diff mbox series

[5/7] RISC-V: Add intrinsic functions for crypto vector Zvknh[ab] extension

Message ID 20231204025709.3783-5-wangfeng@eswincomputing.com
State Unresolved
Headers
Series None |

Checks

Context Check Description
snail/gcc-patch-check warning Git am fail log

Commit Message

Feng Wang Dec. 4, 2023, 2:57 a.m. UTC 
  This patch add the intrinsic functions(according to https://github.com/
riscv-non-isa/rvv-intrinsic-doc/blob/eopc/vector-crypto/auto-generated/
vector-crypto/intrinsic_funcs.md) for crypto vector Zvknh[ab] extension. And all
the test cases are added for api-testing.

Co-Authored by: Songhe Zhu <zhusonghe@eswincomputing.com>

gcc/ChangeLog:

        * common/config/riscv/riscv-common.cc: Add Zvknh[ab] in riscv_implied_info.
        * config/riscv/riscv-vector-builtins-bases.cc (class vghsh): Add new function_base for Zvknh[ab].
        (class vg_nhab): Ditto.
        (BASE): Add Zvknh[ab] BASE declaration.
        * config/riscv/riscv-vector-builtins-bases.h: Ditto.
        * config/riscv/riscv-vector-builtins-shapes.cc (struct crypto_vv_def): Add function_builder for Zvknh[ab].
        * config/riscv/riscv-vector-builtins.cc: Define new data struct for Zvknh[ab].
        * config/riscv/riscv-vector-crypto-builtins-avail.h (AVAIL): Add enable condition.
        * config/riscv/riscv-vector-crypto-builtins-functions.def (vaeskf2): Add intrinsc def.
        (vsha2ms): Ditto.
        (vsha2ch): Ditto.
        (vsha2cl): Ditto.
        * config/riscv/riscv.md: Add Zvknh[ab] ins name.
        * config/riscv/vector-crypto.md (sha2ms): Add Zvknh[ab] md patterns.
        (@pred_vghsh<VSI:mode>): Ditto.
        (@pred_v<vv_ins1_name><mode>): Dito.
        (@pred_vgmul<VSI:mode>): Ditto
        * config/riscv/vector.md: Add the corresponding attribute for Zvknh[ab].

gcc/testsuite/ChangeLog:

        * gcc.target/riscv/zvk/zvk.exp:
        * gcc.target/riscv/zvk/zvknha/vsha2ch.c: New test.
        * gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c: New test.
        * gcc.target/riscv/zvk/zvknha/vsha2cl.c: New test.
        * gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c: New test.
        * gcc.target/riscv/zvk/zvknha/vsha2ms.c: New test.
        * gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c: New test.
        * gcc.target/riscv/zvk/zvknhb/vsha2ch.c: New test.
        * gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c: New test.
        * gcc.target/riscv/zvk/zvknhb/vsha2cl.c: New test.
        * gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c: New test.
        * gcc.target/riscv/zvk/zvknhb/vsha2ms.c: New test.
        * gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c: New test.
---
 gcc/common/config/riscv/riscv-common.cc       |  2 +
 .../riscv/riscv-vector-builtins-bases.cc      | 15 +++-
 .../riscv/riscv-vector-builtins-bases.h       |  3 +
 .../riscv/riscv-vector-builtins-shapes.cc     |  7 +-
 gcc/config/riscv/riscv-vector-builtins.cc     |  6 ++
 .../riscv-vector-crypto-builtins-avail.h      |  2 +
 ...riscv-vector-crypto-builtins-functions.def | 10 ++-
 gcc/config/riscv/riscv.md                     | 27 +++---
 gcc/config/riscv/vector-crypto.md             | 55 +++++-------
 gcc/config/riscv/vector.md                    | 12 +--
 gcc/testsuite/gcc.target/riscv/zvk/zvk.exp    |  4 +
 .../gcc.target/riscv/zvk/zvknha/vsha2ch.c     | 51 ++++++++++++
 .../riscv/zvk/zvknha/vsha2ch_overloaded.c     | 51 ++++++++++++
 .../gcc.target/riscv/zvk/zvknha/vsha2cl.c     | 51 ++++++++++++
 .../riscv/zvk/zvknha/vsha2cl_overloaded.c     | 51 ++++++++++++
 .../gcc.target/riscv/zvk/zvknha/vsha2ms.c     | 51 ++++++++++++
 .../riscv/zvk/zvknha/vsha2ms_overloaded.c     | 51 ++++++++++++
 .../gcc.target/riscv/zvk/zvknhb/vsha2ch.c     | 83 +++++++++++++++++++
 .../riscv/zvk/zvknhb/vsha2ch_overloaded.c     | 83 +++++++++++++++++++
 .../gcc.target/riscv/zvk/zvknhb/vsha2cl.c     | 83 +++++++++++++++++++
 .../riscv/zvk/zvknhb/vsha2cl_overloaded.c     | 83 +++++++++++++++++++
 .../gcc.target/riscv/zvk/zvknhb/vsha2ms.c     | 83 +++++++++++++++++++
 .../riscv/zvk/zvknhb/vsha2ms_overloaded.c     | 83 +++++++++++++++++++
 23 files changed, 892 insertions(+), 55 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c
diff mbox series

