RISC-V: Some minior tweak on dynamic LMUL cost model

Tweak some codes of dynamic LMUL cost model to make computation more predictable and accurate.

Tested on both RV32 and RV64 no regression.

Committed.

	PR target/113112

gcc/ChangeLog:

	* config/riscv/riscv-vector-costs.cc (compute_estimated_lmul): Tweak LMUL estimation.
	(has_unexpected_spills_p): Ditto.
	(costs::record_potential_unexpected_spills): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-1.c: Add more checks.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-2.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-3.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-4.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-5.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-6.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-7.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-1.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-2.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-3.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-4.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-5.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-1.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-2.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-3.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-5.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-6.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-7.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-8.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-1.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-10.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-11.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-2.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-3.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-4.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-5.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-6.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-7.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-8.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-9.c: Ditto.
	* gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-12.c: New test.
	* gcc.dg/vect/costmodel/riscv/rvv/pr113112-2.c: New test.

33 files changed, 166 insertions, 15 deletions

diff --git a/gcc/config/riscv/riscv-vector-costs.cc b/gcc/config/riscv/riscv-vector-costs.cc
index 7b837b0..74b8e86 100644
--- a/gcc/config/riscv/riscv-vector-costs.cc
+++ b/gcc/config/riscv/riscv-vector-costs.cc
@@ -394,21 +394,32 @@ compute_estimated_lmul (loop_vec_info loop_vinfo, machine_mode mode)
 {
   gcc_assert (GET_MODE_BITSIZE (mode).is_constant ());
   int regno_alignment = riscv_get_v_regno_alignment (loop_vinfo->vector_mode);
-  if (known_eq (LOOP_VINFO_SLP_UNROLLING_FACTOR (loop_vinfo), 1U))
+  if (riscv_v_ext_vls_mode_p (loop_vinfo->vector_mode))
+    return regno_alignment;
+  else if (known_eq (LOOP_VINFO_SLP_UNROLLING_FACTOR (loop_vinfo), 1U)
+	   || LOOP_VINFO_SLP_UNROLLING_FACTOR (loop_vinfo).is_constant ())
     {
       int estimated_vf = vect_vf_for_cost (loop_vinfo);
       return estimated_vf * GET_MODE_BITSIZE (mode).to_constant ()
 	     / TARGET_MIN_VLEN;
     }
-  else if (regno_alignment > 1)
-    return regno_alignment;
   else
     {
-      int ratio;
-      if (can_div_trunc_p (BYTES_PER_RISCV_VECTOR,
-			   LOOP_VINFO_SLP_UNROLLING_FACTOR (loop_vinfo),
-			   &ratio))
-	return TARGET_MAX_LMUL / ratio;
+      /* Estimate the VLA SLP LMUL.  */
+      if (regno_alignment > RVV_M1)
+	return regno_alignment;
+      else if (mode != QImode)
+	{
+	  int ratio;
+	  if (can_div_trunc_p (BYTES_PER_RISCV_VECTOR,
+			       GET_MODE_SIZE (loop_vinfo->vector_mode), &ratio))
+	    {
+	      if (ratio == 1)
+		return RVV_M4;
+	      else if (ratio == 2)
+		return RVV_M2;
+	    }
+	}
     }
   return 0;
 }
@@ -540,7 +551,10 @@ update_local_live_ranges (
 	  stmt_vec_info stmt_info = vinfo->lookup_stmt (gsi_stmt (si));
 	  enum stmt_vec_info_type type
 	    = STMT_VINFO_TYPE (vect_stmt_to_vectorize (stmt_info));
-	  if (non_contiguous_memory_access_p (stmt_info))
+	  if (non_contiguous_memory_access_p (stmt_info)
+	      /* LOAD_LANES/STORE_LANES doesn't need a perm indice.  */
+	      && STMT_VINFO_MEMORY_ACCESS_TYPE (stmt_info)
+		   != VMAT_LOAD_STORE_LANES)
 	    {
 	      /* For non-adjacent load/store STMT, we will potentially
 		 convert it into:
@@ -578,9 +592,6 @@ update_local_live_ranges (
 static bool
 has_unexpected_spills_p (loop_vec_info loop_vinfo)
 {
-  /* We don't apply dynamic LMUL cost model on VLS modes.  */
-  if (!riscv_v_ext_vector_mode_p (loop_vinfo->vector_mode))
-    return false;
   /* Compute local program points.
      It's a fast and effective computation.  */
   hash_map<basic_block, vec<stmt_point>> program_points_per_bb;
@@ -682,7 +693,12 @@ costs::analyze_loop_vinfo (loop_vec_info loop_vinfo)
 void
 costs::record_potential_unexpected_spills (loop_vec_info loop_vinfo)
 {
-  if (riscv_autovec_lmul == RVV_DYNAMIC)
+  /* We only want to apply the heuristic if LOOP_VINFO is being
+     vectorized for VLA and known NITERS VLS loop.  */
+  if (riscv_autovec_lmul == RVV_DYNAMIC
+      && (m_cost_type == VLA_VECTOR_COST
+	  || (m_cost_type == VLS_VECTOR_COST
+	      && LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo))))
     {
       bool post_dom_available_p = dom_info_available_p (CDI_POST_DOMINATORS);
       if (!post_dom_available_p)
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-1.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-1.c
index 76c47dd..f481c80 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-1.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-1.c
@@ -86,3 +86,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b,    int32_t *__restrict c,
 /* { dg-final { scan-assembler {e32,m1} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 3 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-2.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-2.c
index f2ca677..e044c65 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-2.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-2.c
@@ -58,3 +58,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b,    int32_t *__restrict c,
