Re: Re: [PATCH] Middle-end: Fix bug of induction variable vectorization for RVV

[钟居哲 <juzhe.zhong@rivai.ai>]

[-- Attachment #1: Type: text/plain, Size: 8619 bytes --]

Hi, Richard.

>> I think it would be better to split out building a tree from VF from both
>> arms and avoid using 'vf' when LOOP_VINFO_USING_SELECT_VL_P.

I am trying to split out building tree from both arms as you suggested..
Could you take a look the following codes ?

diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
index 8abc1937d74..24a86187d11 100644
--- a/gcc/tree-vect-loop.cc
+++ b/gcc/tree-vect-loop.cc
@@ -10315,19 +10315,47 @@ vectorizable_induction (loop_vec_info loop_vinfo,
       /* iv_loop is the loop to be vectorized. Generate:
    vec_step = [VF*S, VF*S, VF*S, VF*S]  */
       gimple_seq seq = NULL;
-      if (SCALAR_FLOAT_TYPE_P (TREE_TYPE (step_expr)))
+      if (LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo))
  {
-   expr = build_int_cst (integer_type_node, vf);
-   expr = gimple_build (&seq, FLOAT_EXPR, TREE_TYPE (step_expr), expr);
+   /* When we're using loop_len produced by SELEC_VL, the non-final
+      iterations are not always processing VF elements.  So vectorize
+      induction variable instead of
+
+        _21 = vect_vec_iv_.6_22 + { VF, ... };
+
+      We should generate:
+
+       _35 = .SELECT_VL (ivtmp_33, VF);
+       vect_cst__22 = [vec_duplicate_expr] _35;
+       _21 = vect_vec_iv_.6_22 + vect_cst__22;  */
+   vec_loop_lens *lens = &LOOP_VINFO_LENS (loop_vinfo);
+   tree len
+     = vect_get_loop_len (loop_vinfo, NULL, lens, 1, vectype, 0, 0);
+   expr = force_gimple_operand (fold_convert (TREE_TYPE (step_expr),
+      unshare_expr (len)),
+        &seq, true, NULL_TREE);
  }
       else
- expr = build_int_cst (TREE_TYPE (step_expr), vf);
+ {
+   bool float_p = SCALAR_FLOAT_TYPE_P (TREE_TYPE (step_expr));
+   expr = build_int_cst (float_p ? integer_type_node
+ : TREE_TYPE (step_expr),
+ vf);
+   if (float_p)
+     expr = gimple_build (&seq, FLOAT_EXPR, TREE_TYPE (step_expr), expr);
+ }
+
       new_name = gimple_build (&seq, MULT_EXPR, TREE_TYPE (step_expr),
         expr, step_expr);
       if (seq)
  {
-   new_bb = gsi_insert_seq_on_edge_immediate (pe, seq);
-   gcc_assert (!new_bb);
+   if (LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo))
+     gsi_insert_seq_before (&si, seq, GSI_SAME_STMT);
+   else
+     {
+       new_bb = gsi_insert_seq_on_edge_immediate (pe, seq);
+       gcc_assert (!new_bb);
+     }
  }
     }
 
@@ -10335,9 +10363,9 @@ vectorizable_induction (loop_vec_info loop_vinfo,
   gcc_assert (CONSTANT_CLASS_P (new_name)
        || TREE_CODE (new_name) == SSA_NAME);
   new_vec = build_vector_from_val (step_vectype, t);
-  vec_step = vect_init_vector (loop_vinfo, stmt_info,
-        new_vec, step_vectype, NULL);
-
+  vec_step
+    = vect_init_vector (loop_vinfo, stmt_info, new_vec, step_vectype,
+ LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) ? &si : NULL);

Thanks.