Patch

diff --git a/gcc/common/config/riscv/riscv-common.cc b/gcc/common/config/riscv/riscv-common.cc
index 60a174d4801..7201ac3866c 100644
--- a/gcc/common/config/riscv/riscv-common.cc
+++ b/gcc/common/config/riscv/riscv-common.cc
@@ -125,6 +125,8 @@  static const riscv_implied_info_t riscv_implied_info[] =
   {"zvkb",     "v"},
   {"zvkg",     "v"},
   {"zvkned",   "v"},
+  {"zvknha",   "v"},
+  {"zvknhb",   "v"},
 
   {"zfh", "zfhmin"},
   {"zfhmin", "f"},
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index 61167c8d4e4..a3670ec5b38 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -2228,15 +2228,18 @@  public:
   }
 };
 
-class vghsh : public function_base
+/* Implements vghsh/vsh2ms/vsha2c[hl]. */
+template<int UNSPEC>
+class vg_nhab : public function_base
 {
 public:
   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
   {
-      return e.use_exact_insn (code_for_pred_vghsh (e.vector_mode ()));
+    return e.use_exact_insn (code_for_pred_v (UNSPEC, e.vector_mode ()));
   }
 };
 
@@ -2581,7 +2584,7 @@  static CONSTEXPR const vcltz<UNSPEC_VCTZ>        vctz_obj;
 static CONSTEXPR const vwsll vwsll_obj;
 static CONSTEXPR const clmul<UNSPEC_VCLMUL>      vclmul_obj;
 static CONSTEXPR const clmul<UNSPEC_VCLMULH>     vclmulh_obj;
-static CONSTEXPR const vghsh vghsh_obj;
+static CONSTEXPR const vg_nhab<UNSPEC_VGHSH>     vghsh_obj;
 static CONSTEXPR const crypto_vv<UNSPEC_VGMUL>   vgmul_obj;
 static CONSTEXPR const crypto_vv<UNSPEC_VAESEF>  vaesef_obj;
 static CONSTEXPR const crypto_vv<UNSPEC_VAESEM>  vaesem_obj;
@@ -2590,6 +2593,9 @@  static CONSTEXPR const crypto_vv<UNSPEC_VAESDM>  vaesdm_obj;
 static CONSTEXPR const crypto_vv<UNSPEC_VAESZ>   vaesz_obj;
 static CONSTEXPR const vaeskf1 vaeskf1_obj;
 static CONSTEXPR const vaeskf2 vaeskf2_obj;
+static CONSTEXPR const vg_nhab<UNSPEC_VSHA2MS>   vsha2ms_obj;
+static CONSTEXPR const vg_nhab<UNSPEC_VSHA2CH>   vsha2ch_obj;
+static CONSTEXPR const vg_nhab<UNSPEC_VSHA2CL>   vsha2cl_obj;
 
