Re: [5/6] Account for the cost of generating loop masks
On Tue, Nov 5, 2019 at 3:31 PM Richard Sandiford
wrote:
>
> We didn't take the cost of generating loop masks into account, and so
> tended to underestimate the cost of loops that need multiple masks.
OK.
>
> 2019-11-05 Richard Sandiford
>
> gcc/
> * tree-vect-loop.c (vect_estimate_min_profitable_iters): Include
> the cost of generating loop masks.
>
> gcc/testsuite/
> * gcc.target/aarch64/sve/mask_struct_store_3.c: Add
> -fno-vect-cost-model.
> * gcc.target/aarch64/sve/mask_struct_store_3_run.c: Likewise.
> * gcc.target/aarch64/sve/peel_ind_3.c: Likewise.
> * gcc.target/aarch64/sve/peel_ind_3_run.c: Likewise.
>
> Index: gcc/tree-vect-loop.c
> ===
> --- gcc/tree-vect-loop.c2019-11-05 14:19:58.781197820 +
> +++ gcc/tree-vect-loop.c2019-11-05 14:20:40.188909187 +
> @@ -3435,6 +3435,32 @@ vect_estimate_min_profitable_iters (loop
> si->kind, si->stmt_info, si->misalign,
> vect_epilogue);
> }
> +
> + /* Calculate how many masks we need to generate. */
> + unsigned int num_masks = 0;
> + rgroup_masks *rgm;
> + unsigned int num_vectors_m1;
> + FOR_EACH_VEC_ELT (LOOP_VINFO_MASKS (loop_vinfo), num_vectors_m1, rgm)
> + if (rgm->mask_type)
> + num_masks += num_vectors_m1 + 1;
> + gcc_assert (num_masks > 0);
> +
> + /* In the worst case, we need to generate each mask in the prologue
> +and in the loop body. One of the loop body mask instructions
> +replaces the comparison in the scalar loop, and since we don't
> +count the scalar comparison against the scalar body, we shouldn't
> +count that vector instruction against the vector body either.
> +
> +Sometimes we can use unpacks instead of generating prologue
> +masks and sometimes the prologue mask will fold to a constant,
> +so the actual prologue cost might be smaller. However, it's
> +simpler and safer to use the worst-case cost; if this ends up
> +being the tie-breaker between vectorizing or not, then it's
> +probably better not to vectorize. */
> + (void) add_stmt_cost (target_cost_data, num_masks, vector_stmt,
> + NULL, 0, vect_prologue);
> + (void) add_stmt_cost (target_cost_data, num_masks - 1, vector_stmt,
> + NULL, 0, vect_body);
> }
>else if (npeel < 0)
> {
> Index: gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c
> ===
> --- gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c 2019-03-08
> 18:14:29.768994780 +
> +++ gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c 2019-11-05
> 14:20:40.184909216 +
> @@ -1,5 +1,5 @@
> /* { dg-do compile } */
> -/* { dg-options "-O2 -ftree-vectorize -ffast-math" } */
> +/* { dg-options "-O2 -ftree-vectorize -ffast-math -fno-vect-cost-model" } */
>
> #include
>
> Index: gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c
> ===
> --- gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c
> 2019-03-08 18:14:29.772994767 +
> +++ gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c
> 2019-11-05 14:20:40.184909216 +
> @@ -1,5 +1,5 @@
> /* { dg-do run { target aarch64_sve_hw } } */
> -/* { dg-options "-O2 -ftree-vectorize -ffast-math" } */
> +/* { dg-options "-O2 -ftree-vectorize -ffast-math -fno-vect-cost-model" } */
>
> #include "mask_struct_store_3.c"
>
> Index: gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c
> ===
> --- gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c 2019-03-08
> 18:14:29.776994751 +
> +++ gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c 2019-11-05
> 14:20:40.184909216 +
> @@ -1,7 +1,7 @@
> /* { dg-do compile } */
> /* Pick an arbitrary target for which unaligned accesses are more
> expensive. */
> -/* { dg-options "-O3 -msve-vector-bits=256 -mtune=thunderx" } */
> +/* { dg-options "-O3 -msve-vector-bits=256 -mtune=thunderx
> -fno-vect-cost-model" } */
>
> #define N 32
> #define MAX_START 8
> Index: gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c
> ===
> --- gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c 2019-03-08
> 18:14:29.784994721 +
> +++ gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c 2019-11-05
> 14:20:40.184909216 +
> @@ -1,6 +1,6 @@
> /* { dg-do run { target aarch64_sve_hw } } */
> -/* { dg-options "-O3 -mtune=thunderx" } */
> -/* { dg-options "-O3 -mtune=thunderx -msve-vector-bits=256" { target
> aarch64_sve256_hw } } */
> +/* { dg-options "-O3 -mtune=thunderx
[5/6] Account for the cost of generating loop masks
We didn't take the cost of generating loop masks into account, and so
tended to underestimate the cost of loops that need multiple masks.
