diff mbox series

[v2] RISC-V: Allow VMS{Compare} (V1, V1) shortcut optimization

Message ID 20230419112307.3805682-1-pan2.li@intel.com
State Accepted
Headers
Series [v2] RISC-V: Allow VMS{Compare} (V1, V1) shortcut optimization |

Checks

Context Check Description
snail/gcc-patch-check success Github commit url

Commit Message

Li, Pan2 via Gcc-patches April 19, 2023, 11:23 a.m. UTC 
  From: Pan Li <pan2.li@intel.com>

This patch try to adjust the RISC-V Vector RTL for the
generic shortcut optimization for RVV integer compare.
It includes compare operator eq, ne, ltu, lt, leu, le,
gtu, gt, geu and ge.

Assume we have below test code.
vbool1_t test_shortcut_for_riscv_vmslt_case_0(vint8m8_t v1, size_t vl) {
  return __riscv_vmslt_vv_i8m8_b1(v1, v1, vl);
}

Before this patch:
vsetvli  zero,a2,e8,m8,ta,ma
vl8re8.v v24,0(a1)
vmslt.vv v8,v24,v24
vsetvli  a5,zero,e8,m8,ta,ma
vsm.v    v8,0(a0)
ret

After this patch:
vsetvli zero,a2,e8,mf8,ta,ma
vmclr.m v24                    <- optimized to vmclr.m
vsetvli zero,a5,e8,mf8,ta,ma
vsm.v   v24,0(a0)
ret

We would like to make it happen in the generic way for the optimization.
The patch add one more operand(aka policy tail) to VMS{Compare} pattern,
to match the pred_mov<mode> (aka vmset/vmclr) pattern. We would like to
let the GCC to recognize (lt:(reg v) (reg v)) and lower it to
(const_vector:0), and then map into the pred_mov and VMS{Compare} pattern
for both the tail policy and avl operand.

The pred_mov may looks like
...(unspec:
     [(match_operand 1 ...)
      (match_operand 4 ...)
+     (match_operand 5 ...)       <- added policy tail
      (reg:SI VL)
      (reg:SI VTYPE)] ...)
   (match_operand     3 "vector_move_operand" ...)  <-------+
   (match_operand     2 "vector_undef_operand" ...)         |
                                                            |
The pred_cmp may looks like                                 |
...(unspec:                                                 |
     [(match_operand  1 ...)                                |
      (match_operand  6 ...)                                |
      (match_operand  7 ...)                                |
      (match_operand  8 ...)      <- existing policy tail   |
      (reg:SI VL)                                           |
      (reg:SI VTYPE)] ...)                               lower to
   (match_operator    3 ...)                      ----+     |
     [(match_operator 4 ...)                          +-----+
      (match_operator 5 "vector_arith_operand"])] ----+
   (match_operand     2 "vector_undef_operand" ...)

However, there some cases in the test files cannot be optimized right
now. We will file separated patches to try to make it happen.

gcc/ChangeLog:

	* config/riscv/riscv-v.cc (emit_pred_op): Add api to add the
	  policy tail or policy mask separately.
	* config/riscv/riscv-vector-builtins-bases.cc: Change the
	  VMS{Compare} default tail policy from false to true.
	* config/riscv/vector.md: Add the policy tail operand for the
	  pred_mov, pred_cmp.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/base/integer_compare_insn_shortcut.c: New test.

Signed-off-by: Pan Li <pan2.li@intel.com>
Co-authored-by: Ju-Zhe Zhong <juzhe.zhong@rivai.ai>
---
 gcc/config/riscv/riscv-v.cc                   |  15 +-
 .../riscv/riscv-vector-builtins-bases.cc      |   6 +-
 gcc/config/riscv/vector.md                    |  14 +-
 .../rvv/base/integer_compare_insn_shortcut.c  | 291 ++++++++++++++++++
 4 files changed, 319 insertions(+), 7 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/integer_compare_insn_shortcut.c
diff mbox series

