ (reg:SI VTYPE_REGNUM)] UNSPEC_TH_VSMEM_OP)
+ (match_operand:VI 2 "register_operand" " vr")
+ (match_dup 0)))]
+ "TARGET_XTHEADVECTOR"
+ "vs<vlmem_op_attr>.v\t%2,%0%p1"
+ [(set_attr "type" "vste")
+ (set_attr "mode" "<MODE>")
+ (set (attr "avl_type_idx") (const_int 4))
+ (set_attr "vl_op_idx" "3")])
+
+(define_insn "@pred_strided_load_width<vlmem_op_attr><mode>"
+ [(set (match_operand:VI 0 "register_operand" "=vr, vr, vd")
+ (if_then_else:VI
+ (unspec:<VM>
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1, Wc1, vm")
+ (match_operand 5 "vector_length_operand" " rK, rK, rK")
+ (match_operand 6 "const_int_operand" " i, i, i")
+ (match_operand 7 "const_int_operand" " i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i")
+ (reg:SI VL_REGNUM)
+ (reg:SI VTYPE_REGNUM)] UNSPEC_TH_VLSMEM_OP)
+ (unspec:VI
+ [(match_operand:VI 3 "memory_operand" " m, m, m")
+ (match_operand 4 "pmode_reg_or_0_operand" " rJ, rJ, rJ")] UNSPEC_TH_VLSMEM_OP)
+ (match_operand:VI 2 "vector_merge_operand" " 0, vu, vu")))]
+ "TARGET_XTHEADVECTOR"
+ "vls<vlmem_op_attr>.v\t%0,%3,%z4%p1"
+ [(set_attr "type" "vlds")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "@pred_strided_store_width<vlmem_op_attr><mode>"
+ [(set (match_operand:VI 0 "memory_operand" "+m")
+ (if_then_else:VI
+ (unspec:<VM>
+ [(match_operand:<VM> 1 "vector_mask_operand" "vmWc1")
+ (match_operand 4 "vector_length_operand" " rK")
+ (match_operand 5 "const_int_operand" " i")
+ (reg:SI VL_REGNUM)
+ (reg:SI VTYPE_REGNUM)] UNSPEC_TH_VSSMEM_OP)
+ (unspec:VI
+ [(match_operand 2 "pmode_reg_or_0_operand" " rJ")
+ (match_operand:VI 3 "register_operand" " vr")] UNSPEC_TH_VSSMEM_OP)
+ (match_dup 0)))]
+ "TARGET_XTHEADVECTOR"
+ "vss<vlmem_op_attr>.v\t%3,%0,%z2%p1"
+ [(set_attr "type" "vsts")
+ (set_attr "mode" "<MODE>")
+ (set (attr "avl_type_idx") (const_int 5))])
+
+(define_insn "@pred_indexed_load_width<vlmem_op_attr><mode>"
+ [(set (match_operand:VI 0 "register_operand" "=vd, vr,vd, vr")
+ (if_then_else:VI
+ (unspec:<VM>
+ [(match_operand:<VM> 1 "vector_mask_operand" " vm,Wc1,vm,Wc1")
+ (match_operand 5 "vector_length_operand" " rK, rK,rK, rK")
+ (match_operand 6 "const_int_operand" " i, i, i, i")
+ (match_operand 7 "const_int_operand" " i, i, i, i")
+ (match_operand 8 "const_int_operand" " i, i, i, i")
+ (reg:SI VL_REGNUM)
+ (reg:SI VTYPE_REGNUM)] UNSPEC_TH_VLXMEM_OP)
+ (unspec:VI
+ [(match_operand 3 "pmode_reg_or_0_operand" " rJ, rJ,rJ, rJ")
+ (mem:BLK (scratch))
+ (match_operand:VI 4 "register_operand" " vr, vr,vr, vr")] UNSPEC_TH_VLXMEM_OP)
+ (match_operand:VI 2 "vector_merge_operand" " vu, vu, 0, 0")))]
+ "TARGET_XTHEADVECTOR"
+ "vlx<vlmem_op_attr>.v\t%0,(%z3),%4%p1"
+ [(set_attr "type" "vldux")
+ (set_attr "mode" "<MODE>")])
+
+(define_insn "@pred_indexed_<vlmem_order_attr>store_width<vlmem_op_attr><mode>"
+ [(set (mem:BLK (scratch))
+ (unspec:BLK
+ [(unspec:<VM>
+ [(match_operand:<VM> 0 "vector_mask_operand" "vmWc1")
+ (match_operand 4 "vector_length_operand" " rK")
+ (match_operand 5 "const_int_operand" " i")
+ (reg:SI VL_REGNUM)
+ (reg:SI VTYPE_REGNUM)] UNSPEC_TH_VSXMEM_OP)
+ (match_operand 1 "pmode_reg_or_0_operand" " rJ")
+ (match_operand:VI 2 "register_operand" " vr")
+ (match_operand:VI 3 "register_operand" " vr")] UNSPEC_TH_VSXMEM_OP))]
+ "TARGET_XTHEADVECTOR"
+ "vs<vlmem_order_attr>x<vlmem_op_attr>.v\t%3,(%z1),%2%p0"
+ [(set_attr "type" "vstux")
+ (set_attr "mode" "<MODE>")])
+
+(define_expand "@pred_th_extract<mode>"
+ [(set (match_operand:<VEL> 0 "register_operand")
+ (unspec:<VEL>
+ [(vec_select:<VEL>
+ (match_operand:V_VLSI 1 "register_operand")