 /* { dg-final { scan-assembler {e32,m1} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 3 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-3.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-3.c
index 49553a3..212788a 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-3.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-3.c
@@ -86,3 +86,6 @@ foo (int8_t *__restrict a, int8_t *__restrict b,    int8_t *__restrict c,
 /* { dg-final { scan-assembler {e8,m1} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 3 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-4.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-4.c
index 6afbbf8..2e2ff9d 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-4.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-4.c
@@ -116,3 +116,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b,    int32_t *__restrict c,
 /* { dg-final { scan-assembler {e32,m1} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 3 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-5.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-5.c
index 9037187..80eb38c 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-5.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-5.c
@@ -144,3 +144,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b,    int32_t *__restrict c,
 /* { dg-final { scan-assembler {e32,m1} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 3 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-6.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-6.c
index cabb5f5..3dd594e3 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-6.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-6.c
@@ -145,3 +145,6 @@ foo (int8_t *__restrict a, int8_t *__restrict b,    int8_t *__restrict c,
 /* { dg-final { scan-assembler {e8,m1} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 3 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-7.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-7.c
index b3902e2..87b943c 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-7.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul1-7.c
@@ -43,3 +43,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b, int32_t *__restrict c,
 /* { dg-final { scan-assembler {e32,m1} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 3 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-1.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-1.c
index 2145cb8..0079aa0 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-1.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-1.c
@@ -46,3 +46,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b,    int32_t *__restrict c,
 /* { dg-final { scan-assembler {e32,m2} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-2.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-2.c
index a5bf4b6..d8a0e66 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-2.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-2.c
@@ -46,3 +46,6 @@ foo (int8_t *__restrict a, int8_t *__restrict b,    int8_t *__restrict c,
 /* { dg-final { scan-assembler {e8,m2} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-3.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-3.c
index 2145cb8..0079aa0 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-3.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-3.c
@@ -46,3 +46,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b,    int32_t *__restrict c,
 /* { dg-final { scan-assembler {e32,m2} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-4.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-4.c
index 6ed9eea..2326919 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-4.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-4.c
@@ -44,3 +44,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b, int32_t *__restrict c,
 /* { dg-final { scan-assembler {e32,m2} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-5.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-5.c
index 72c1cb4..2ef88a3 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-5.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul2-5.c
@@ -47,3 +47,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b, int32_t *__restrict c,
 /* { dg-final { scan-assembler {e8,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-1.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-1.c
index a87ff67..08dc7ca 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-1.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-1.c
@@ -30,3 +30,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b, int32_t *__restrict c,
 /* { dg-final { scan-assembler {e32,m4} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-2.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-2.c
index 3d7dc92..b9a9229 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-2.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-2.c
@@ -30,3 +30,6 @@ foo (int8_t *__restrict a, int8_t *__restrict b, int8_t *__restrict c,
 /* { dg-final { scan-assembler {e8,m4} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-3.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-3.c
index 09eacca..cd476cb 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-3.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-3.c
@@ -42,3 +42,6 @@ void foo2 (int64_t *__restrict a,
 /* { dg-final { scan-assembler {e64,m4} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-5.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-5.c
index 88f5844..d48a376 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-5.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-5.c
@@ -42,3 +42,6 @@ void foo2 (int16_t *__restrict a,
 /* { dg-final { scan-assembler {e16,m2} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-6.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-6.c
index aa4f4b1..d2766f5 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-6.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-6.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-march=rv32gcv -mabi=ilp32 -O3 -ftree-vectorize --param riscv-autovec-lmul=dynamic -fselective-scheduling -fdump-tree-vect-details" } */
+/* { dg-options "-march=rv32gcv -mabi=ilp32 -O3 -ftree-vectorize --param riscv-autovec-lmul=dynamic --param riscv-autovec-preference=scalable -fselective-scheduling -fdump-tree-vect-details" } */
 