juzhe.zhong@rivai.ai
 
From: Richard Biener
Date: 2023-11-09 20:16
To: Juzhe-Zhong
CC: gcc-patches; richard.sandiford; rguenther; kito.cheng; kito.cheng
Subject: Re: [PATCH] Middle-end: Fix bug of induction variable vectorization for RVV
On Wed, Nov 8, 2023 at 11:53 AM Juzhe-Zhong <juzhe.zhong@rivai.ai> wrote:
>
> PR: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=112438
>
> SELECT_VL result is not necessary always VF in non-final iteration.
>
> Current GIMPLE IR is wrong:
>
> # vect_vec_iv_.21_25 = PHI <_24(4), { 0, 1, 2, ... }(3)>
> ...
> _24 = vect_vec_iv_.21_25 + { POLY_INT_CST [4, 4], ... };
>
> After this patch which is correct for SELECT_VL:
>
> # vect_vec_iv_.8_22 = PHI <_21(4), { 0, 1, 2, ... }(3)>
> ...
> _35 = .SELECT_VL (ivtmp_33, POLY_INT_CST [4, 4]);
> _21 = vect_vec_iv_.8_22 + { POLY_INT_CST [4, 4], ... };
>
> kito, could you give more explanation ?
>
>         PR middle/112438
>
> gcc/ChangeLog:
>
>         * tree-vect-loop.cc (vectorizable_induction): Fix bug.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.target/riscv/rvv/autovec/pr112438.c: New test.
>
> ---
>  .../gcc.target/riscv/rvv/autovec/pr112438.c   | 35 +++++++++++++++++
>  gcc/tree-vect-loop.cc                         | 39 +++++++++++++++----
>  2 files changed, 67 insertions(+), 7 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/autovec/pr112438.c
>
> diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr112438.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr112438.c
> new file mode 100644
> index 00000000000..b326d56a52c
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/pr112438.c
> @@ -0,0 +1,35 @@
> +/* { dg-do compile } */
> +/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -fno-vect-cost-model -ffast-math -fdump-tree-optimized-details" } */
> +
> +void
> +foo (int n, int *__restrict in, int *__restrict out)
> +{
> +  for (int i = 0; i < n; i += 1)
> +    {
> +      out[i] = in[i] + i;
> +    }
> +}
> +
> +void
> +foo2 (int n, float * __restrict in,
> +float * __restrict out)
> +{
> +  for (int i = 0; i < n; i += 1)
> +    {
> +      out[i] = in[i] + i;
> +    }
> +}
> +
> +void
> +foo3 (int n, float * __restrict in,
> +float * __restrict out, float x)
> +{
> +  for (int i = 0; i < n; i += 1)
> +    {
> +      out[i] = in[i] + i* i;
> +    }
> +}
> +
> +/* We don't want to see vect_vec_iv_.21_25 + { POLY_INT_CST [4, 4], ... }.  */
> +/* { dg-final { scan-tree-dump-not "\\+ \{ POLY_INT_CST" "optimized" } } */
> +
> diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
> index a544bc9b059..3e103946168 100644
> --- a/gcc/tree-vect-loop.cc
> +++ b/gcc/tree-vect-loop.cc
> @@ -10309,10 +10309,30 @@ vectorizable_induction (loop_vec_info loop_vinfo,
>      new_name = step_expr;
>    else
>      {
> +      gimple_seq seq = NULL;
> +      if (LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo))
> +       {
> +         /* When we're using loop_len produced by SELEC_VL, the non-final
> +            iterations are not always processing VF elements.  So vectorize
> +            induction variable instead of
> +
> +              _21 = vect_vec_iv_.6_22 + { VF, ... };
> +
> +            We should generate:
> +
> +              _35 = .SELECT_VL (ivtmp_33, VF);
> +              vect_cst__22 = [vec_duplicate_expr] _35;
> +              _21 = vect_vec_iv_.6_22 + vect_cst__22;  */
> +         vec_loop_lens *lens = &LOOP_VINFO_LENS (loop_vinfo);
> +         tree len
> +           = vect_get_loop_len (loop_vinfo, NULL, lens, 1, vectype, 0, 0);
> +         expr = force_gimple_operand (fold_convert (TREE_TYPE (step_expr),
> +                                                    unshare_expr (len)),
> +                                      &seq, true, NULL_TREE);
> +       }
 
I think it would be better to split out building a tree from VF from both
arms and avoid using 'vf' when LOOP_VINFO_USING_SELECT_VL_P.
 
Btw, you are not patching the SLP path here which I believe has the same
problem but is currently exempt from non-constant VF at least.
 
Richard.
 
>        /* iv_loop is the loop to be vectorized. Generate:
>           vec_step = [VF*S, VF*S, VF*S, VF*S]  */
> -      gimple_seq seq = NULL;
> -      if (SCALAR_FLOAT_TYPE_P (TREE_TYPE (step_expr)))
> +      else if (SCALAR_FLOAT_TYPE_P (TREE_TYPE (step_expr)))
>         {
>           expr = build_int_cst (integer_type_node, vf);
>           expr = gimple_build (&seq, FLOAT_EXPR, TREE_TYPE (step_expr), expr);
> @@ -10323,8 +10343,13 @@ vectorizable_induction (loop_vec_info loop_vinfo,
>                                expr, step_expr);
>        if (seq)
>         {
> -         new_bb = gsi_insert_seq_on_edge_immediate (pe, seq);
> -         gcc_assert (!new_bb);
> +         if (LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo))
> +           gsi_insert_seq_before (&si, seq, GSI_SAME_STMT);
> +         else
> +           {
> +             new_bb = gsi_insert_seq_on_edge_immediate (pe, seq);
> +             gcc_assert (!new_bb);
> +           }
>         }
>      }
>
> @@ -10332,9 +10357,9 @@ vectorizable_induction (loop_vec_info loop_vinfo,
>    gcc_assert (CONSTANT_CLASS_P (new_name)
>               || TREE_CODE (new_name) == SSA_NAME);
>    new_vec = build_vector_from_val (step_vectype, t);
> -  vec_step = vect_init_vector (loop_vinfo, stmt_info,
> -                              new_vec, step_vectype, NULL);
> -
> +  vec_step
> +    = vect_init_vector (loop_vinfo, stmt_info, new_vec, step_vectype,
> +                       LOOP_VINFO_USING_SELECT_VL_P (loop_vinfo) ? &si : NULL);
>
>    /* Create the following def-use cycle:
>       loop prolog:
> --
> 2.36.3
>