Patch

diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index 392f5d02e17..c3881920812 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -71,12 +71,23 @@  public:
     add_input_operand (RVV_VUNDEF (mode), mode);
   }
   void add_policy_operand (enum tail_policy vta, enum mask_policy vma)
+  {
+    add_tail_policy_operand (vta);
+    add_mask_policy_operand (vma);
+  }
+
+  void add_tail_policy_operand (enum tail_policy vta)
   {
     rtx tail_policy_rtx = gen_int_mode (vta, Pmode);
-    rtx mask_policy_rtx = gen_int_mode (vma, Pmode);
     add_input_operand (tail_policy_rtx, Pmode);
+  }
+
+  void add_mask_policy_operand (enum mask_policy vma)
+  {
+    rtx mask_policy_rtx = gen_int_mode (vma, Pmode);
     add_input_operand (mask_policy_rtx, Pmode);
   }
+
   void add_avl_type_operand (avl_type type)
   {
     add_input_operand (gen_int_mode (type, Pmode), Pmode);
@@ -206,6 +217,8 @@  emit_pred_op (unsigned icode, rtx mask, rtx dest, rtx src, rtx len,
 
   if (GET_MODE_CLASS (mode) != MODE_VECTOR_BOOL)
     e.add_policy_operand (get_prefer_tail_policy (), get_prefer_mask_policy ());
+  else
+    e.add_tail_policy_operand (get_prefer_tail_policy ());
 
   if (vlmax_p)
     e.add_avl_type_operand (avl_type::VLMAX);
diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc
index 52467bbc961..7c6064a5a24 100644
--- a/gcc/config/riscv/riscv-vector-builtins-bases.cc
+++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc
@@ -756,7 +756,7 @@  template<rtx_code CODE>
 class mask_logic : public function_base
 {
 public:
-  bool apply_tail_policy_p () const override { return false; }
+  bool apply_tail_policy_p () const override { return true; }
   bool apply_mask_policy_p () const override { return false; }
 
   rtx expand (function_expander &e) const override
@@ -768,7 +768,7 @@  template<rtx_code CODE>
 class mask_nlogic : public function_base
 {
 public:
-  bool apply_tail_policy_p () const override { return false; }
+  bool apply_tail_policy_p () const override { return true; }
   bool apply_mask_policy_p () const override { return false; }
 
   rtx expand (function_expander &e) const override
@@ -780,7 +780,7 @@  template<rtx_code CODE>
 class mask_notlogic : public function_base
 {
 public:
-  bool apply_tail_policy_p () const override { return false; }
+  bool apply_tail_policy_p () const override { return true; }
   bool apply_mask_policy_p () const override { return false; }
 
