public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc r14-5669] AArch64: only discount MLA for vector and scalar statements
@ 2023-11-21 13:16 Tamar Christina
0 siblings, 0 replies; only message in thread
From: Tamar Christina @ 2023-11-21 13:16 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:5ff006bd3db5580fa70a05bd275b67067b8486d9
commit r14-5669-g5ff006bd3db5580fa70a05bd275b67067b8486d9
Author: Tamar Christina <tamar.christina@arm.com>
Date: Tue Nov 21 13:14:29 2023 +0000
AArch64: only discount MLA for vector and scalar statements
In testcases gcc.dg/tree-ssa/slsr-19.c and gcc.dg/tree-ssa/slsr-20.c we have a
fairly simple computation. On the current generic costing we generate:
f:
add w0, w0, 2
madd w1, w0, w1, w1
lsl w0, w1, 1
ret
but on any other cost model but generic (including the new up coming generic)
we generate:
f:
adrp x2, .LC0
dup v31.2s, w0
fmov s30, w1
ldr d29, [x2, #:lo12:.LC0]
add v31.2s, v31.2s, v29.2s
mul v31.2s, v31.2s, v30.s[0]
addp v31.2s, v31.2s, v31.2s
fmov w0, s31
ret
.LC0:
.word 2
.word 4
This seems to be because the vectorizer thinks the vector transfers are free:
x1_4 + x2_6 1 times vector_stmt costs 0 in body
x1_4 + x2_6 1 times vec_to_scalar costs 0 in body
This happens because the stmt it's using to get the cost of register transfers
for the given type happens to be one feeding into a MUL. we incorrectly
discount the + for the register transfer.
This is fixed by guarding the check for aarch64_multiply_add_p with a kind
check and only do it for scalar_stmt and vector_stmt.
I'm sending this separate to my patch series but it's required for it.
It also seems to fix overvectorization cases in fotonik3d_r in SPECCPU 2017.
gcc/ChangeLog:
* config/aarch64/aarch64.cc (aarch64_adjust_stmt_cost): Guard mla.
(aarch64_vector_costs::count_ops): Likewise.
Diff:
---
gcc/config/aarch64/aarch64.cc | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 800a8b0e110..72e135037bc 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -17007,7 +17007,7 @@ aarch64_adjust_stmt_cost (vec_info *vinfo, vect_cost_for_stmt kind,
}
gassign *assign = dyn_cast<gassign *> (STMT_VINFO_STMT (stmt_info));
- if (assign)
+ if ((kind == scalar_stmt || kind == vector_stmt) && assign)
{
/* For MLA we need to reduce the cost since MLA is 1 instruction. */
if (!vect_is_reduction (stmt_info)
@@ -17088,15 +17088,18 @@ aarch64_vector_costs::count_ops (unsigned int count, vect_cost_for_stmt kind,
ops->reduction_latency = MAX (ops->reduction_latency, base);
}
- /* Assume that multiply-adds will become a single operation. */
- if (stmt_info && aarch64_multiply_add_p (m_vinfo, stmt_info, m_vec_flags))
- return;
+ if (stmt_info && (kind == scalar_stmt || kind == vector_stmt))
+ {
+ /* Assume that multiply-adds will become a single operation. */
+ if (aarch64_multiply_add_p (m_vinfo, stmt_info, m_vec_flags))
+ return;
+
+ /* Assume that bool AND with compare operands will become a single
+ operation. */
+ if (aarch64_bool_compound_p (m_vinfo, stmt_info, m_vec_flags))
+ return;
+ }
- /* Assume that bool AND with compare operands will become a single
- operation. */
- if (stmt_info
- && aarch64_bool_compound_p (m_vinfo, stmt_info, m_vec_flags))
- return;
/* Count the basic operation cost associated with KIND. */
switch (kind)
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2023-11-21 13:16 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2023-11-21 13:16 [gcc r14-5669] AArch64: only discount MLA for vector and scalar statements Tamar Christina
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).