 /* Declare the function base NAME, pointing it to an instance
    of class <NAME>_obj.  */
@@ -2873,4 +2879,7 @@  BASE (vaesdm)
 BASE (vaesz)
 BASE (vaeskf1)
 BASE (vaeskf2)
+BASE (vsha2ms)
+BASE (vsha2ch)
+BASE (vsha2cl)
 } // end namespace riscv_vector
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.h b/gcc/config/riscv/riscv-vector-builtins-bases.h
index a420d9acd2c..0560b0008f0 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.h
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.h
@@ -301,6 +301,9 @@  extern const function_base *const vaesdm;
 extern const function_base *const vaesz;
 extern const function_base *const vaeskf1;
 extern const function_base *const vaeskf2;
+extern const function_base *const vsha2ms;
+extern const function_base *const vsha2ch;
+extern const function_base *const vsha2cl;
 }
 
 } // end namespace riscv_vector
diff --git a/gcc/config/riscv/riscv-vector-builtins-shapes.cc b/gcc/config/riscv/riscv-vector-builtins-shapes.cc
index 22a2689eae5..5873103857a 100644
--- a/gcc/config/riscv/riscv-vector-builtins-shapes.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-shapes.cc
@@ -1019,10 +1019,13 @@  struct crypto_vv_def : public build_base
     if (overloaded_p && !instance.base->can_be_overloaded_p (instance.pred))
       return nullptr;
     b.append_base_name (instance.base_name);
-    /* There is no op_type name in vghsh/vgmul/vaesz overloaded intrinsic */
+    /* There is no op_type name in vghsh/vgmul/vaesz/vsha2ms/vsha2ch/vsha2cl overloaded intrinsic */
     if (!((strcmp (instance.base_name, "vghsh") == 0
           || strcmp (instance.base_name, "vgmul") == 0
-          || strcmp (instance.base_name, "vaesz") == 0)
+          || strcmp (instance.base_name, "vaesz") == 0
+          || strcmp (instance.base_name, "vsha2ms") == 0
+          || strcmp (instance.base_name, "vsha2ch") == 0
+          || strcmp (instance.base_name, "vsha2cl") == 0)
           && overloaded_p))
       b.append_name (operand_suffixes[instance.op_info->op]);
     if (!overloaded_p)
diff --git a/gcc/config/riscv/riscv-vector-builtins.cc b/gcc/config/riscv/riscv-vector-builtins.cc
index 45162b289ec..e5e8f0d19ac 100644
--- a/gcc/config/riscv/riscv-vector-builtins.cc
+++ b/gcc/config/riscv/riscv-vector-builtins.cc
@@ -2728,6 +2728,12 @@  static CONSTEXPR const rvv_op_info u_vvx_crypto_sew64_ops
      rvv_arg_type_info (RVV_BASE_vector), /* Return type */
      vx_args /* Args */};
 