 #include <stdint-gcc.h>
 
@@ -23,3 +23,6 @@ foo (uint8_t *restrict a, uint8_t *restrict b, int n)
 /* { dg-final { scan-assembler-times {csrr} 1 } } */
 /* Since we don't support VLA SLP for LMUL = 8, dynamic LMUL cost model start from LMUL = 4.  */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-not "Maximum lmul = 8" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-7.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-7.c
index 0606320..45bceaa 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-7.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-7.c
@@ -42,3 +42,6 @@ void foo2 (int8_t *__restrict a,
 /* { dg-final { scan-assembler {e64,m4} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-times "Preferring smaller LMUL loop because it has unexpected spills" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-8.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-8.c
index 717cce9..362c49f 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-8.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul4-8.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-march=rv32gcv -mabi=ilp32 -O3 -ftree-vectorize --param riscv-autovec-lmul=dynamic -fselective-scheduling -fdump-tree-vect-details" } */
+/* { dg-options "-march=rv32gcv -mabi=ilp32 -O3 -ftree-vectorize --param riscv-autovec-lmul=dynamic --param riscv-autovec-preference=scalable -fselective-scheduling -fdump-tree-vect-details" } */
 
 #include <stdint-gcc.h>
 
@@ -32,3 +32,6 @@ foo (uint8_t *restrict a, uint8_t *restrict b, int n)
 /* { dg-final { scan-assembler-times {csrr} 1 } } */
 /* Since we don't support VLA SLP for LMUL = 8, dynamic LMUL cost model start from LMUL = 4.  */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-not "Maximum lmul = 8" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-1.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-1.c
index 7eda6b0..702a3b7 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-1.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-1.c
@@ -13,3 +13,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b, int n)
 /* { dg-final { scan-assembler {e32,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-10.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-10.c
index b0f8f8f..95b0600 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-10.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-10.c
@@ -17,3 +17,6 @@ foo (int *x, int n, int res)
 /* { dg-final { scan-assembler {e32,m8} } } */
 /* { dg-final { scan-assembler-times {csrr} 1 } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-11.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-11.c
index 3b37c89..83df2bc 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-11.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-11.c
@@ -42,3 +42,6 @@ void foo2 (int64_t *__restrict a,
 /* { dg-final { scan-assembler {e64,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-12.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-12.c
new file mode 100644
index 0000000..d0f3542
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-12.c
@@ -0,0 +1,25 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv32gcv -mabi=ilp32 -O3 -ftree-vectorize --param riscv-autovec-lmul=dynamic --param riscv-autovec-preference=scalable -fselective-scheduling -fdump-tree-vect-details" } */
+
+void
+foo (int *restrict a, int *restrict b, int n)
+{
+  for (int i = 0; i < n; ++i)
+    {
+      a[i * 8] = b[i * 8 + 7] + 1;
+      a[i * 8 + 1] = b[i * 8 + 6] + 2;
+      a[i * 8 + 2] = b[i * 8 + 5] + 3;
+      a[i * 8 + 3] = b[i * 8 + 4] + 4;
+      a[i * 8 + 4] = b[i * 8 + 3] + 5;
+      a[i * 8 + 5] = b[i * 8 + 2] + 6;
+      a[i * 8 + 6] = b[i * 8 + 1] + 7;
+      a[i * 8 + 7] = b[i * 8 + 0] + 8;
+    }
+}
+
+/* { dg-final { scan-assembler {e32,m8} } } */
+/* { dg-final { scan-assembler-times {csrr} 1 } } */
+/* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-2.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-2.c
