[PATCH V3] RISC-V: Expand VLS mode to scalar mode move[PR111391]

[Juzhe-Zhong <juzhe.zhong@rivai.ai>]

This patch fixes https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111391

I notice that previous patch (V2 patch) cause additional execution fail of pr69719.c
This FAIL is because of the latent BUG of VSETVL PASS.

So this patch includes VSETVL PASS fix even though it's not related to the PR111391.

I have confirm the whole regression no additional FAILs are introduced.

	PR target/111391

gcc/ChangeLog:

	* config/riscv/autovec.md (@vec_extract<mode><vel>): Remove @.
	(vec_extract<mode><vel>): Ditto.
	* config/riscv/riscv-vsetvl.cc (emit_vsetvl_insn): Fix bug.
	(pass_vsetvl::local_eliminate_vsetvl_insn): Ditto.
	* config/riscv/riscv.cc (riscv_legitimize_move): Expand move.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/autovec/partial/slp-9.c: Adapt test.
	* gcc.target/riscv/rvv/autovec/pr111391.c: New test.

---
 gcc/config/riscv/autovec.md                   |  2 +-
 gcc/config/riscv/riscv-vsetvl.cc              |  4 ++-
 gcc/config/riscv/riscv.cc                     | 32 +++++++++++++++++++
 .../riscv/rvv/autovec/partial/slp-9.c         |  1 -
 .../gcc.target/riscv/rvv/autovec/pr111391.c   | 28 ++++++++++++++++
 5 files changed, 64 insertions(+), 3 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/pr111391.c

diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index e74a1695709..7121bab1716 100644
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -1442,7 +1442,7 @@
 ;; -------------------------------------------------------------------------
 ;; ---- [INT,FP] Extract a vector element.
 ;; -------------------------------------------------------------------------
-(define_expand "@vec_extract<mode><vel>"
+(define_expand "vec_extract<mode><vel>"
   [(set (match_operand:<VEL>	  0 "register_operand")
      (vec_select:<VEL>
        (match_operand:V_VLS	  1 "register_operand")
diff --git a/gcc/config/riscv/riscv-vsetvl.cc b/gcc/config/riscv/riscv-vsetvl.cc
index f81361c4ccd..7731e2a5f20 100644
--- a/gcc/config/riscv/riscv-vsetvl.cc
+++ b/gcc/config/riscv/riscv-vsetvl.cc
@@ -649,6 +649,8 @@ emit_vsetvl_insn (enum vsetvl_type insn_type, enum emit_type emit_type,
     {
       fprintf (dump_file, "\nInsert vsetvl insn PATTERN:\n");
       print_rtl_single (dump_file, pat);
+      fprintf (dump_file, "\nfor insn:\n");
+      print_rtl_single (dump_file, rinsn);
     }
 
   if (emit_type == EMIT_DIRECT)
@@ -3861,7 +3863,7 @@ pass_vsetvl::local_eliminate_vsetvl_insn (const bb_info *bb) const
 	      skip_one = true;
 	    }
 
-	  curr_avl = get_avl (rinsn);
+	  curr_avl = curr_dem.get_avl ();
 
 	  /* Some instrucion like pred_extract_first<mode> don't reqruie avl, so
 	     the avl is null, use vl_placeholder for unify the handling
diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index 762937b0e37..3ba6379028f 100644
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -2513,6 +2513,38 @@ riscv_legitimize_move (machine_mode mode, rtx dest, rtx src)
 	}
       return true;
     }
+  /* Expand
+       (set (reg:DI target) (subreg:DI (reg:V8QI reg) 0))
+     Expand this data movement instead of simply forbid it since
+     we can improve the code generation for this following scenario
+     by RVV auto-vectorization:
+       (set (reg:V8QI 149) (vec_duplicate:V8QI (reg:QI))
+       (set (reg:DI target) (subreg:DI (reg:V8QI reg) 0))
+     Since RVV mode and scalar mode are in different REG_CLASS,
+     we need to explicitly move data from V_REGS to GR_REGS by scalar move.  */
+  if (SUBREG_P (src) && riscv_v_ext_mode_p (GET_MODE (SUBREG_REG (src))))
+    {
+      machine_mode vmode = GET_MODE (SUBREG_REG (src));
+      unsigned int mode_size = GET_MODE_SIZE (mode).to_constant ();
+      unsigned int vmode_size = GET_MODE_SIZE (vmode).to_constant ();
+      unsigned int nunits = vmode_size / mode_size;
+      scalar_mode smode = as_a<scalar_mode> (mode);
+      vmode = riscv_vector::get_vector_mode (smode, nunits).require ();
+      enum insn_code icode
+	= convert_optab_handler (vec_extract_optab, vmode, mode);
+      gcc_assert (icode != CODE_FOR_nothing);
+      class expand_operand ops[3];
+      create_output_operand (&ops[0], dest, mode);
+      ops[0].target = 1;
+      create_input_operand (&ops[1], gen_lowpart (vmode, SUBREG_REG (src)),
+			    vmode);
+      unsigned int index = SUBREG_BYTE (src).to_constant () / mode_size;
+      create_integer_operand (&ops[2], index);
+      expand_insn (icode, 3, ops);
+      if (ops[0].value != dest)
+	emit_move_insn (dest, ops[0].value);
+      return true;
+    }
   /* Expand
        (set (reg:QI target) (mem:QI (address)))
      to
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-9.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-9.c
index 5fba27c7a35..7c42438c9d9 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-9.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/partial/slp-9.c
@@ -29,4 +29,3 @@
 TEST_ALL (VEC_PERM)
 
 /* { dg-final { scan-assembler-times {viota.m} 2 } } */
-/* { dg-final { scan-assembler-not {vmv\.v\.i} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr111391.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr111391.c
new file mode 100644
index 00000000000..a7f64c937c6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr111391.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -Wno-int-conversion -Wno-implicit-function -Wno-incompatible-pointer-types -Wno-implicit-function-declaration -Ofast -ftree-vectorize" } */
+
+int d ();
+typedef struct
+{
+  int b;
+} c;
+int
+e (char *f, long g)
+{
+  f += g;
+  while (g--)
+    *--f = d;
+}
+
+int
+d (c * f)
+{
+  while (h ())
+    switch (f->b)
+      case 'Q':
+      {
+	long a;
+	e (&a, sizeof (a));
+	i (a);
+      }
+}
-- 
2.36.3