[Bug tree-optimization/83253] -ftree-slsr causes performance regression

[wschmidt at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83253

--- Comment #5 from Bill Schmidt <wschmidt at gcc dot gnu.org> ---
Here's an untested patch (bootstraps successfully but regtest is still
ongoing):

Index: gcc/gimple-ssa-strength-reduction.c                                      
===================================================================
--- gcc/gimple-ssa-strength-reduction.c (revision 255588)                       
+++ gcc/gimple-ssa-strength-reduction.c (working copy)                          
@@ -3083,7 +3083,17 @@ analyze_increments (slsr_cand_t first_dep, machine
       else if (first_dep->kind == CAND_MULT)                                   
        {                                                                       
          int cost = mult_by_coeff_cost (incr, mode, speed);                    
-         int repl_savings = mul_cost (speed, mode) - add_cost (speed, mode);   
+         int repl_savings;                                                     
+                                                                               
+         if (TREE_CODE (first_dep->stride) == INTEGER_CST)                     
+           {                                                                   
+             HOST_WIDE_INT hwi_stride = tree_to_shwi (first_dep->stride);      
+             repl_savings = (mult_by_coeff_cost (hwi_stride, mode, speed)      
+                             - add_cost (speed, mode));                        
+           }                                                                   
+         else                                                                  
+           repl_savings = mul_cost (speed, mode) - add_cost (speed, mode);     
+                                                                               
          if (speed)                                                            
            cost = lowest_cost_path (cost, repl_savings, first_dep,             
                                     incr_vec[i].incr, COUNT_PHIS);             

OP, since you have confirmed the problem on a number of targets, would you be
willing to try this patch on a couple of them and see whether it solves it? 
Otherwise I can build some crosses later this week.

Thanks!