   rtx expand (function_expander &e) const override
diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md
index 0ecca98f20c..6819363b9ff 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -1032,6 +1032,7 @@  (define_insn_and_split "@pred_mov<mode>"
 	    [(match_operand:VB 1 "vector_all_trues_mask_operand" "Wc1, Wc1, Wc1, Wc1, Wc1")
 	     (match_operand 4 "vector_length_operand"            " rK,  rK,  rK,  rK,  rK")
 	     (match_operand 5 "const_int_operand"                "  i,   i,   i,   i,   i")
+	     (match_operand 6 "const_int_operand"                "  i,   i,   i,   i,   i")
 	     (reg:SI VL_REGNUM)
 	     (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
 	  (match_operand:VB 3 "vector_move_operand"              "  m,  vr,  vr, Wc0, Wc1")
@@ -4113,7 +4114,8 @@  (define_expand "@pred_ge<mode>_scalar"
       if (satisfies_constraint_Wc1 (operands[1]))
 	emit_insn (
 	  gen_pred_mov (<VM>mode, operands[0], CONSTM1_RTX (<VM>mode), undef,
-			CONSTM1_RTX (<VM>mode), operands[6], operands[8]));
+			CONSTM1_RTX (<VM>mode), operands[6], operands[8],
+			gen_int_mode (riscv_vector::get_prefer_mask_policy (), Pmode)));
       else
 	{
 	  /* If vmsgeu_mask with 0 immediate, expand it to vmor mask, maskedoff.
@@ -4158,7 +4160,8 @@  (define_expand "@pred_ge<mode>_scalar"
 					operands[6], operands[7], operands[8]));
 	  emit_insn (gen_pred_nand<vm> (operands[0], CONSTM1_RTX (<VM>mode),
 					undef, operands[0], operands[0],
-					operands[6], operands[8]));
+					operands[6], operands[8],
+					gen_int_mode (riscv_vector::get_prefer_mask_policy (), Pmode)));
 	}
       else
 	{
@@ -4173,7 +4176,8 @@  (define_expand "@pred_ge<mode>_scalar"
 		operands[5], operands[6], operands[7], operands[8]));
 	      emit_insn (
 		gen_pred_andnot<vm> (operands[0], CONSTM1_RTX (<VM>mode), undef,
-				   operands[1], reg, operands[6], operands[8]));
+				     operands[1], reg, operands[6], operands[8],
+				     gen_int_mode (riscv_vector::get_prefer_mask_policy (), Pmode)));
 	    }
 	  else
 	    {
@@ -5196,6 +5200,7 @@  (define_insn "@pred_<optab><mode>"
 	    [(match_operand:VB 1 "vector_all_trues_mask_operand" "Wc1")
 	     (match_operand 5 "vector_length_operand"            " rK")
 	     (match_operand 6 "const_int_operand"                "  i")
+	     (match_operand 7 "const_int_operand"                "  i")
 	     (reg:SI VL_REGNUM)
 	     (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
 	  (any_bitwise:VB
@@ -5216,6 +5221,7 @@  (define_insn "@pred_n<optab><mode>"
 	    [(match_operand:VB 1 "vector_all_trues_mask_operand" "Wc1")
 	     (match_operand 5 "vector_length_operand"            " rK")
 	     (match_operand 6 "const_int_operand"                "  i")
+	     (match_operand 7 "const_int_operand"                "  i")
 	     (reg:SI VL_REGNUM)
 	     (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
 	  (not:VB
@@ -5237,6 +5243,7 @@  (define_insn "@pred_<optab>not<mode>"
 	    [(match_operand:VB 1 "vector_all_trues_mask_operand" "Wc1")
 	     (match_operand 5 "vector_length_operand"            " rK")
 	     (match_operand 6 "const_int_operand"                "  i")
+	     (match_operand 7 "const_int_operand"                "  i")
 	     (reg:SI VL_REGNUM)
 	     (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
 	  (and_ior:VB
@@ -5258,6 +5265,7 @@  (define_insn "@pred_not<mode>"
 	    [(match_operand:VB 1 "vector_all_trues_mask_operand" "Wc1")
 	     (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)
 	  (not:VB
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/integer_compare_insn_shortcut.c b/gcc/testsuite/gcc.target/riscv/rvv/base/integer_compare_insn_shortcut.c
new file mode 100644
index 00000000000..495a0f11440
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/integer_compare_insn_shortcut.c
@@ -0,0 +1,291 @@ 
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O3" } */
+
+#include "riscv_vector.h"
+
+vbool1_t test_shortcut_for_riscv_vmseq_case_0(vint8m8_t v1, size_t vl) {
+  return __riscv_vmseq_vv_i8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmseq_case_1(vint8m4_t v1, size_t vl) {
+  return __riscv_vmseq_vv_i8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmseq_case_2(vint8m2_t v1, size_t vl) {
+  return __riscv_vmseq_vv_i8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmseq_case_3(vint8m1_t v1, size_t vl) {
