[PATCH V2] VECT: Support loop len control on EXTRACT_LAST vectorization

[juzhe.zhong@rivai.ai]

From: Ju-Zhe Zhong <juzhe.zhong@rivai.ai>

Hi, Richard and Richi.

This patch add support live vectorization by VEC_EXTRACT for LEN loop control.

Consider this following case:

#include <stdint.h>

#define EXTRACT_LAST(TYPE)			\
  TYPE __attribute__ ((noinline, noclone))	\
  test_##TYPE (TYPE *x, int n, TYPE value)	\
  {						\
    TYPE last;					\
    for (int j = 0; j < n; ++j)			\
      {						\
	last = x[j];				\
	x[j] = last * value;			\
      }						\
    return last;				\
  }

#define TEST_ALL(T)				\
  T (uint8_t)					\

TEST_ALL (EXTRACT_LAST)

ARM SVE IR:

Preheader:
  max_mask_34 = .WHILE_ULT (0, bnd.5_6, { 0, ... });

Loop:
  ...
  # loop_mask_22 = PHI <next_mask_35(4), max_mask_34(3)>
  ...
  vect_last_12.8_23 = .MASK_LOAD (_7, 8B, loop_mask_22);
  vect__4.9_27 = vect_last_12.8_23 * vect_cst__26;
  .MASK_STORE (_7, 8B, loop_mask_22, vect__4.9_27);
  ...
  next_mask_35 = .WHILE_ULT (_1, bnd.5_6, { 0, ... });
  ...

Epilogue:
  _25 = .EXTRACT_LAST (loop_mask_22, vect_last_12.8_23);

For RVV since we prefer len in loop control, after this patch for RVV:

Loop:
  ...
  loop_len_22 = SELECT_VL;
  vect_last_12.8_23 = .MASK_LOAD (_7, 8B, loop_len_22);
  vect__4.9_27 = vect_last_12.8_23 * vect_cst__26;
  .MASK_STORE (_7, 8B, loop_len_22, vect__4.9_27);
  ...

Epilogue:
  _25 = .VEC_EXTRACT (loop_len_22 - 1 - bias, vect_last_12.8_23);

Details of this approach:

1. Step 1 - Add 'vect_can_vectorize_extract_last_with_len_p'  to enable live vectorization
            for LEN loop control.
   
   This function we check whether target support:
    - Use LEN as the loop control.
    - Support VEC_EXTRACT optab.

2. Step 2 - Record LEN for loop control if 'vect_can_vectorize_extract_last_with_len_p' is true.

3. Step 3 - Gerenate VEC_EXTRACT (v, LEN - 1 - BIAS).

NOTE: This patch set 'vinfo->any_known_not_updated_vssa = true;' since the original STMT is a simple
      assignment wheras VEC_EXTRACT is neither pure nor const function according to internal-fn.def:

      DEF_INTERNAL_OPTAB_FN (VEC_EXTRACT, 0, vec_extract, vec_extract)

      If we don't set 'vinfo->any_known_not_updated_vssa' as true, it will cause ICE in:

        if (need_ssa_update_p (cfun))
          {
            gcc_assert (loop_vinfo->any_known_not_updated_vssa);  ----> Report assertion fail here.
            fun->gimple_df->ssa_renaming_needed = false;
            todo |= TODO_update_ssa_only_virtuals;
          }
      
      I saw there are 2 places set 'vinfo->any_known_not_updated_vssa' as true:
        
	- The one is in 'vectorizable_simd_clone_call':

	/* When the original call is pure or const but the SIMD ABI dictates
	 an aggregate return we will have to use a virtual definition and
	 in a loop eventually even need to add a virtual PHI.  That's
	 not straight-forward so allow to fix this up via renaming.  */
      if (gimple_call_lhs (stmt)
	  && !gimple_vdef (stmt)
	  && TREE_CODE (TREE_TYPE (TREE_TYPE (bestn->decl))) == ARRAY_TYPE)
	vinfo->any_known_not_updated_vssa = true;
       
       - The other is in 'vectorizable_load':
       
        if (memory_access_type == VMAT_LOAD_STORE_LANES)
	  vinfo->any_known_not_updated_vssa = true;

      It seems that they are the same reason as me doing in 'vectorizable_live_operation'.
      Feel free to correct me if I am wrong.

      Bootstrap and Regression on X86 passed.
	
gcc/ChangeLog:

        * tree-vect-loop.cc (vect_can_vectorize_extract_last_with_len_p): New function.
        (vectorizable_live_operation): Add loop LEN control.

