Re: [PATCH v2] expansion: make layout of x_shift*cost[][][] more efficient

2023-04-19 Thread Richard Biener via Gcc-patches
On Tue, Apr 18, 2023 at 10:51 PM Vineet Gupta  wrote:
>
> when debugging expmed.[ch] for PR/108987 saw that some of the cost arrays have
> less than ideal layout as follows:
>
>x_shift*cost[0..63][speed][modes]
>
> We would want speed to be first index since a typical compile will have
> that fixed, followed by mode and then the shift values.
>
> It should be non-functional from compiler semantics pov, except
> executing slightly faster due to better locality of shift values for
> given speed and mode. And also a bit more intutive when debugging.

OK, but please wait 24h in case somebody else wants to comment.

Thanks,
Richard.

> gcc/Changelog:
>
> * expmed.h (x_shift*_cost): convert to int [speed][mode][shift].
> (shift*_cost_ptr ()): Access x_shift*_cost array directly.
>
> Signed-off-by: Vineet Gupta 
> ---
> Changes since v1:
>- Post a non stale version of patch
> ---
>  gcc/expmed.h | 27 +--
>  1 file changed, 13 insertions(+), 14 deletions(-)
>
> diff --git a/gcc/expmed.h b/gcc/expmed.h
> index c747a0da1637..22ae1d2d0743 100644
> --- a/gcc/expmed.h
> +++ b/gcc/expmed.h
> @@ -161,15 +161,14 @@ struct target_expmed {
>struct expmed_op_cheap x_sdiv_pow2_cheap;
>struct expmed_op_cheap x_smod_pow2_cheap;
>
> -  /* Cost of various pieces of RTL.  Note that some of these are indexed by
> - shift count and some by mode.  */
> +  /* Cost of various pieces of RTL.  */
>int x_zero_cost[2];
>struct expmed_op_costs x_add_cost;
>struct expmed_op_costs x_neg_cost;
> -  struct expmed_op_costs x_shift_cost[MAX_BITS_PER_WORD];
> -  struct expmed_op_costs x_shiftadd_cost[MAX_BITS_PER_WORD];
> -  struct expmed_op_costs x_shiftsub0_cost[MAX_BITS_PER_WORD];
> -  struct expmed_op_costs x_shiftsub1_cost[MAX_BITS_PER_WORD];
> +  int x_shift_cost[2][NUM_MODE_IPV_INT][MAX_BITS_PER_WORD];
> +  int x_shiftadd_cost[2][NUM_MODE_IPV_INT][MAX_BITS_PER_WORD];
> +  int x_shiftsub0_cost[2][NUM_MODE_IPV_INT][MAX_BITS_PER_WORD];
> +  int x_shiftsub1_cost[2][NUM_MODE_IPV_INT][MAX_BITS_PER_WORD];
>struct expmed_op_costs x_mul_cost;
>struct expmed_op_costs x_sdiv_cost;
>struct expmed_op_costs x_udiv_cost;
> @@ -395,8 +394,8 @@ neg_cost (bool speed, machine_mode mode)
>  inline int *
>  shift_cost_ptr (bool speed, machine_mode mode, int bits)
>  {
> -  return expmed_op_cost_ptr (_target_expmed->x_shift_cost[bits],
> -speed, mode);
> +  int midx = expmed_mode_index (mode);
> +  return _target_expmed->x_shift_cost[speed][midx][bits];
>  }
>
>  /* Set the COST of doing a shift in MODE by BITS when optimizing for SPEED.  
> */
> @@ -421,8 +420,8 @@ shift_cost (bool speed, machine_mode mode, int bits)
>  inline int *
>  shiftadd_cost_ptr (bool speed, machine_mode mode, int bits)
>  {
> -  return expmed_op_cost_ptr (_target_expmed->x_shiftadd_cost[bits],
> -speed, mode);
> +  int midx = expmed_mode_index (mode);
> +  return _target_expmed->x_shiftadd_cost[speed][midx][bits];
>  }
>
>  /* Set the COST of doing a shift in MODE by BITS followed by an add when
> @@ -448,8 +447,8 @@ shiftadd_cost (bool speed, machine_mode mode, int bits)
>  inline int *
>  shiftsub0_cost_ptr (bool speed, machine_mode mode, int bits)
>  {
> -  return expmed_op_cost_ptr (_target_expmed->x_shiftsub0_cost[bits],
> -speed, mode);
> +  int midx = expmed_mode_index (mode);
> +  return _target_expmed->x_shiftsub0_cost[speed][midx][bits];
>  }
>
>  /* Set the COST of doing a shift in MODE by BITS and then subtracting a
> @@ -475,8 +474,8 @@ shiftsub0_cost (bool speed, machine_mode mode, int bits)
>  inline int *
>  shiftsub1_cost_ptr (bool speed, machine_mode mode, int bits)
>  {
> -  return expmed_op_cost_ptr (_target_expmed->x_shiftsub1_cost[bits],
> -speed, mode);
> +  int midx = expmed_mode_index (mode);
> +  return _target_expmed->x_shiftsub1_cost[speed][midx][bits];
>  }
>
>  /* Set the COST of subtracting a shift in MODE by BITS from a value when
> --
> 2.34.1
>


[PATCH v2] expansion: make layout of x_shift*cost[][][] more efficient

2023-04-18 Thread Vineet Gupta
when debugging expmed.[ch] for PR/108987 saw that some of the cost arrays have
less than ideal layout as follows:

   x_shift*cost[0..63][speed][modes]

We would want speed to be first index since a typical compile will have
that fixed, followed by mode and then the shift values.