+static CONSTEXPR const rvv_op_info u_vvvv_crypto_sew64_ops
+  = {crypto_sew64_ops,			   /* Types */
+     OP_TYPE_vv,					   /* Suffix */
+     rvv_arg_type_info (RVV_BASE_vector), /* Return type */
+     vvv_args /* Args */};
+
 /* A list of all RVV base function types.  */
 static CONSTEXPR const function_type_info function_types[] = {
 #define DEF_RVV_TYPE_INDEX(                                                    \
diff --git a/gcc/config/riscv/riscv-vector-crypto-builtins-avail.h b/gcc/config/riscv/riscv-vector-crypto-builtins-avail.h
index 8b993fb31f5..bc1b6ec9b5b 100755
--- a/gcc/config/riscv/riscv-vector-crypto-builtins-avail.h
+++ b/gcc/config/riscv/riscv-vector-crypto-builtins-avail.h
@@ -17,5 +17,7 @@  AVAIL (zvbc, TARGET_ZVBC)
 AVAIL (zvkb_or_zvbb, TARGET_ZVKB || TARGET_ZVBB)
 AVAIL (zvkg, TARGET_ZVKG)
 AVAIL (zvkned, TARGET_ZVKNED)
+AVAIL (zvknha_or_zvknhb, TARGET_ZVKNHA || TARGET_ZVKNHB)
+AVAIL (zvknhb, TARGET_ZVKNHB)
 }
 #endif
diff --git a/gcc/config/riscv/riscv-vector-crypto-builtins-functions.def b/gcc/config/riscv/riscv-vector-crypto-builtins-functions.def
index 9fea9f1a757..9c89412a9a9 100755
--- a/gcc/config/riscv/riscv-vector-crypto-builtins-functions.def
+++ b/gcc/config/riscv/riscv-vector-crypto-builtins-functions.def
@@ -56,4 +56,12 @@  DEF_VECTOR_CRYPTO_FUNCTION (vaesz,    crypto_vv, none_tu_preds, u_vvs_crypto_sew
 DEF_VECTOR_CRYPTO_FUNCTION (vaesz,    crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x8_ops,  zvkned)
 DEF_VECTOR_CRYPTO_FUNCTION (vaesz,    crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x16_ops, zvkned)
 DEF_VECTOR_CRYPTO_FUNCTION (vaeskf1,  crypto_vi, none_tu_preds, u_vv_size_crypto_sew32_ops,  zvkned)
-DEF_VECTOR_CRYPTO_FUNCTION (vaeskf2,  crypto_vi, none_tu_preds, u_vvv_size_crypto_sew32_ops, zvkned)
\ No newline at end of file
+DEF_VECTOR_CRYPTO_FUNCTION (vaeskf2,  crypto_vi, none_tu_preds, u_vvv_size_crypto_sew32_ops, zvkned)
+//ZVKNHA
+DEF_VECTOR_CRYPTO_FUNCTION (vsha2ms,  crypto_vv, none_tu_preds, u_vvvv_crypto_sew32_ops, zvknha_or_zvknhb)
+DEF_VECTOR_CRYPTO_FUNCTION (vsha2ch,  crypto_vv, none_tu_preds, u_vvvv_crypto_sew32_ops, zvknha_or_zvknhb)
+DEF_VECTOR_CRYPTO_FUNCTION (vsha2cl,  crypto_vv, none_tu_preds, u_vvvv_crypto_sew32_ops, zvknha_or_zvknhb)
+//ZVKNHB
+DEF_VECTOR_CRYPTO_FUNCTION (vsha2ms,  crypto_vv, none_tu_preds, u_vvvv_crypto_sew64_ops, zvknhb)
+DEF_VECTOR_CRYPTO_FUNCTION (vsha2ch,  crypto_vv, none_tu_preds, u_vvvv_crypto_sew64_ops, zvknhb)
+DEF_VECTOR_CRYPTO_FUNCTION (vsha2cl,  crypto_vv, none_tu_preds, u_vvvv_crypto_sew64_ops, zvknhb)
\ No newline at end of file
diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index 39b4e4b2f6a..e8fc21e8ceb 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -437,16 +437,20 @@ 
 ;; vrol         crypto vector rotate left instructions
 ;; vror         crypto vector rotate right instructions
 ;; vwsll        crypto vector widening shift left logical instructions
-;; vclmul       vector crypto carry-less multiply - return low half instructions
-;; vclmulh      vector crypto carry-less multiply - return high half instructions
-;; vghsh        vector crypto add-multiply over GHASH Galois-Field instructions
-;; vgmul        vector crypto multiply over GHASH Galois-Field instrumctions
-;; vaesef       vector crypto AES final-round encryption instructions
-;; vaesem       vector crypto AES middle-round encryption instructions
-;; vaesdf       vector crypto AES final-round decryption instructions
-;; vaesdm       vector crypto AES middle-round decryption instructions
-;; vaeskf1      vector crypto AES-128 Forward KeySchedule generation instructions
-;; vaeskf2      vector crypto AES-256 Forward KeySchedule generation instructions
+;; vclmul       crypto vector carry-less multiply - return low half instructions
+;; vclmulh      crypto vector carry-less multiply - return high half instructions
+;; vghsh        crypto vector add-multiply over GHASH Galois-Field instructions
+;; vgmul        crypto vector multiply over GHASH Galois-Field instrumctions
+;; vaesef       crypto vector AES final-round encryption instructions
+;; vaesem       crypto vector AES middle-round encryption instructions
+;; vaesdf       crypto vector AES final-round decryption instructions
+;; vaesdm       crypto vector AES middle-round decryption instructions
+;; vaeskf1      crypto vector AES-128 Forward KeySchedule generation instructions
+;; vaeskf2      crypto vector AES-256 Forward KeySchedule generation instructions
+;; vaesz        crypto vector AES round zero encryption/decryption instructions
+;; vsha2ms      crypto vector SHA-2 message schedule instructions
+;; vsha2ch      crypto vector SHA-2 two rounds of compression instructions
+;; vsha2cl      crypto vector SHA-2 two rounds of compression instructions
 (define_attr "type"
   "unknown,branch,jump,jalr,ret,call,load,fpload,store,fpstore,
    mtc,mfc,const,arith,logical,shift,slt,imul,idiv,move,fmove,fadd,fmul,
@@ -467,7 +471,8 @@ 
    vmalu,vmpop,vmffs,vmsfs,vmiota,vmidx,vimovvx,vimovxv,vfmovvf,vfmovfv,
    vslideup,vslidedown,vislide1up,vislide1down,vfslide1up,vfslide1down,
    vgather,vcompress,vmov,vector,vandn,vbrev,vbrev8,vrev8,vclz,vctz,vrol,vror,vwsll,
-   vclmul,vclmulh,vghsh,vgmul,vaesef,vaesem,vaesdf,vaesdm,vaeskf1,vaeskf2,vaesz"
+   vclmul,vclmulh,vghsh,vgmul,vaesef,vaesem,vaesdf,vaesdm,vaeskf1,vaeskf2,vaesz,
+   vsha2ms,vsha2ch,vsha2cl"
   (cond [(eq_attr "got" "load") (const_string "load")
 
