RISC-V: Allow LICM hoist POLY_INT configuration code sequence

Realize in recent benchmark evaluation (coremark-pro zip-test):

        vid.v   v2
        vmv.v.i v5,0
.L9:
        vle16.v v3,0(a4)
        vrsub.vx        v4,v2,a6   ---> LICM failed to hoist it outside the loop.

The root cause is:

(insn 56 47 57 4 (set (subreg:DI (reg:HI 220) 0)
        (reg:DI 223)) "rvv.c":11:9 208 {*movdi_64bit}  -> Its result used by the following vrsub.vx then supress the hoist of the vrsub.vx
     (nil))

(insn 57 56 59 4 (set (reg:RVVMF2HI 216)
        (if_then_else:RVVMF2HI (unspec:RVVMF32BI [
                    (const_vector:RVVMF32BI repeat [
                            (const_int 1 [0x1])
                        ])
                    (reg:DI 350)
                    (const_int 2 [0x2]) repeated x2
                    (const_int 1 [0x1])
                    (reg:SI 66 vl)
                    (reg:SI 67 vtype)
                ] UNSPEC_VPREDICATE)
            (minus:RVVMF2HI (vec_duplicate:RVVMF2HI (reg:HI 220))
                (reg:RVVMF2HI 217))
            (unspec:RVVMF2HI [
                    (reg:DI 0 zero)
                ] UNSPEC_VUNDEF))) "rvv.c":11:9 6938 {pred_subrvvmf2hi_reverse_scalar}
     (expr_list:REG_DEAD (reg:HI 220)
        (nil)))

This patch fixes it generate (set (reg:HI) (subreg:HI (reg:DI))) instead of (set (subreg:DI (reg:DI)) (reg:DI)).

After this patch:

	vid.v	v2
	vrsub.vx	v2,v2,a7
	vmv.v.i	v4,0
.L3:
	vle16.v	v3,0(a4)

Tested on both RV32 and RV64 no regression.

gcc/ChangeLog:

	* config/riscv/riscv.cc (riscv_legitimize_move): Fix poly_int dest generation.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/poly_licm-1.c: New test.
	* gcc.target/riscv/rvv/autovec/poly_licm-2.c: New test.

3 files changed, 50 insertions, 4 deletions

diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index d7cdd71..3230fe1 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -2728,16 +2728,17 @@ riscv_legitimize_move (machine_mode mode, rtx dest, rtx src)
 				    (const_poly_int:HI [m, n])
 				    (const_poly_int:SI [m, n]).  */
 	  rtx tmp = gen_reg_rtx (Pmode);
-	  riscv_legitimize_poly_move (Pmode, gen_lowpart (Pmode, dest), tmp,
-				      src);
+	  rtx tmp2 = gen_reg_rtx (Pmode);
+	  riscv_legitimize_poly_move (Pmode, tmp2, tmp, src);
+	  emit_move_insn (dest, gen_lowpart (mode, tmp2));
 	}
       else
 	{
 	  /* In RV32 system, handle (const_poly_int:SI [m, n])
 				    (const_poly_int:DI [m, n]).
 	     In RV64 system, handle (const_poly_int:DI [m, n]).
-       FIXME: Maybe we could gen SImode in RV32 and then sign-extend to DImode,
-       the offset should not exceed 4GiB in general.  */
+	     FIXME: Maybe we could gen SImode in RV32 and then sign-extend to
+	     DImode, the offset should not exceed 4GiB in general.  */
 	  rtx tmp = gen_reg_rtx (mode);
 	  riscv_legitimize_poly_move (mode, dest, tmp, src);
 	}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/poly_licm-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/poly_licm-1.c
new file mode 100644
index 0000000..b7da65f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/poly_licm-1.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -fno-schedule-insns -fno-schedule-insns2" } */
+
+extern int wsize;
+
+typedef unsigned short Posf;
+#define NIL 0
+
+void foo (Posf *p)
+{
+  register unsigned n, m;
+  do {
+      m = *--p;
+      *p = (Posf)(m >= wsize ? m-wsize : NIL);
+  } while (--n);
+}
+
+/* { dg-final { scan-assembler-times {vid\.v\s+v[0-9]+\s+addi\s+\s*[a-x0-9]+,\s*[a-x0-9]+,\s*-1\s+vrsub\.vx\s+} 1 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/poly_licm-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/poly_licm-2.c
new file mode 100644
index 0000000..ffb3c63
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/poly_licm-2.c
@@ -0,0 +1,27 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -fno-schedule-insns -fno-schedule-insns2" } */
+
+typedef unsigned short uint16_t;
+
+void AAA (uint16_t *x, uint16_t *y, unsigned wsize, unsigned count)
+{
+  unsigned m = 0, n = count;
+  register uint16_t *p;
+
+  p = x;
+
+  do {
+    m = *--p;
+    *p = (uint16_t)(m >= wsize ? m-wsize : 0);
+  } while (--n);
+
+  n = wsize;
+  p = y;
+
+  do {
+      m = *--p;
+      *p = (uint16_t)(m >= wsize ? m-wsize : 0);
+  } while (--n);
+}
+
+/* { dg-final { scan-assembler-times {vid\.v\s+v[0-9]+\s+vrsub\.vx\s+} 2 } } */