It should be non-functional from compiler semantics pov, except
executing slightly faster due to better locality of shift values for
given speed and mode. And also a bit more intutive when debugging.

gcc/Changelog:

* expmed.h (x_shift*_cost): convert to int [speed][mode][shift].
(shift*_cost_ptr ()): Access x_shift*_cost array directly.

Signed-off-by: Vineet Gupta 
---
Changes since v1:
   - Post a non stale version of patch
---
 gcc/expmed.h | 27 +--
 1 file changed, 13 insertions(+), 14 deletions(-)

diff --git a/gcc/expmed.h b/gcc/expmed.h
index c747a0da1637..22ae1d2d0743 100644
--- a/gcc/expmed.h
+++ b/gcc/expmed.h
@@ -161,15 +161,14 @@ struct target_expmed {
   struct expmed_op_cheap x_sdiv_pow2_cheap;
   struct expmed_op_cheap x_smod_pow2_cheap;
 
-  /* Cost of various pieces of RTL.  Note that some of these are indexed by
- shift count and some by mode.  */
+  /* Cost of various pieces of RTL.  */
   int x_zero_cost[2];
   struct expmed_op_costs x_add_cost;
   struct expmed_op_costs x_neg_cost;
-  struct expmed_op_costs x_shift_cost[MAX_BITS_PER_WORD];
-  struct expmed_op_costs x_shiftadd_cost[MAX_BITS_PER_WORD];
-  struct expmed_op_costs x_shiftsub0_cost[MAX_BITS_PER_WORD];
-  struct expmed_op_costs x_shiftsub1_cost[MAX_BITS_PER_WORD];
+  int x_shift_cost[2][NUM_MODE_IPV_INT][MAX_BITS_PER_WORD];
+  int x_shiftadd_cost[2][NUM_MODE_IPV_INT][MAX_BITS_PER_WORD];
+  int x_shiftsub0_cost[2][NUM_MODE_IPV_INT][MAX_BITS_PER_WORD];
+  int x_shiftsub1_cost[2][NUM_MODE_IPV_INT][MAX_BITS_PER_WORD];
   struct expmed_op_costs x_mul_cost;
   struct expmed_op_costs x_sdiv_cost;
   struct expmed_op_costs x_udiv_cost;
@@ -395,8 +394,8 @@ neg_cost (bool speed, machine_mode mode)
 inline int *
 shift_cost_ptr (bool speed, machine_mode mode, int bits)
 {
-  return expmed_op_cost_ptr (_target_expmed->x_shift_cost[bits],
-speed, mode);
+  int midx = expmed_mode_index (mode);
+  return _target_expmed->x_shift_cost[speed][midx][bits];
 }
 
 /* Set the COST of doing a shift in MODE by BITS when optimizing for SPEED.  */
@@ -421,8 +420,8 @@ shift_cost (bool speed, machine_mode mode, int bits)
 inline int *
 shiftadd_cost_ptr (bool speed, machine_mode mode, int bits)
 {
-  return expmed_op_cost_ptr (_target_expmed->x_shiftadd_cost[bits],
-speed, mode);
+  int midx = expmed_mode_index (mode);
+  return _target_expmed->x_shiftadd_cost[speed][midx][bits];
 }
 
 /* Set the COST of doing a shift in MODE by BITS followed by an add when
@@ -448,8 +447,8 @@ shiftadd_cost (bool speed, machine_mode mode, int bits)
 inline int *
 shiftsub0_cost_ptr (bool speed, machine_mode mode, int bits)
 {
-  return expmed_op_cost_ptr (_target_expmed->x_shiftsub0_cost[bits],
-speed, mode);
+  int midx = expmed_mode_index (mode);
+  return _target_expmed->x_shiftsub0_cost[speed][midx][bits];
 }
 
 /* Set the COST of doing a shift in MODE by BITS and then subtracting a
@@ -475,8 +474,8 @@ shiftsub0_cost (bool speed, machine_mode mode, int bits)
 inline int *
 shiftsub1_cost_ptr (bool speed, machine_mode mode, int bits)
 {
-  return expmed_op_cost_ptr (_target_expmed->x_shiftsub1_cost[bits],
-speed, mode);
+  int midx = expmed_mode_index (mode);
+  return _target_expmed->x_shiftsub1_cost[speed][midx][bits];
 }
 
 /* Set the COST of subtracting a shift in MODE by BITS from a value when
-- 
2.34.1