 	 ;; If a doubleword move uses these expensive instructions,
diff --git a/gcc/config/riscv/vector-crypto.md b/gcc/config/riscv/vector-crypto.md
index e84aaf50fc0..38b41fb3664 100755
--- a/gcc/config/riscv/vector-crypto.md
+++ b/gcc/config/riscv/vector-crypto.md
@@ -30,6 +30,9 @@ 
     UNSPEC_VAESZVS
     UNSPEC_VAESKF1
     UNSPEC_VAESKF2
+    UNSPEC_VSHA2MS
+    UNSPEC_VSHA2CH
+    UNSPEC_VSHA2CL
 ])
 
 (define_int_attr ror_rol [(UNSPEC_VROL "rol") (UNSPEC_VROR "ror")])
@@ -46,6 +49,9 @@ 
                               (UNSPEC_VAESEMVS "aesem") (UNSPEC_VAESDFVS "aesdf")
                               (UNSPEC_VAESDMVS "aesdm") (UNSPEC_VAESZVS  "aesz" )])
 
+(define_int_attr vv_ins1_name [(UNSPEC_VGHSH "ghsh")     (UNSPEC_VSHA2MS "sha2ms")
+                               (UNSPEC_VSHA2CH "sha2ch") (UNSPEC_VSHA2CL "sha2cl")])
+
 (define_int_attr ins_type [(UNSPEC_VGMUL    "vv") (UNSPEC_VAESEFVV "vv")
                            (UNSPEC_VAESEMVV "vv") (UNSPEC_VAESDFVV "vv")
                            (UNSPEC_VAESDMVV "vv") (UNSPEC_VAESEFVS "vs")
@@ -65,6 +71,8 @@ 
                                        UNSPEC_VAESEMVS UNSPEC_VAESDFVS UNSPEC_VAESDMVS
                                        UNSPEC_VAESZVS])
 
+(define_int_iterator UNSPEC_VGNHAB [UNSPEC_VGHSH UNSPEC_VSHA2MS UNSPEC_VSHA2CH UNSPEC_VSHA2CL])
+
 ;; zvbb instructions patterns.
 ;; vandn.vv vandn.vx vrol.vv vrol.vx
 ;; vror.vv vror.vx vror.vi
@@ -292,44 +300,27 @@ 
   [(set_attr "type" "vclmul<h>")
    (set_attr "mode" "<VDI:MODE>")])
 
