public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc r12-802] aarch64: Make sqdmlal2 patterns match canonical RTL
@ 2021-05-14 14:31 Kyrylo Tkachov
0 siblings, 0 replies; only message in thread
From: Kyrylo Tkachov @ 2021-05-14 14:31 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:ff3809b459db881e80f627e81ec946e7bbd7041d
commit r12-802-gff3809b459db881e80f627e81ec946e7bbd7041d
Author: Kyrylo Tkachov <kyrylo.tkachov@arm.com>
Date: Fri May 14 10:05:42 2021 +0100
aarch64: Make sqdmlal2 patterns match canonical RTL
The sqdmlal2 patterns are hidden beneath the SBINQOPS iterator and unfortunately they don't match
canonical RTL because the simple accumulate operand comes in the first arm of the SS_PLUS.
This patch splits the SS_PLUS and SS_MINUS forms with the SS_PLUS operands set up to match
the canonical form, where the complex operand comes first.
gcc/ChangeLog:
* config/aarch64/aarch64-simd.md
(aarch64_sqdml<SBINQOPS:as>l2_lane<mode>_internal): Split into...
(aarch64_sqdmlsl2_lane<mode>_internal): ... This...
(aarch64_sqdmlal2_lane<mode>_internal): ... And this.
(aarch64_sqdml<SBINQOPS:as>l2_laneq<mode>_internal): Split into ...
(aarch64_sqdmlsl2_laneq<mode>_internal): ... This...
(aarch64_sqdmlal2_laneq<mode>_internal): ... And this.
(aarch64_sqdml<SBINQOPS:as>l2_n<mode>_internal): Split into...
(aarch64_sqdmlsl2_n<mode>_internal): ... This...
(aarch64_sqdmlal2_n<mode>_internal): ... And this.
Diff:
---
gcc/config/aarch64/aarch64-simd.md | 89 ++++++++++++++++++++++++++++++++++----
1 file changed, 80 insertions(+), 9 deletions(-)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 802cca3a68a..e59bc7b4583 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -5374,9 +5374,9 @@
;; vqdml[sa]l2_lane
-(define_insn "aarch64_sqdml<SBINQOPS:as>l2_lane<mode>_internal"
+(define_insn "aarch64_sqdmlsl2_lane<mode>_internal"
[(set (match_operand:<VWIDE> 0 "register_operand" "=w")
- (SBINQOPS:<VWIDE>
+ (ss_minus:<VWIDE>
(match_operand:<VWIDE> 1 "register_operand" "0")
(ss_ashift:<VWIDE>
(mult:<VWIDE>
@@ -5395,14 +5395,40 @@
{
operands[4] = aarch64_endian_lane_rtx (<VCOND>mode, INTVAL (operands[4]));
return
- "sqdml<SBINQOPS:as>l2\\t%<vw2>0<Vmwtype>, %<v>2<Vmtype>, %3.<Vetype>[%4]";
+ "sqdmlsl2\\t%<vw2>0<Vmwtype>, %<v>2<Vmtype>, %3.<Vetype>[%4]";
+ }
+ [(set_attr "type" "neon_sat_mla_<Vetype>_scalar_long")]
+)
+
+(define_insn "aarch64_sqdmlal2_lane<mode>_internal"
+ [(set (match_operand:<VWIDE> 0 "register_operand" "=w")
+ (ss_plus:<VWIDE>
+ (ss_ashift:<VWIDE>
+ (mult:<VWIDE>
+ (sign_extend:<VWIDE>