+ (parallel [(match_operand:DI 2 "register_operand" "r")]))
+ (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE))]
+ "TARGET_XTHEADVECTOR"
+{})
+
+(define_insn "*pred_th_extract<mode>"
+ [(set (match_operand:<VEL> 0 "register_operand" "=r")
+ (unspec:<VEL>
+ [(vec_select:<VEL>
+ (match_operand:V_VLSI 1 "register_operand" "vr")
+ (parallel [(match_operand:DI 2 "register_operand" "r")]))
+ (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE))]
+ "TARGET_XTHEADVECTOR"
+ "vext.x.v\t%0,%1,%2"
+ [(set_attr "type" "vimovvx")
+ (set_attr "mode" "<MODE>")])
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlb-vsb.c b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlb-vsb.c
new file mode 100644
index 00000000000..3c12c124597
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlb-vsb.c
@@ -0,0 +1,68 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcxtheadvector -mabi=ilp32d -O3" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+#include "riscv_th_vector.h"
+
+/*
+** f1:
+** th.vsetivli\tzero,4,e32,m1,tu,ma
+** th.vlb\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlb\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vadd\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+
+** th.vadd\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+
+** th.vsb\.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f1 (void * in, void *out)
+{
+ vint32m1_t v = __riscv_th_vlb_v_i32m1 (in, 4);
+ vint32m1_t v2 = __riscv_th_vlb_v_i32m1_tu (v, in, 4);
+ vint32m1_t v3 = __riscv_vadd_vv_i32m1 (v2, v2, 4);
+ vint32m1_t v4 = __riscv_vadd_vv_i32m1_tu (v3, v2, v2, 4);
+ __riscv_th_vsb_v_i32m1 (out, v4, 4);
+}
+
+/*
+** f2:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,ta,ma
+** th.vlb.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+
+** th.vadd\.vv\tv[1-9][0-9]?,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t
+** th.vsb.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f2 (void * in, void *out)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vint32m1_t v = __riscv_th_vlb_v_i32m1 (in, 4);
+ vint32m1_t v2 = __riscv_th_vlb_v_i32m1_m (mask, in, 4);
+ vint32m1_t v3 = __riscv_vadd_vv_i32m1 (v2, v2, 4);
+ vint32m1_t v4 = __riscv_vadd_vv_i32m1_m (mask, v3, v3, 4);
+ __riscv_th_vsb_v_i32m1 (out, v4, 4);
+}
+
+/*
+** f3:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,tu,mu
+** th.vlb\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlb.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vv\tv[0-9]+,\s*v[0-9]+,\s*v[0-9]+
+** th.vadd\.vv\tv[1-9][0-9]?,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t
+** th.vsb.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f3 (void * in, void *out)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vint32m1_t v = __riscv_th_vlb_v_i32m1 (in, 4);
+ vint32m1_t v2 = __riscv_th_vlb_v_i32m1_tumu (mask, v, in, 4);
+ vint32m1_t v3 = __riscv_vadd_vv_i32m1 (v2, v2, 4);
+ vint32m1_t v4 = __riscv_vadd_vv_i32m1_tumu (mask, v3, v2, v2, 4);
+ __riscv_th_vsb_v_i32m1 (out, v4, 4);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlbu-vsb.c b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlbu-vsb.c
new file mode 100644
index 00000000000..30bef369375
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlbu-vsb.c
@@ -0,0 +1,68 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcxtheadvector -mabi=ilp32d -O3" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+#include "riscv_th_vector.h"
+
+/*
+** f1:
+** th.vsetivli\tzero,4,e32,m1,tu,ma
+** th.vlbu\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlbu\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vsb\.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f1 (void * in, void *out, uint32_t x)