-;; zvkg instructions patterns.
-;; vghsh.vv  vgmul.vv
-(define_insn "@pred_vghsh<VSI:mode>"
-  [(set (match_operand:VSI 0 "register_operand"           "=vd")
-        (if_then_else:VSI
-          (unspec:<VSI:VM>
+;; zvknh[ab] and zvkg instructions patterns.
+;; vsha2ms.vv vsha2ch.vv vsha2cl.vv vghsh.vv
+
+(define_insn "@pred_v<vv_ins1_name><mode>"
+  [(set (match_operand:VQEXTI 0 "register_operand"           "=vd")
+        (if_then_else:VQEXTI
+          (unspec:<VQEXTI:VM>
             [(match_operand 4 "vector_length_operand"     "rK")
              (match_operand 5 "const_int_operand"         " i")
              (match_operand 6 "const_int_operand"         " i")
              (reg:SI VL_REGNUM)
              (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
-          (unspec:VSI
-             [(match_operand:VSI 1 "register_operand" " 0")
-              (match_operand:VSI 2 "register_operand" "vr")
-			  (match_operand:VSI 3 "register_operand" "vr")] UNSPEC_VGHSH)
-          (match_dup 1)))]
-  "TARGET_ZVKG"
-  "vghsh.vv\t%0,%2,%3"
-  [(set_attr "type" "vghsh")
-   (set_attr "mode" "<VSI:MODE>")])
-
-(define_insn "@pred_vgmul<VSI:mode>"
-  [(set (match_operand:VSI 0 "register_operand"           "=vd")
-        (if_then_else:VSI
-          (unspec:<VSI:VM>
-            [(match_operand 3 "vector_length_operand"     "rK")
-             (match_operand 4 "const_int_operand"         " i")
-             (match_operand 5 "const_int_operand"         " i")
-             (reg:SI VL_REGNUM)
-             (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
-          (unspec:VSI
-             [(match_operand:VSI 1 "register_operand" " 0")
-              (match_operand:VSI 2 "register_operand" "vr")] UNSPEC_VGMUL)
+          (unspec:VQEXTI
+             [(match_operand:VQEXTI 1 "register_operand" " 0")
+              (match_operand:VQEXTI 2 "register_operand" "vr")
+              (match_operand:VQEXTI 3 "register_operand" "vr")] UNSPEC_VGNHAB)
           (match_dup 1)))]
-  "TARGET_ZVKG"
-  "vgmul.vv\t%0,%2"
-  [(set_attr "type" "vgmul")
-   (set_attr "mode" "<VSI:MODE>")])
+  "TARGET_ZVKNHA || TARGET_ZVKNHB || TARGET_ZVKG"
+  "v<vv_ins1_name>.vv\t%0,%2,%3"
+  [(set_attr "type" "v<vv_ins1_name>")
+   (set_attr "mode" "<VQEXTI:MODE>")])
 
 ;; zvkned instructions patterns.
 ;; vgmul.vv       vaesz.vs
diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md
index 66a2e9358cb..e2de9bfc496 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -54,7 +54,7 @@ 
 			  vgather,vcompress,vlsegde,vssegte,vlsegds,vssegts,vlsegdux,vlsegdox,\
 			  vssegtux,vssegtox,vlsegdff,vandn,vbrev,vbrev8,vrev8,vclz,vctz,vrol,\
                           vror,vwsll,vclmul,vclmulh,vghsh,vgmul,vaesef,vaesem,vaesdf,vaesdm,\
-                          vaeskf1,vaeskf2,vaesz")
+                          vaeskf1,vaeskf2,vaesz,vsha2ms,vsha2ch,vsha2cl")
 	 (const_string "true")]
 	(const_string "false")))
 
@@ -78,7 +78,7 @@ 
 			  vgather,vcompress,vlsegde,vssegte,vlsegds,vssegts,vlsegdux,vlsegdox,\
 			  vssegtux,vssegtox,vlsegdff,vandn,vbrev,vbrev8,vrev8,vclz,vctz,vrol,\
                           vror,vwsll,vclmul,vclmulh,vghsh,vgmul,vaesef,vaesem,vaesdf,vaesdm,\
-                          vaeskf1,vaeskf2,vaesz")
+                          vaeskf1,vaeskf2,vaesz,vsha2ms,vsha2ch,vsha2cl")
 	 (const_string "true")]
 	(const_string "false")))
 
@@ -707,7 +707,7 @@ 
 	       (const_int 2)
 
