Hi!

On 2023-12-13T08:14:28+0000, Di Zhao OS <dizhao@os.amperecomputing.com> wrote:
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/pr110279-2.c
> @@ -0,0 +1,41 @@
> +/* PR tree-optimization/110279 */
> +/* { dg-do compile } */
> +/* { dg-options "-Ofast --param tree-reassoc-width=4 --param fully-pipelined-fma=1 -fdump-tree-reassoc2-details -fdump-tree-optimized" } */
> +/* { dg-additional-options "-march=armv8.2-a" { target aarch64-*-* } } */
> +
> +#define LOOP_COUNT 800000000
> +typedef double data_e;
> +
> +#include <stdio.h>
> +
> +__attribute_noinline__ data_e
> +foo (data_e in)

Pushed to master branch commit 91e9e8faea4086b3b8aef2355fc12c1559d425f6
"Fix 'gcc.dg/pr110279-2.c' syntax error due to '__attribute_noinline__'",
see attached.

However:

> +{
> +  data_e a1, a2, a3, a4;
> +  data_e tmp, result = 0;
> +  a1 = in + 0.1;
> +  a2 = in * 0.1;
> +  a3 = in + 0.01;
> +  a4 = in * 0.59;
> +
> +  data_e result2 = 0;
> +
> +  for (int ic = 0; ic < LOOP_COUNT; ic++)
> +    {
> +      /* Test that a complete FMA chain with length=4 is not broken.  */
> +      tmp = a1 + a2 * a2 + a3 * a3 + a4 * a4 ;
> +      result += tmp - ic;
> +      result2 = result2 / 2 - tmp;
> +
> +      a1 += 0.91;
> +      a2 += 0.1;
> +      a3 -= 0.01;
> +      a4 -= 0.89;
> +
> +    }
> +
> +  return result + result2;
> +}
> +
> +/* { dg-final { scan-tree-dump-not "was chosen for reassociation" "reassoc2"} } */
> +/* { dg-final { scan-tree-dump-times {\.FMA } 3 "optimized"} } */

..., I still see these latter two tree dump scans FAIL, for GCN:

    $ grep -C2 'was chosen for reassociation' pr110279-2.c.197t.reassoc2
      2 *: a3_40
      2 *: a2_39
    Width = 4 was chosen for reassociation
    Transforming _15 = powmult_1 + powmult_3;
     into _63 = powmult_1 + a1_38;
    $ grep -F .FMA pr110279-2.c.265t.optimized
      _63 = .FMA (a2_39, a2_39, a1_38);
      _64 = .FMA (a3_40, a3_40, powmult_5);

..., nvptx:

    $ grep -C2 'was chosen for reassociation' pr110279-2.c.197t.reassoc2
      2 *: a3_40
      2 *: a2_39
    Width = 4 was chosen for reassociation
    Transforming _15 = powmult_1 + powmult_3;
     into _63 = powmult_1 + a1_38;
    $ grep -F .FMA pr110279-2.c.265t.optimized
      _63 = .FMA (a2_39, a2_39, a1_38);
      _64 = .FMA (a3_40, a3_40, powmult_5);

..., but also x86_64-pc-linux-gnu:

    $  grep -C2 'was chosen for reassociation' pr110279-2.c.197t.reassoc2
      2 *: a3_40
      2 *: a2_39
    Width = 2 was chosen for reassociation
    Transforming _15 = powmult_1 + powmult_3;
     into _63 = powmult_1 + powmult_3;
    $ grep -cF .FMA pr110279-2.c.265t.optimized
    0


Grüße
 Thomas


-----------------
Siemens Electronic Design Automation GmbH; Anschrift: Arnulfstraße 201, 80634 München; Gesellschaft mit beschränkter Haftung; Geschäftsführer: Thomas Heurung, Frank Thürauf; Sitz der Gesellschaft: München; Registergericht München, HRB 106955