2019-11-05 Richard Sandiford
gcc/
* tree-vect-loop.c (vect_estimate_min_profitable_iters): Include
the cost of generating loop masks.
gcc/testsuite/
* gcc.target/aarch64/sve/mask_struct_store_3.c: Add
-fno-vect-cost-model.
* gcc.target/aarch64/sve/mask_struct_store_3_run.c: Likewise.
* gcc.target/aarch64/sve/peel_ind_3.c: Likewise.
* gcc.target/aarch64/sve/peel_ind_3_run.c: Likewise.
Index: gcc/tree-vect-loop.c
===
--- gcc/tree-vect-loop.c2019-11-05 14:19:58.781197820 +
+++ gcc/tree-vect-loop.c2019-11-05 14:20:40.188909187 +
@@ -3435,6 +3435,32 @@ vect_estimate_min_profitable_iters (loop
si->kind, si->stmt_info, si->misalign,
vect_epilogue);
}
+
+ /* Calculate how many masks we need to generate. */
+ unsigned int num_masks = 0;
+ rgroup_masks *rgm;
+ unsigned int num_vectors_m1;
+ FOR_EACH_VEC_ELT (LOOP_VINFO_MASKS (loop_vinfo), num_vectors_m1, rgm)
+ if (rgm->mask_type)
+ num_masks += num_vectors_m1 + 1;
+ gcc_assert (num_masks > 0);
+
+ /* In the worst case, we need to generate each mask in the prologue
+and in the loop body. One of the loop body mask instructions
+replaces the comparison in the scalar loop, and since we don't
+count the scalar comparison against the scalar body, we shouldn't
+count that vector instruction against the vector body either.
+
+Sometimes we can use unpacks instead of generating prologue
+masks and sometimes the prologue mask will fold to a constant,
+so the actual prologue cost might be smaller. However, it's
+simpler and safer to use the worst-case cost; if this ends up
+being the tie-breaker between vectorizing or not, then it's
+probably better not to vectorize. */
+ (void) add_stmt_cost (target_cost_data, num_masks, vector_stmt,
+ NULL, 0, vect_prologue);
+ (void) add_stmt_cost (target_cost_data, num_masks - 1, vector_stmt,
+ NULL, 0, vect_body);
}
else if (npeel < 0)
{
Index: gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c
===
--- gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c 2019-03-08
18:14:29.768994780 +
+++ gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c 2019-11-05
14:20:40.184909216 +
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -ftree-vectorize -ffast-math" } */
+/* { dg-options "-O2 -ftree-vectorize -ffast-math -fno-vect-cost-model" } */
#include
Index: gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c
===
--- gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c
2019-03-08 18:14:29.772994767 +
+++ gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c
2019-11-05 14:20:40.184909216 +
@@ -1,5 +1,5 @@
/* { dg-do run { target aarch64_sve_hw } } */
-/* { dg-options "-O2 -ftree-vectorize -ffast-math" } */
+/* { dg-options "-O2 -ftree-vectorize -ffast-math -fno-vect-cost-model" } */
#include "mask_struct_store_3.c"
Index: gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c
===
--- gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c 2019-03-08
18:14:29.776994751 +
+++ gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c 2019-11-05
14:20:40.184909216 +
@@ -1,7 +1,7 @@
/* { dg-do compile } */
/* Pick an arbitrary target for which unaligned accesses are more
expensive. */
-/* { dg-options "-O3 -msve-vector-bits=256 -mtune=thunderx" } */
+/* { dg-options "-O3 -msve-vector-bits=256 -mtune=thunderx
-fno-vect-cost-model" } */
#define N 32
#define MAX_START 8
Index: gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c
===
--- gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c 2019-03-08
18:14:29.784994721 +
+++ gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c 2019-11-05
14:20:40.184909216 +
@@ -1,6 +1,6 @@
/* { dg-do run { target aarch64_sve_hw } } */
-/* { dg-options "-O3 -mtune=thunderx" } */
-/* { dg-options "-O3 -mtune=thunderx -msve-vector-bits=256" { target
aarch64_sve256_hw } } */
+/* { dg-options "-O3 -mtune=thunderx -fno-vect-cost-model" } */
+/* { dg-options "-O3 -mtune=thunderx -msve-vector-bits=256
-fno-vect-cost-model" { target aarch64_sve256_hw } } */
#include "peel_ind_3.c"
