public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc r11-8835] aarch64: Add gather_load_xNN_cost tuning fields
@ 2021-08-06 14:37 Richard Sandiford
0 siblings, 0 replies; only message in thread
From: Richard Sandiford @ 2021-08-06 14:37 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:b28c5f682bf90fc71538cbf368400d126c9c057a
commit r11-8835-gb28c5f682bf90fc71538cbf368400d126c9c057a
Author: Richard Sandiford <richard.sandiford@arm.com>
Date: Fri Aug 6 15:36:55 2021 +0100
aarch64: Add gather_load_xNN_cost tuning fields
This patch adds tuning fields for the total cost of a gather load
instruction. Until now, we've costed them as one scalar load
per element instead. Those scalar_load-based values are also
what the patch uses to fill in the new fields for existing
cost structures.
gcc/
* config/aarch64/aarch64-protos.h (sve_vec_cost):
Add gather_load_x32_cost and gather_load_x64_cost.
* config/aarch64/aarch64.c (generic_sve_vector_cost)
(a64fx_sve_vector_cost, neoversev1_sve_vector_cost): Update
accordingly, using the values given by the scalar_load * number
of elements calculation that we used previously.
(aarch64_detect_vector_stmt_subtype): Use the new fields.
(cherry picked from commit 78770e0e5d9fef70679e1db4eb2fb06596fbb2f8)
Diff:
---
gcc/config/aarch64/aarch64-protos.h | 9 +++++++++
gcc/config/aarch64/aarch64.c | 19 +++++++++++++++++++
2 files changed, 28 insertions(+)
diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index fb4ce8e9f84..b91eeeba101 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -259,12 +259,16 @@ struct sve_vec_cost : simd_vec_cost
unsigned int fadda_f16_cost,
unsigned int fadda_f32_cost,
unsigned int fadda_f64_cost,
+ unsigned int gather_load_x32_cost,
+ unsigned int gather_load_x64_cost,
unsigned int scatter_store_elt_cost)
: simd_vec_cost (base),
clast_cost (clast_cost),
fadda_f16_cost (fadda_f16_cost),
fadda_f32_cost (fadda_f32_cost),
fadda_f64_cost (fadda_f64_cost),
+ gather_load_x32_cost (gather_load_x32_cost),
+ gather_load_x64_cost (gather_load_x64_cost),
scatter_store_elt_cost (scatter_store_elt_cost)
{}
@@ -279,6 +283,11 @@ struct sve_vec_cost : simd_vec_cost
const int fadda_f32_cost;
const int fadda_f64_cost;
+ /* The cost of a gather load instruction. The x32 value is for loads
+ of 32-bit elements and the x64 value is for loads of 64-bit elements. */
+ const int gather_load_x32_cost;
+ const int gather_load_x64_cost;
+
/* The per-element cost of a scatter store. */
const int scatter_store_elt_cost;
};
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 70706710d47..5b6cd063e29 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -677,6 +677,8 @@ static const sve_vec_cost generic_sve_vector_cost =
2, /* fadda_f16_cost */
2, /* fadda_f32_cost */
2, /* fadda_f64_cost */
+ 4, /* gather_load_x32_cost */
+ 2, /* gather_load_x64_cost */
1 /* scatter_store_elt_cost */
};
@@ -746,6 +748,8 @@ static const sve_vec_cost a64fx_sve_vector_cost =
13, /* fadda_f16_cost */
13, /* fadda_f32_cost */
13, /* fadda_f64_cost */
+ 64, /* gather_load_x32_cost */
+ 32, /* gather_load_x64_cost */
1 /* scatter_store_elt_cost */
};
@@ -1741,6 +1745,8 @@ static const sve_vec_cost neoversev1_sve_vector_cost =
19, /* fadda_f16_cost */
11, /* fadda_f32_cost */
8, /* fadda_f64_cost */
+ 32, /* gather_load_x32_cost */
+ 16, /* gather_load_x64_cost */
3 /* scatter_store_elt_cost */
};
@@ -14960,6 +14966,19 @@ aarch64_detect_vector_stmt_subtype (vec_info *vinfo, vect_cost_for_stmt kind,
&& DR_IS_WRITE (STMT_VINFO_DATA_REF (stmt_info)))
return simd_costs->store_elt_extra_cost;
+ /* Detect SVE gather loads, which are costed as a single scalar_load
+ for each element. We therefore need to divide the full-instruction
+ cost by the number of elements in the vector. */
+ if (kind == scalar_load
+ && sve_costs
+ && STMT_VINFO_MEMORY_ACCESS_TYPE (stmt_info) == VMAT_GATHER_SCATTER)
+ {
+ unsigned int nunits = vect_nunits_for_cost (vectype);
+ if (GET_MODE_UNIT_BITSIZE (TYPE_MODE (vectype)) == 64)
+ return { sve_costs->gather_load_x64_cost, nunits };
+ return { sve_costs->gather_load_x32_cost, nunits };
+ }
+
/* Detect cases in which a scalar_store is really storing one element
in a scatter operation. */
if (kind == scalar_store
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2021-08-06 14:37 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-08-06 14:37 [gcc r11-8835] aarch64: Add gather_load_xNN_cost tuning fields Richard Sandiford
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).