+  return __riscv_vmseq_vv_i8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmseq_case_4(vint8mf2_t v1, size_t vl) {
+  return __riscv_vmseq_vv_i8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmseq_case_5(vint8mf4_t v1, size_t vl) {
+  return __riscv_vmseq_vv_i8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmseq_case_6(vint8mf8_t v1, size_t vl) {
+  return __riscv_vmseq_vv_i8mf8_b64(v1, v1, vl);
+}
+
+vbool1_t test_shortcut_for_riscv_vmsne_case_0(vint8m8_t v1, size_t vl) {
+  return __riscv_vmsne_vv_i8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmsne_case_1(vint8m4_t v1, size_t vl) {
+  return __riscv_vmsne_vv_i8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmsne_case_2(vint8m2_t v1, size_t vl) {
+  return __riscv_vmsne_vv_i8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmsne_case_3(vint8m1_t v1, size_t vl) {
+  return __riscv_vmsne_vv_i8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmsne_case_4(vint8mf2_t v1, size_t vl) {
+  return __riscv_vmsne_vv_i8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmsne_case_5(vint8mf4_t v1, size_t vl) {
+  return __riscv_vmsne_vv_i8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmsne_case_6(vint8mf8_t v1, size_t vl) {
+  return __riscv_vmsne_vv_i8mf8_b64(v1, v1, vl);
+}
+
+vbool1_t test_shortcut_for_riscv_vmslt_case_0(vint8m8_t v1, size_t vl) {
+  return __riscv_vmslt_vv_i8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmslt_case_1(vint8m4_t v1, size_t vl) {
+  return __riscv_vmslt_vv_i8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmslt_case_2(vint8m2_t v1, size_t vl) {
+  return __riscv_vmslt_vv_i8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmslt_case_3(vint8m1_t v1, size_t vl) {
+  return __riscv_vmslt_vv_i8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmslt_case_4(vint8mf2_t v1, size_t vl) {
+  return __riscv_vmslt_vv_i8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmslt_case_5(vint8mf4_t v1, size_t vl) {
+  return __riscv_vmslt_vv_i8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmslt_case_6(vint8mf8_t v1, size_t vl) {
+  return __riscv_vmslt_vv_i8mf8_b64(v1, v1, vl);
+}
+
+vbool1_t test_shortcut_for_riscv_vmsltu_case_0(vuint8m8_t v1, size_t vl) {
+  return __riscv_vmsltu_vv_u8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmsltu_case_1(vuint8m4_t v1, size_t vl) {
+  return __riscv_vmsltu_vv_u8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmsltu_case_2(vuint8m2_t v1, size_t vl) {
+  return __riscv_vmsltu_vv_u8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmsltu_case_3(vuint8m1_t v1, size_t vl) {
+  return __riscv_vmsltu_vv_u8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmsltu_case_4(vuint8mf2_t v1, size_t vl) {
+  return __riscv_vmsltu_vv_u8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmsltu_case_5(vuint8mf4_t v1, size_t vl) {
+  return __riscv_vmsltu_vv_u8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmsltu_case_6(vuint8mf8_t v1, size_t vl) {
+  return __riscv_vmsltu_vv_u8mf8_b64(v1, v1, vl);
+}
+
+vbool1_t test_shortcut_for_riscv_vmsle_case_0(vint8m8_t v1, size_t vl) {
+  return __riscv_vmsle_vv_i8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmsle_case_1(vint8m4_t v1, size_t vl) {
+  return __riscv_vmsle_vv_i8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmsle_case_2(vint8m2_t v1, size_t vl) {
+  return __riscv_vmsle_vv_i8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmsle_case_3(vint8m1_t v1, size_t vl) {
+  return __riscv_vmsle_vv_i8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmsle_case_4(vint8mf2_t v1, size_t vl) {
+  return __riscv_vmsle_vv_i8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmsle_case_5(vint8mf4_t v1, size_t vl) {
+  return __riscv_vmsle_vv_i8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmsle_case_6(vint8mf8_t v1, size_t vl) {
+  return __riscv_vmsle_vv_i8mf8_b64(v1, v1, vl);
+}
+
+vbool1_t test_shortcut_for_riscv_vmsleu_case_0(vuint8m8_t v1, size_t vl) {
+  return __riscv_vmsleu_vv_u8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmsleu_case_1(vuint8m4_t v1, size_t vl) {
+  return __riscv_vmsleu_vv_u8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmsleu_case_2(vuint8m2_t v1, size_t vl) {
+  return __riscv_vmsleu_vv_u8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmsleu_case_3(vuint8m1_t v1, size_t vl) {
+  return __riscv_vmsleu_vv_u8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmsleu_case_4(vuint8mf2_t v1, size_t vl) {
