RISC-V: Tweak generic vector COST model

Notice current generic vector cost model make PR112387 failed to vectorize.

Adapt it same as ARM SVE generic vector cost model which can fix it.

Committed as it is obvious fix.

	PR target/112387

gcc/ChangeLog:

	* config/riscv/riscv.cc: Adapt generic cost model same ARM SVE.

gcc/testsuite/ChangeLog:

	* gcc.dg/vect/costmodel/riscv/rvv/pr112387.c: Moved to...
	* gcc.dg/vect/costmodel/riscv/rvv/pr112387-1.c: ...here.
	* gcc.dg/vect/costmodel/riscv/rvv/pr112387-2.c: New test.

gcc/config/riscv/riscv.cc

@@ -355,13 +355,13 @@ static const common_vector_cost generic_vls_vector_cost = {
   1, /* fp_stmt_cost  */
   1, /* gather_load_cost  */
   1, /* scatter_store_cost  */
-  1, /* vec_to_scalar_cost  */
+  2, /* vec_to_scalar_cost  */
   1, /* scalar_to_vec_cost  */
-  1, /* permute_cost  */
-  3, /* align_load_cost  */
-  3, /* align_store_cost  */
-  3, /* unalign_load_cost  */
-  3, /* unalign_store_cost  */
+  2, /* permute_cost  */
+  1, /* align_load_cost  */
+  1, /* align_store_cost  */
+  1, /* unalign_load_cost  */
+  1, /* unalign_store_cost  */
 };
 
 /* Generic costs for VLA vector operations.  */
@@ -371,13 +371,13 @@ static const scalable_vector_cost generic_vla_vector_cost = {
     1, /* fp_stmt_cost  */
     1, /* gather_load_cost  */
     1, /* scatter_store_cost  */
-    1, /* vec_to_scalar_cost  */
+    2, /* vec_to_scalar_cost  */
     1, /* scalar_to_vec_cost  */
-    1, /* permute_cost  */
-    3, /* align_load_cost  */
-    3, /* align_store_cost  */
-    3, /* unalign_load_cost  */
-    3, /* unalign_store_cost  */
+    2, /* permute_cost  */
+    1, /* align_load_cost  */
+    1, /* align_store_cost  */
+    1, /* unalign_load_cost  */
+    1, /* unalign_store_cost  */
   },
 };
 

gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr112387-2.c

@@ -0,0 +1,19 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -mtune=generic-ooo -O3 -ftree-vectorize -fdump-tree-vect-details" } */
+
+#include <stdint-gcc.h>
+
+void
+f2 (uint64_t *__restrict y, uint64_t *__restrict x,
+    uint64_t *__restrict indices, uint64_t n)
+{
+  for (int64_t i = 0; i < n; ++i)
+    {
+      y[i * 2] = x[indices[i * 2]] + 1;
+      y[i * 2 + 1] = x[indices[i * 2 + 1]] + 2;
+    }
+}
+
+/* { dg-final { scan-tree-dump "Loop contains only SLP stmts" vect } } */
+/* { dg-final { scan-assembler-not "vlseg" } } */
+/* { dg-final { scan-assembler-not "vsseg" } } */