---
 gcc/tree-vect-loop.cc | 74 +++++++++++++++++++++++++++++++++++++++----
 1 file changed, 68 insertions(+), 6 deletions(-)

diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index 00058c3c13e..208918f53fb 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -8964,6 +8964,24 @@ vect_can_vectorize_without_simd_p (code_helper code)
 	  && vect_can_vectorize_without_simd_p (tree_code (code)));
 }
 
+/* Return true if target supports extract last vectorization with LEN.  */
+
+static bool
+vect_can_vectorize_extract_last_with_len_p (tree vectype)
+{
+  /* Return false if target doesn't support LEN in loop control.  */
+  machine_mode vmode;
+  if (!get_len_load_store_mode (TYPE_MODE (vectype), true).exists (&vmode)
+      || !get_len_load_store_mode (TYPE_MODE (vectype), false).exists (&vmode))
+    return false;
+
+  /* Target need to support VEC_EXTRACT to extract the last active element.  */
+  return convert_optab_handler (vec_extract_optab,
+				TYPE_MODE (vectype),
+				TYPE_MODE (TREE_TYPE (vectype)))
+	 != CODE_FOR_nothing;
+}
+
 /* Create vector init for vectorized iv.  */
 static tree
 vect_create_nonlinear_iv_init (gimple_seq* stmts, tree init_expr,
@@ -10282,7 +10300,8 @@ vectorizable_live_operation (vec_info *vinfo,
       if (loop_vinfo && LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo))
 	{
 	  if (!direct_internal_fn_supported_p (IFN_EXTRACT_LAST, vectype,
-					       OPTIMIZE_FOR_SPEED))
+					       OPTIMIZE_FOR_SPEED)
+	      && !vect_can_vectorize_extract_last_with_len_p (vectype))
 	    {
 	      if (dump_enabled_p ())
 		dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
@@ -10311,9 +10330,14 @@ vectorizable_live_operation (vec_info *vinfo,
 	  else
 	    {
 	      gcc_assert (ncopies == 1 && !slp_node);
-	      vect_record_loop_mask (loop_vinfo,
-				     &LOOP_VINFO_MASKS (loop_vinfo),
-				     1, vectype, NULL);
+	      if (vect_can_vectorize_extract_last_with_len_p (vectype))
+		vect_record_loop_len (loop_vinfo,
+				      &LOOP_VINFO_LENS (loop_vinfo),
+				      1, vectype, 1);
+	      else
+		vect_record_loop_mask (loop_vinfo,
+				       &LOOP_VINFO_MASKS (loop_vinfo),
+				       1, vectype, NULL);
 	    }
 	}
       /* ???  Enable for loop costing as well.  */
@@ -10339,7 +10363,9 @@ vectorizable_live_operation (vec_info *vinfo,
   gimple *vec_stmt;
   if (slp_node)
     {
-      gcc_assert (!loop_vinfo || !LOOP_VINFO_FULLY_MASKED_P (loop_vinfo));
+      gcc_assert (!loop_vinfo
+		  || (!LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)
+		      && !LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo)));
 
       /* Get the correct slp vectorized stmt.  */
       vec_lhs = SLP_TREE_VEC_DEFS (slp_node)[vec_entry];
@@ -10383,7 +10409,43 @@ vectorizable_live_operation (vec_info *vinfo,
 
       gimple_seq stmts = NULL;
       tree new_tree;
-      if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo))
+      if (LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo))
+	{
+	  /* Emit:
+
+	       SCALAR_RES = VEC_EXTRACT <VEC_LHS, LEN - BIAS - 1>
+
+	     where VEC_LHS is the vectorized live-out result and MASK is
+	     the loop mask for the final iteration.  */
+	  gcc_assert (ncopies == 1 && !slp_node);
+	  tree scalar_type = TREE_TYPE (STMT_VINFO_VECTYPE (stmt_info));
+	  tree len
+	    = vect_get_loop_len (loop_vinfo, gsi, &LOOP_VINFO_LENS (loop_vinfo),
+				 1, vectype, 0, 0);
+
+	  /* BIAS + 1.  */
+	  signed char biasval = LOOP_VINFO_PARTIAL_LOAD_STORE_BIAS (loop_vinfo);
+	  tree bias_one
+	    = size_binop (PLUS_EXPR, build_int_cst (TREE_TYPE (len), biasval),
+			  build_one_cst (TREE_TYPE (len)));
+
+	  /* LAST_INDEX = LEN - (BIAS + 1).  */
+	  tree last_index
+	    = gimple_build (&stmts, MINUS_EXPR, TREE_TYPE (len), len, bias_one);
+
+	  tree scalar_res = gimple_build (&stmts, CFN_VEC_EXTRACT, scalar_type,
+					  vec_lhs_phi, last_index);
+
+	  /* Convert the extracted vector element to the scalar type.  */
+	  new_tree = gimple_convert (&stmts, lhs_type, scalar_res);
+	  /* When the original stmt is an assignment but VEC_EXTRACT is not pure
+	     or const since it may return a memory result.  We will have to use
+	     a virtual definition and in a loop eventually even need to add a
+	     virtual PHI. That's not straight-forward so allow to fix this up
+	     via renaming.  */
+	  vinfo->any_known_not_updated_vssa = true;
+	}
+      else if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo))
 	{
 	  /* Emit:
 
-- 
2.36.3