+{
+ vuint32m1_t v = __riscv_th_vlbu_v_u32m1 (in, 4);
+ vuint32m1_t v2 = __riscv_th_vlbu_v_u32m1_tu (v, in, 4);
+ vuint32m1_t v3 = __riscv_vadd_vx_u32m1 (v2, -16, 4);
+ vuint32m1_t v4 = __riscv_vadd_vx_u32m1_tu (v3, v2, -16, 4);
+ __riscv_th_vsb_v_u32m1 (out, v4, 4);
+}
+
+/*
+** f2:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,ta,ma
+** th.vlbu.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[1-9][0-9]?,\s*v[0-9]+,\s*-16,\s*v0.t
+** th.vsb.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f2 (void * in, void *out, uint32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vuint32m1_t v = __riscv_th_vlbu_v_u32m1 (in, 4);
+ vuint32m1_t v2 = __riscv_th_vlbu_v_u32m1_m (mask, in, 4);
+ vuint32m1_t v3 = __riscv_vadd_vx_u32m1 (v2, -16, 4);
+ vuint32m1_t v4 = __riscv_vadd_vx_u32m1_m (mask, v3, -16, 4);
+ __riscv_th_vsb_v_u32m1 (out, v4, 4);
+}
+
+/*
+** f3:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,tu,mu
+** th.vlbu\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlbu.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[1-9][0-9]?,\s*v[0-9]+,\s*-16,\s*v0.t
+** th.vsb.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f3 (void * in, void *out, uint32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vuint32m1_t v = __riscv_th_vlbu_v_u32m1 (in, 4);
+ vuint32m1_t v2 = __riscv_th_vlbu_v_u32m1_tumu (mask, v, in, 4);
+ vuint32m1_t v3 = __riscv_vadd_vx_u32m1 (v2, -16, 4);
+ vuint32m1_t v4 = __riscv_vadd_vx_u32m1_tumu (mask, v3, v2, -16, 4);
+ __riscv_th_vsb_v_u32m1 (out, v4, 4);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlh-vsh.c b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlh-vsh.c
new file mode 100644
index 00000000000..3c8b5ccc16b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlh-vsh.c
@@ -0,0 +1,68 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcxtheadvector -mabi=ilp32d -O3" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+#include "riscv_th_vector.h"
+
+/*
+** f1:
+** th.vsetivli\tzero,4,e32,m1,tu,ma
+** th.vlh\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlh\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vsh\.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f1 (void * in, void *out, int32_t x)
+{
+ vint32m1_t v = __riscv_th_vlh_v_i32m1 (in, 4);
+ vint32m1_t v2 = __riscv_th_vlh_v_i32m1_tu (v, in, 4);
+ vint32m1_t v3 = __riscv_vadd_vx_i32m1 (v2, -16, 4);
+ vint32m1_t v4 = __riscv_vadd_vx_i32m1_tu (v3, v2, -16, 4);
+ __riscv_th_vsh_v_i32m1 (out, v4, 4);
+}
+
+/*
+** f2:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,ta,ma
+** th.vlh.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[1-9][0-9]?,\s*v[0-9]+,\s*-16,\s*v0.t
+** th.vsh.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f2 (void * in, void *out, int32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vint32m1_t v = __riscv_th_vlh_v_i32m1 (in, 4);
+ vint32m1_t v2 = __riscv_th_vlh_v_i32m1_m (mask, in, 4);
+ vint32m1_t v3 = __riscv_vadd_vx_i32m1 (v2, -16, 4);
+ vint32m1_t v4 = __riscv_vadd_vx_i32m1_m (mask, v3, -16, 4);
+ __riscv_th_vsh_v_i32m1 (out, v4, 4);
+}
+
+/*
+** f3:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,tu,mu
+** th.vlh\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlh.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[1-9][0-9]?,\s*v[0-9]+,\s*-16,\s*v0.t
+** th.vsh.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f3 (void * in, void *out, int32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vint32m1_t v = __riscv_th_vlh_v_i32m1 (in, 4);
+ vint32m1_t v2 = __riscv_th_vlh_v_i32m1_tumu (mask, v, in, 4);
+ vint32m1_t v3 = __riscv_vadd_vx_i32m1 (v2, -16, 4);
+ vint32m1_t v4 = __riscv_vadd_vx_i32m1_tumu (mask, v3, v2, -16, 4);
+ __riscv_th_vsh_v_i32m1 (out, v4, 4);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlhu-vsh.c b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlhu-vsh.c
new file mode 100644
index 00000000000..b7c00404f18
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlhu-vsh.c
@@ -0,0 +1,68 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcxtheadvector -mabi=ilp32d -O3" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+#include "riscv_th_vector.h"
+
+/*
+** f1:
+** th.vsetivli\tzero,4,e32,m1,tu,ma
+** th.vlhu\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlhu\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vsh\.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f1 (void * in, void *out, uint32_t x)
+{
+ vuint32m1_t v = __riscv_th_vlhu_v_u32m1 (in, 4);
+ vuint32m1_t v2 = __riscv_th_vlhu_v_u32m1_tu (v, in, 4);
+ vuint32m1_t v3 = __riscv_vadd_vx_u32m1 (v2, -16, 4);
+ vuint32m1_t v4 = __riscv_vadd_vx_u32m1_tu (v3, v2, -16, 4);
+ __riscv_th_vsh_v_u32m1 (out, v4, 4);
+}
+
+/*
+** f2:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,ta,ma
+** th.vlhu.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[1-9][0-9]?,\s*v[0-9]+,\s*-16,\s*v0.t
+** th.vsh.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f2 (void * in, void *out, uint32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vuint32m1_t v = __riscv_th_vlhu_v_u32m1 (in, 4);
+ vuint32m1_t v2 = __riscv_th_vlhu_v_u32m1_m (mask, in, 4);
+ vuint32m1_t v3 = __riscv_vadd_vx_u32m1 (v2, -16, 4);
+ vuint32m1_t v4 = __riscv_vadd_vx_u32m1_m (mask, v3, -16, 4);
+ __riscv_th_vsh_v_u32m1 (out, v4, 4);
+}
+
+/*
+** f3:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,tu,mu
+** th.vlhu\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlhu.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[1-9][0-9]?,\s*v[0-9]+,\s*-16,\s*v0.t
+** th.vsh.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f3 (void * in, void *out, uint32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vuint32m1_t v = __riscv_th_vlhu_v_u32m1 (in, 4);
+ vuint32m1_t v2 = __riscv_th_vlhu_v_u32m1_tumu (mask, v, in, 4);
+ vuint32m1_t v3 = __riscv_vadd_vx_u32m1 (v2, -16, 4);
+ vuint32m1_t v4 = __riscv_vadd_vx_u32m1_tumu (mask, v3, v2, -16, 4);
+ __riscv_th_vsh_v_u32m1 (out, v4, 4);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlw-vsw.c b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlw-vsw.c
new file mode 100644
index 00000000000..17a53012acf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlw-vsw.c
@@ -0,0 +1,68 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcxtheadvector -mabi=ilp32d -O3" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+#include "riscv_th_vector.h"
+
+/*
+** f1:
+** th.vsetivli\tzero,4,e32,m1,tu,ma
+** th.vlw\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlw\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vadd\.vx\tv[0-9]+,\s*v[0-9]+,\s*[a-x0-9]+
+** th.vadd\.vx\tv[0-9]+,\s*v[0-9]+,\s*[a-x0-9]+
+** th.vsw\.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f1 (void * in, void *out, int32_t x)
+{
+ vint32m1_t v = __riscv_th_vlw_v_i32m1 (in, 4);
+ vint32m1_t v2 = __riscv_th_vlw_v_i32m1_tu (v, in, 4);
+ vint32m1_t v3 = __riscv_vadd_vx_i32m1 (v2, x, 4);
+ vint32m1_t v4 = __riscv_vadd_vx_i32m1_tu (v3, v2, x, 4);
+ __riscv_th_vsw_v_i32m1 (out, v4, 4);
+}
+
+/*
+** f2:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,ta,ma