+  return __riscv_vmsleu_vv_u8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmsleu_case_5(vuint8mf4_t v1, size_t vl) {
+  return __riscv_vmsleu_vv_u8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmsleu_case_6(vuint8mf8_t v1, size_t vl) {
+  return __riscv_vmsleu_vv_u8mf8_b64(v1, v1, vl);
+}
+
+vbool1_t test_shortcut_for_riscv_vmsgt_case_0(vint8m8_t v1, size_t vl) {
+  return __riscv_vmsgt_vv_i8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmsgt_case_1(vint8m4_t v1, size_t vl) {
+  return __riscv_vmsgt_vv_i8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmsgt_case_2(vint8m2_t v1, size_t vl) {
+  return __riscv_vmsgt_vv_i8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmsgt_case_3(vint8m1_t v1, size_t vl) {
+  return __riscv_vmsgt_vv_i8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmsgt_case_4(vint8mf2_t v1, size_t vl) {
+  return __riscv_vmsgt_vv_i8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmsgt_case_5(vint8mf4_t v1, size_t vl) {
+  return __riscv_vmsgt_vv_i8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmsgt_case_6(vint8mf8_t v1, size_t vl) {
+  return __riscv_vmsgt_vv_i8mf8_b64(v1, v1, vl);
+}
+
+vbool1_t test_shortcut_for_riscv_vmsgtu_case_0(vuint8m8_t v1, size_t vl) {
+  return __riscv_vmsgtu_vv_u8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmsgtu_case_1(vuint8m4_t v1, size_t vl) {
+  return __riscv_vmsgtu_vv_u8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmsgtu_case_2(vuint8m2_t v1, size_t vl) {
+  return __riscv_vmsgtu_vv_u8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmsgtu_case_3(vuint8m1_t v1, size_t vl) {
+  return __riscv_vmsgtu_vv_u8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmsgtu_case_4(vuint8mf2_t v1, size_t vl) {
+  return __riscv_vmsgtu_vv_u8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmsgtu_case_5(vuint8mf4_t v1, size_t vl) {
+  return __riscv_vmsgtu_vv_u8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmsgtu_case_6(vuint8mf8_t v1, size_t vl) {
+  return __riscv_vmsgtu_vv_u8mf8_b64(v1, v1, vl);
+}
+
+vbool1_t test_shortcut_for_riscv_vmsge_case_0(vint8m8_t v1, size_t vl) {
+  return __riscv_vmsge_vv_i8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmsge_case_1(vint8m4_t v1, size_t vl) {
+  return __riscv_vmsge_vv_i8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmsge_case_2(vint8m2_t v1, size_t vl) {
+  return __riscv_vmsge_vv_i8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmsge_case_3(vint8m1_t v1, size_t vl) {
+  return __riscv_vmsge_vv_i8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmsge_case_4(vint8mf2_t v1, size_t vl) {
+  return __riscv_vmsge_vv_i8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmsge_case_5(vint8mf4_t v1, size_t vl) {
+  return __riscv_vmsge_vv_i8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmsge_case_6(vint8mf8_t v1, size_t vl) {
+  return __riscv_vmsge_vv_i8mf8_b64(v1, v1, vl);
+}
+
+vbool1_t test_shortcut_for_riscv_vmsgeu_case_0(vuint8m8_t v1, size_t vl) {
+  return __riscv_vmsgeu_vv_u8m8_b1(v1, v1, vl);
+}
+
+vbool2_t test_shortcut_for_riscv_vmsgeu_case_1(vuint8m4_t v1, size_t vl) {
+  return __riscv_vmsgeu_vv_u8m4_b2(v1, v1, vl);
+}
+
+vbool4_t test_shortcut_for_riscv_vmsgeu_case_2(vuint8m2_t v1, size_t vl) {
+  return __riscv_vmsgeu_vv_u8m2_b4(v1, v1, vl);
+}
+
+vbool8_t test_shortcut_for_riscv_vmsgeu_case_3(vuint8m1_t v1, size_t vl) {
+  return __riscv_vmsgeu_vv_u8m1_b8(v1, v1, vl);
+}
+
+vbool16_t test_shortcut_for_riscv_vmsgeu_case_4(vuint8mf2_t v1, size_t vl) {
+  return __riscv_vmsgeu_vv_u8mf2_b16(v1, v1, vl);
+}
+
+vbool32_t test_shortcut_for_riscv_vmsgeu_case_5(vuint8mf4_t v1, size_t vl) {
+  return __riscv_vmsgeu_vv_u8mf4_b32(v1, v1, vl);
+}
+
+vbool64_t test_shortcut_for_riscv_vmsgeu_case_6(vuint8mf8_t v1, size_t vl) {
+  return __riscv_vmsgeu_vv_u8mf8_b64(v1, v1, vl);
+}
+
+/* { dg-final { scan-assembler-times {vmseq\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 7 } } */
+/* { dg-final { scan-assembler-times {vmsle\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 7 } } */
+/* { dg-final { scan-assembler-times {vmsleu\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 7 } } */
+/* { dg-final { scan-assembler-times {vmsge\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 7 } } */
+/* { dg-final { scan-assembler-times {vmsgeu\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 7 } } */
+/* { dg-final { scan-assembler-times {vmclr\.m\s+v[0-9]+} 35 } } */