 	       (eq_attr "type" "vimerge,vfmerge,vcompress,vghsh,vgmul,vaesef,vaesem,vaesdf,vaesdm,\
-                                vaeskf1,vaeskf2,vaesz")
+                                vaeskf1,vaeskf2,vaesz,vsha2ms,vsha2ch,vsha2cl")
 	       (const_int 1)
 
 	       (eq_attr "type" "vimuladd,vfmuladd")
@@ -747,7 +747,7 @@ 
 			  vfcvtftoi,vfwcvtitof,vfwcvtftoi,vfwcvtftof,vfncvtitof,\
 			  vfncvtftoi,vfncvtftof,vfclass,vimovxv,vfmovfv,vcompress,\
 			  vlsegde,vssegts,vssegtux,vssegtox,vlsegdff,vbrev,vbrev8,vrev8,\
-                          vghsh,vaeskf1,vaeskf2")
+                          vghsh,vaeskf1,vaeskf2,vsha2ms,vsha2ch,vsha2cl")
 	   (const_int 4)
 
 	 ;; If operands[3] of "vlds" is not vector mode, it is pred_broadcast.
@@ -780,7 +780,7 @@ 
 			  vfcvtitof,vfcvtftoi,vfwcvtitof,vfwcvtftoi,vfwcvtftof,\
 			  vfncvtitof,vfncvtftoi,vfncvtftof,vfclass,vimovxv,vfmovfv,\
 			  vcompress,vldff,vlsegde,vlsegdff,vbrev,vbrev8,vrev8,vghsh,\
-                          vaeskf1,vaeskf2")
+                          vaeskf1,vaeskf2,vsha2ms,vsha2ch,vsha2cl")
 	   (symbol_ref "riscv_vector::get_ta(operands[5])")
 
 	 ;; If operands[3] of "vlds" is not vector mode, it is pred_broadcast.
@@ -867,7 +867,7 @@ 
 	 (eq_attr "type" "vimuladd,vfmuladd")
 	   (const_int 9)
 
-	 (eq_attr "type" "vmsfs,vmidx,vcompress,vghsh,vaeskf1,vaeskf2")
+	 (eq_attr "type" "vmsfs,vmidx,vcompress,vghsh,vaeskf1,vaeskf2,vsha2ms,vsha2ch,vsha2cl")
 	   (const_int 6)
 
 	 (eq_attr "type" "vmpop,vmffs,vssegte,vclz,vctz")
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvk.exp b/gcc/testsuite/gcc.target/riscv/zvk/zvk.exp
index b47602e1c83..13f1302314a 100644
--- a/gcc/testsuite/gcc.target/riscv/zvk/zvk.exp
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvk.exp
@@ -42,6 +42,10 @@  dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvkg/*.\[cS\]]] \
         "" $DEFAULT_CFLAGS
 dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvkned/*.\[cS\]]] \
         "" $DEFAULT_CFLAGS
+dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvknha/*.\[cS\]]] \
+        "" $DEFAULT_CFLAGS
+dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvknhb/*.\[cS\]]] \
+        "" $DEFAULT_CFLAGS
 