index 802a4dd..c3d0d5d 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-2.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-2.c
@@ -13,3 +13,6 @@ foo (int32_t *__restrict a, int16_t *__restrict b, int n)
 /* { dg-final { scan-assembler {e16,m4} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-3.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-3.c
index b55863d..a575427 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-3.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-3.c
@@ -13,3 +13,6 @@ foo (int8_t *__restrict a, int8_t *__restrict b, int n)
 /* { dg-final { scan-assembler {e8,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-4.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-4.c
index faa4428..b55bcad 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-4.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-4.c
@@ -14,3 +14,6 @@ foo (size_t *__restrict a, size_t *__restrict b, int n)
 /* { dg-final { scan-assembler {e64,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-5.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-5.c
index 944c239..307dd69 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-5.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-5.c
@@ -20,3 +20,6 @@ foo (int8_t *__restrict a, int8_t *__restrict b, int n)
 /* { dg-final { scan-assembler {e8,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-6.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-6.c
index 2aeb7df..9a7eb42 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-6.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-6.c
@@ -18,3 +18,6 @@ foo (int8_t *__restrict a, int8_t *__restrict b, int8_t *__restrict a2,
 /* { dg-final { scan-assembler {e8,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-7.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-7.c
index 37757c8..103d22b 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-7.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-7.c
@@ -18,3 +18,6 @@ foo (int32_t *__restrict a, int32_t *__restrict b, int32_t *__restrict a2,
 /* { dg-final { scan-assembler {e32,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-8.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-8.c
index 90ccbf1..0255bdf 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-8.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-8.c
@@ -14,3 +14,6 @@ foo (int8_t *__restrict a, int8_t init, int n)
 /* { dg-final { scan-assembler {e8,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-9.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-9.c
index 7ad5799..e6cc1ad 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-9.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/dynamic-lmul8-9.c
@@ -14,3 +14,6 @@ foo (int64_t *__restrict a, int64_t init, int n)
 /* { dg-final { scan-assembler {e64,m8} } } */
 /* { dg-final { scan-assembler-not {csrr} } } */
 /* { dg-final { scan-tree-dump-not "Preferring smaller LMUL loop because it has unexpected spills" "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 8" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 2" 1 "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113112-2.c b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113112-2.c
new file mode 100644
index 0000000..bc4f40d
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/riscv/rvv/pr113112-2.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize --param riscv-autovec-lmul=dynamic --param riscv-autovec-preference=fixed-vlmax -fdump-tree-vect-details" } */
+
+#define TYPE double
+#define N 200
+
+#include <complex.h>
+
+void addconjboth (_Complex TYPE a[restrict N], _Complex TYPE b[restrict N],
+		  _Complex TYPE c[restrict N])
+{
+#if defined (UNROLL)
+#pragma GCC unroll 16
+#endif
+  for (int i=0; i < N; i++)
+    c[i] = ~a[i] + ~b[i];
+}
+
+/* { dg-final { scan-assembler {e64,m4} } } */
+/* { dg-final { scan-tree-dump-times "Maximum lmul = 4, At most 16 number of live V_REG" 1 "vect" } } */