[gcc(refs/vendors/riscv/heads/gcc-15-with-riscv-opts)] RISC-V: Combine vec_duplicate + vremu.vv to vremu.vx on GR2VR cost

[Jeff Law]

https://gcc.gnu.org/g:3a96680f3a87b3862103976616dbd07da3132173

commit 3a96680f3a87b3862103976616dbd07da3132173
Author: Pan Li <pan2.li@intel.com>
Date:   Mon Jun 9 16:24:34 2025 +0800

    RISC-V: Combine vec_duplicate + vremu.vv to vremu.vx on GR2VR cost
    
    This patch would like to combine the vec_duplicate + vremu.vv to the
    vremu.vx.  From example as below code.  The related pattern will depend
    on the cost of vec_duplicate from GR2VR.  Then the late-combine will
    take action if the cost of GR2VR is zero, and reject the combination
    if the GR2VR cost is greater than zero.
    
    Assume we have example code like below, GR2VR cost is 0.
    
      #define DEF_VX_BINARY(T, OP)                                        \
      void                                                                \
      test_vx_binary (T * restrict out, T * restrict in, T x, unsigned n) \
      {                                                                   \
        for (unsigned i = 0; i < n; i++)                                  \
          out[i] = in[i] OP x;                                            \
      }
    
      DEF_VX_BINARY(int32_t, /)
    
    Before this patch:
      10   │ test_vx_binary_or_int32_t_case_0:
      11   │     beq a3,zero,.L8
      12   │     vsetvli a5,zero,e32,m1,ta,ma
      13   │     vmv.v.x v2,a2
      14   │     slli    a3,a3,32
      15   │     srli    a3,a3,32
      16   │ .L3:
      17   │     vsetvli a5,a3,e32,m1,ta,ma
      18   │     vle32.v v1,0(a1)
      19   │     slli    a4,a5,2
      20   │     sub a3,a3,a5
      21   │     add a1,a1,a4
      22   │     vremu.vv v1,v1,v2
      23   │     vse32.v v1,0(a0)
      24   │     add a0,a0,a4
      25   │     bne a3,zero,.L3
    
    After this patch:
      10   │ test_vx_binary_or_int32_t_case_0:
      11   │     beq a3,zero,.L8
      12   │     slli    a3,a3,32
      13   │     srli    a3,a3,32
      14   │ .L3:
      15   │     vsetvli a5,a3,e32,m1,ta,ma
      16   │     vle32.v v1,0(a1)
      17   │     slli    a4,a5,2
      18   │     sub a3,a3,a5
      19   │     add a1,a1,a4
      20   │     vremu.vx v1,v1,a2
      21   │     vse32.v v1,0(a0)
      22   │     add a0,a0,a4
      23   │     bne a3,zero,.L3
    
    gcc/ChangeLog:
    
            * config/riscv/riscv-v.cc (expand_vx_binary_vec_vec_dup): Add new
            case UMOD.
            * config/riscv/riscv.cc (riscv_rtx_costs): Ditto.
            * config/riscv/vector-iterators.md: Add new op umod.
    
    Signed-off-by: Pan Li <pan2.li@intel.com>
    (cherry picked from commit 85de2b8b58e1644f6d5f0f182426122416b19e6f)

Diff:
---
 gcc/config/riscv/riscv-v.cc          | 1 +
 gcc/config/riscv/riscv.cc            | 1 +
 gcc/config/riscv/vector-iterators.md | 2 +-
 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc
index d969e8c23e15..7bf2598c896d 100644
--- a/gcc/config/riscv/riscv-v.cc
+++ b/gcc/config/riscv/riscv-v.cc
@@ -5611,6 +5611,7 @@ expand_vx_binary_vec_vec_dup (rtx op_0, rtx op_1, rtx op_2,
     case DIV:
     case UDIV:
     case MOD:
+    case UMOD:
       icode = code_for_pred_scalar (code, mode);
       break;
     default:
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index f838988edeb4..271a0b58939c 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -3952,6 +3952,7 @@ riscv_rtx_costs (rtx x, machine_mode mode, int outer_code, int opno ATTRIBUTE_UN
 		    case DIV:
 		    case UDIV:
 		    case MOD:
+		    case UMOD:
 		      *total = get_vector_binary_rtx_cost (op, scalar2vr_cost);
 		      break;
 		    default:
diff --git a/gcc/config/riscv/vector-iterators.md b/gcc/config/riscv/vector-iterators.md
index b1fd607320ef..42fc04c0ad38 100644
--- a/gcc/config/riscv/vector-iterators.md
+++ b/gcc/config/riscv/vector-iterators.md
@@ -4042,7 +4042,7 @@
 ])
 
 (define_code_iterator any_int_binop_no_shift_v_vdup [
-  plus minus and ior xor mult div udiv mod
+  plus minus and ior xor mult div udiv mod umod
 ])
 
 (define_code_iterator any_int_binop_no_shift_vdup_v [