 # All done.
 dg-finish
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch.c
new file mode 100644
index 00000000000..2dea4bbb89f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch.c
@@ -0,0 +1,51 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2ch_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32mf2(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ch_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m1(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ch_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m2(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ch_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m4(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ch_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m8(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2ch_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32mf2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ch_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m1_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ch_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ch_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m4_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ch_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m8_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsha2ch\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c
new file mode 100644
index 00000000000..5a16400f800
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c
@@ -0,0 +1,51 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2ch_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ch_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ch_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ch_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ch_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2ch_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ch_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ch_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ch_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ch_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsha2ch\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */
\ No newline at end of file
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl.c
new file mode 100644
index 00000000000..b2bbc1559f6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl.c
@@ -0,0 +1,51 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2cl_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32mf2(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2cl_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m1(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2cl_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m2(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2cl_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m4(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2cl_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m8(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2cl_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32mf2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2cl_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m1_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2cl_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2cl_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m4_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2cl_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m8_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsha2cl\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c
new file mode 100644
index 00000000000..7a54466b204
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c
@@ -0,0 +1,51 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2cl_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2cl_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2cl_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2cl_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2cl_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2cl_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2cl_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2cl_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2cl_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2cl_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsha2cl\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms.c
new file mode 100644
index 00000000000..57523576c3a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms.c
@@ -0,0 +1,51 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2ms_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32mf2(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ms_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m1(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ms_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m2(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ms_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m4(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ms_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m8(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2ms_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32mf2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ms_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m1_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ms_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ms_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m4_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ms_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m8_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsha2ms\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */
\ No newline at end of file
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c
new file mode 100644
index 00000000000..4d31ee0ee34
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c
@@ -0,0 +1,51 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2ms_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ms_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ms_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ms_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ms_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2ms_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ms_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ms_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ms_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ms_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */
+/* { dg-final { scan-assembler-times {vsha2ms\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch.c
new file mode 100644
index 00000000000..811c313887b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch.c
@@ -0,0 +1,83 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2ch_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32mf2(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ch_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m1(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ch_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m2(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ch_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m4(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ch_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m8(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2ch_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u64m1(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2ch_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u64m2(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2ch_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u64m4(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2ch_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u64m8(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2ch_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32mf2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ch_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m1_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ch_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ch_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m4_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ch_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u32m8_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2ch_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u64m1_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2ch_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u64m2_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2ch_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u64m4_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2ch_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch_vv_u64m8_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsha2ch\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c
new file mode 100644
index 00000000000..a09f9876c75
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c
@@ -0,0 +1,83 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2ch_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ch_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ch_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ch_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ch_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2ch_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2ch_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2ch_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2ch_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2ch_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ch_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ch_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ch_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ch_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2ch_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2ch_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2ch_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2ch_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2ch_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsha2ch\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */
\ No newline at end of file
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl.c
new file mode 100644
index 00000000000..f44c5a2cfbf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl.c
@@ -0,0 +1,83 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2cl_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32mf2(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2cl_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m1(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2cl_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m2(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2cl_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m4(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2cl_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m8(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2cl_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u64m1(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2cl_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u64m2(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2cl_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u64m4(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2cl_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u64m8(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2cl_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32mf2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2cl_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m1_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2cl_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2cl_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m4_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2cl_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u32m8_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2cl_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u64m1_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2cl_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u64m2_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2cl_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u64m4_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2cl_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl_vv_u64m8_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsha2cl\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c
new file mode 100644
index 00000000000..2354ab54a63
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c
@@ -0,0 +1,83 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2cl_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2cl_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2cl_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2cl_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2cl_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2cl_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2cl_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2cl_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2cl_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2cl_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2cl_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2cl_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2cl_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2cl_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2cl_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2cl_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2cl_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2cl_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2cl_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsha2cl\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms.c
new file mode 100644
index 00000000000..45aba16119d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms.c
@@ -0,0 +1,83 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2ms_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32mf2(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ms_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m1(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ms_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m2(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ms_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m4(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ms_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m8(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2ms_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u64m1(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2ms_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u64m2(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2ms_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u64m4(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2ms_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u64m8(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2ms_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32mf2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ms_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m1_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ms_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m2_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ms_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m4_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ms_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u32m8_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2ms_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u64m1_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2ms_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u64m2_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2ms_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u64m4_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2ms_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms_vv_u64m8_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsha2ms\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */
\ No newline at end of file
diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c
new file mode 100644
index 00000000000..3cad2e09fc7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c
@@ -0,0 +1,83 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */
+#include <stdint.h>
+#include <riscv_vector.h>
+
+typedef _Float16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+vuint32mf2_t test_vsha2ms_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ms_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ms_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ms_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ms_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2ms_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2ms_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2ms_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2ms_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms(vd, vs2, vs1, vl);
+}
+
+vuint32mf2_t test_vsha2ms_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m1_t test_vsha2ms_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m2_t test_vsha2ms_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m4_t test_vsha2ms_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint32m8_t test_vsha2ms_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m1_t test_vsha2ms_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m2_t test_vsha2ms_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m4_t test_vsha2ms_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+vuint64m8_t test_vsha2ms_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) {
+  return __riscv_vsha2ms_tu(vd, vs2, vs1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */
+/* { dg-final { scan-assembler-times {vsha2ms\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */