[gcc r13-1103] aarch64: Revert bogus fix for PR105254

[Richard Sandiford <rsandifo@gcc.gnu.org>]

https://gcc.gnu.org/g:2636660b6f35423e0cfbf53bfad5c5fed6ae6471

commit r13-1103-g2636660b6f35423e0cfbf53bfad5c5fed6ae6471
Author: Richard Sandiford <richard.sandiford@arm.com>
Date:   Wed Jun 15 11:12:51 2022 +0100

    aarch64: Revert bogus fix for PR105254
    
    In f2ebf2d98efe0ac2314b58cf474f44cb8ebd5244 I'd forced the
    chosen unroll factor to be a factor of the VF, in order to
    work around an exact_div ICE in PR105254.  This was completely
    bogus -- clearly I didn't look in enough detail at why we ended
    up with an unrolled VF that wasn't a multiple of the UF.
    
    Kewen has since fixed the bug properly for PR105940, so this
    patch reverts my earlier attempt.  Sorry for the stupidity.
    
    gcc/
            PR tree-optimization/105254
            PR tree-optimization/105940
    
            Revert:
    
            * config/aarch64/aarch64.cc
            (aarch64_vector_costs::determine_suggested_unroll_factor): Take a
            loop_vec_info as argument.  Restrict the unroll factor to values
            that divide the VF.
            (aarch64_vector_costs::finish_cost): Update call accordingly.
    
    gcc/testsuite/
            * gcc.target/aarch64/sve/cost_model_14.c: New test.

Diff:
---
 gcc/config/aarch64/aarch64.cc                        | 12 ++++--------
 gcc/testsuite/gcc.target/aarch64/sve/cost_model_14.c | 13 +++++++++++++
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index d21e041eccb..d049f9a9819 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -15631,7 +15631,7 @@ private:
   unsigned int adjust_body_cost (loop_vec_info, const aarch64_vector_costs *,
 				 unsigned int);
   bool prefer_unrolled_loop () const;
-  unsigned int determine_suggested_unroll_factor (loop_vec_info);
+  unsigned int determine_suggested_unroll_factor ();
 
   /* True if we have performed one-time initialization based on the
      vec_info.  */
@@ -16740,8 +16740,7 @@ adjust_body_cost_sve (const aarch64_vec_op_count *ops,
 }
 
 unsigned int
-aarch64_vector_costs::
-determine_suggested_unroll_factor (loop_vec_info loop_vinfo)
+aarch64_vector_costs::determine_suggested_unroll_factor ()
 {
   bool sve = m_vec_flags & VEC_ANY_SVE;
   /* If we are trying to unroll an Advanced SIMD main loop that contains
@@ -16755,7 +16754,6 @@ determine_suggested_unroll_factor (loop_vec_info loop_vinfo)
     return 1;
 
   unsigned int max_unroll_factor = 1;
-  auto vf = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
   for (auto vec_ops : m_ops)
     {
       aarch64_simd_vec_issue_info const *vec_issue
@@ -16764,8 +16762,7 @@ determine_suggested_unroll_factor (loop_vec_info loop_vinfo)
 	return 1;
       /* Limit unroll factor to a value adjustable by the user, the default
 	 value is 4. */
-      unsigned int unroll_factor = MIN (aarch64_vect_unroll_limit,
-					(int) known_alignment (vf));
+      unsigned int unroll_factor = aarch64_vect_unroll_limit;
       unsigned int factor
        = vec_ops.reduction_latency > 1 ? vec_ops.reduction_latency : 1;
       unsigned int temp;
@@ -16943,8 +16940,7 @@ aarch64_vector_costs::finish_cost (const vector_costs *uncast_scalar_costs)
     {
       m_costs[vect_body] = adjust_body_cost (loop_vinfo, scalar_costs,
 					     m_costs[vect_body]);
-      m_suggested_unroll_factor
-	= determine_suggested_unroll_factor (loop_vinfo);
+      m_suggested_unroll_factor = determine_suggested_unroll_factor ();
     }
 
   /* Apply the heuristic described above m_stp_sequence_cost.  Prefer
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/cost_model_14.c b/gcc/testsuite/gcc.target/aarch64/sve/cost_model_14.c
new file mode 100644
index 00000000000..b65826b0889
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/cost_model_14.c
@@ -0,0 +1,13 @@
+/* { dg-options "-O3 -mtune=neoverse-v1" } */
+
+#include <stdint.h>
+
+uint64_t f2(uint64_t *ptr, int n) {
+  uint64_t res = 0;
+  for (int i = 0; i < n; ++i)
+    res += ptr[i];
+  return res;
+}
+
+/* { dg-final { scan-assembler-times {\tld1d\tz[0-9]+\.d,} 5 } } */
+/* { dg-final { scan-assembler-times {\tadd\tz[0-9]+\.d,} 8 } } */