+** th.vlw.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vx\tv[0-9]+,\s*v[0-9]+,\s*[a-x0-9]+
+** th.vadd\.vx\tv[1-9][0-9]?,\s*v[0-9]+,\s*[a-x0-9]+,\s*v0.t
+** th.vsw.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f2 (void * in, void *out, int32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vint32m1_t v = __riscv_th_vlw_v_i32m1 (in, 4);
+ vint32m1_t v2 = __riscv_th_vlw_v_i32m1_m (mask, in, 4);
+ vint32m1_t v3 = __riscv_vadd_vx_i32m1 (v2, x, 4);
+ vint32m1_t v4 = __riscv_vadd_vx_i32m1_m (mask, v3, x, 4);
+ __riscv_th_vsw_v_i32m1 (out, v4, 4);
+}
+
+/*
+** f3:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,tu,mu
+** th.vlw\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlw.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vx\tv[0-9]+,\s*v[0-9]+,\s*[a-x0-9]+
+** th.vadd\.vx\tv[1-9][0-9]?,\s*v[0-9]+,\s*[a-x0-9]+,\s*v0.t
+** th.vsw.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f3 (void * in, void *out, int32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vint32m1_t v = __riscv_th_vlw_v_i32m1 (in, 4);
+ vint32m1_t v2 = __riscv_th_vlw_v_i32m1_tumu (mask, v, in, 4);
+ vint32m1_t v3 = __riscv_vadd_vx_i32m1 (v2, x, 4);
+ vint32m1_t v4 = __riscv_vadd_vx_i32m1_tumu (mask, v3, v2, x, 4);
+ __riscv_th_vsw_v_i32m1 (out, v4, 4);
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlwu-vsw.c b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlwu-vsw.c
new file mode 100644
index 00000000000..b187cfc852b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/xtheadvector/vlwu-vsw.c
@@ -0,0 +1,68 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcxtheadvector -mabi=ilp32d -O3" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+#include "riscv_th_vector.h"
+
+/*
+** f1:
+** th.vsetivli\tzero,4,e32,m1,tu,ma
+** th.vlwu\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlwu\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vsw\.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f1 (void * in, void *out, uint32_t x)
+{
+ vuint32m1_t v = __riscv_th_vlwu_v_u32m1 (in, 4);
+ vuint32m1_t v2 = __riscv_th_vlwu_v_u32m1_tu (v, in, 4);
+ vuint32m1_t v3 = __riscv_vadd_vx_u32m1 (v2, -16, 4);
+ vuint32m1_t v4 = __riscv_vadd_vx_u32m1_tu (v3, v2, -16, 4);
+ __riscv_th_vsw_v_u32m1 (out, v4, 4);
+}
+
+/*
+** f2:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,ta,ma
+** th.vlwu.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[1-9][0-9]?,\s*v[0-9]+,\s*-16,\s*v0.t
+** th.vsw.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f2 (void * in, void *out, uint32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vuint32m1_t v = __riscv_th_vlwu_v_u32m1 (in, 4);
+ vuint32m1_t v2 = __riscv_th_vlwu_v_u32m1_m (mask, in, 4);
+ vuint32m1_t v3 = __riscv_vadd_vx_u32m1 (v2, -16, 4);
+ vuint32m1_t v4 = __riscv_vadd_vx_u32m1_m (mask, v3, -16, 4);
+ __riscv_th_vsw_v_u32m1 (out, v4, 4);
+}
+
+/*
+** f3:
+** th.vsetvli\t[a-x0-9]+,zero,e8,mf4,ta,ma
+** th.vlm.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vsetivli\tzero,4,e32,m1,tu,mu
+** th.vlwu\.v\tv[0-9]+,0\([a-x0-9]+\)
+** th.vlwu.v\tv[0-9]+,0\([a-x0-9]+\),v0.t
+** th.vadd\.vi\tv[0-9]+,\s*v[0-9]+,\s*-16
+** th.vadd\.vi\tv[1-9][0-9]?,\s*v[0-9]+,\s*-16,\s*v0.t
+** th.vsw.v\tv[0-9]+,0\([a-x0-9]+\)
+** ret
+*/
+void f3 (void * in, void *out, uint32_t x)
+{
+ vbool32_t mask = *(vbool32_t*)in;
+ asm volatile ("":::"memory");
+ vuint32m1_t v = __riscv_th_vlwu_v_u32m1 (in, 4);
+ vuint32m1_t v2 = __riscv_th_vlwu_v_u32m1_tumu (mask, v, in, 4);
+ vuint32m1_t v3 = __riscv_vadd_vx_u32m1 (v2, -16, 4);
+ vuint32m1_t v4 = __riscv_vadd_vx_u32m1_tumu (mask, v3, v2, -16, 4);
+ __riscv_th_vsw_v_u32m1 (out, v4, 4);
+}