+ (vec_select:<VHALF>
+ (match_operand:VQ_HSI 2 "register_operand" "w")
+ (match_operand:VQ_HSI 5 "vect_par_cnst_hi_half" "")))
+ (sign_extend:<VWIDE>
+ (vec_duplicate:<VHALF>
+ (vec_select:<VEL>
+ (match_operand:<VCOND> 3 "register_operand" "<vwx>")
+ (parallel [(match_operand:SI 4 "immediate_operand" "i")])
+ ))))
+ (const_int 1))
+ (match_operand:<VWIDE> 1 "register_operand" "0")))]
+ "TARGET_SIMD"
+ {
+ operands[4] = aarch64_endian_lane_rtx (<VCOND>mode, INTVAL (operands[4]));
+ return
+ "sqdmlal2\\t%<vw2>0<Vmwtype>, %<v>2<Vmtype>, %3.<Vetype>[%4]";
}
[(set_attr "type" "neon_sat_mla_<Vetype>_scalar_long")]
)
-(define_insn "aarch64_sqdml<SBINQOPS:as>l2_laneq<mode>_internal"
+(define_insn "aarch64_sqdmlsl2_laneq<mode>_internal"
[(set (match_operand:<VWIDE> 0 "register_operand" "=w")
- (SBINQOPS:<VWIDE>
+ (ss_minus:<VWIDE>
(match_operand:<VWIDE> 1 "register_operand" "0")
(ss_ashift:<VWIDE>
(mult:<VWIDE>
@@ -5421,7 +5447,33 @@
{
operands[4] = aarch64_endian_lane_rtx (<VCONQ>mode, INTVAL (operands[4]));
return
- "sqdml<SBINQOPS:as>l2\\t%<vw2>0<Vmwtype>, %<v>2<Vmtype>, %3.<Vetype>[%4]";
+ "sqdmlsl2\\t%<vw2>0<Vmwtype>, %<v>2<Vmtype>, %3.<Vetype>[%4]";
+ }
+ [(set_attr "type" "neon_sat_mla_<Vetype>_scalar_long")]
+)
+
+(define_insn "aarch64_sqdmlal2_laneq<mode>_internal"
+ [(set (match_operand:<VWIDE> 0 "register_operand" "=w")
+ (ss_plus:<VWIDE>
+ (ss_ashift:<VWIDE>
+ (mult:<VWIDE>
+ (sign_extend:<VWIDE>
+ (vec_select:<VHALF>
+ (match_operand:VQ_HSI 2 "register_operand" "w")
+ (match_operand:VQ_HSI 5 "vect_par_cnst_hi_half" "")))
+ (sign_extend:<VWIDE>
+ (vec_duplicate:<VHALF>
+ (vec_select:<VEL>
+ (match_operand:<VCONQ> 3 "register_operand" "<vwx>")
+ (parallel [(match_operand:SI 4 "immediate_operand" "i")])
+ ))))
+ (const_int 1))
+ (match_operand:<VWIDE> 1 "register_operand" "0")))]
+ "TARGET_SIMD"
+ {
+ operands[4] = aarch64_endian_lane_rtx (<VCONQ>mode, INTVAL (operands[4]));
+ return
+ "sqdmlal2\\t%<vw2>0<Vmwtype>, %<v>2<Vmtype>, %3.<Vetype>[%4]";
}
[(set_attr "type" "neon_sat_mla_<Vetype>_scalar_long")]
)
@@ -5460,9 +5512,9 @@
DONE;
})
-(define_insn "aarch64_sqdml<SBINQOPS:as>l2_n<mode>_internal"
+(define_insn "aarch64_sqdmlsl2_n<mode>_internal"
[(set (match_operand:<VWIDE> 0 "register_operand" "=w")
- (SBINQOPS:<VWIDE>
+ (ss_minus:<VWIDE>
(match_operand:<VWIDE> 1 "register_operand" "0")
(ss_ashift:<VWIDE>
(mult:<VWIDE>
@@ -5475,7 +5527,26 @@
(match_operand:<VEL> 3 "register_operand" "<vwx>"))))
(const_int 1))))]
"TARGET_SIMD"
- "sqdml<SBINQOPS:as>l2\\t%<vw2>0<Vmwtype>, %<v>2<Vmtype>, %3.<Vetype>[0]"
+ "sqdmlsl2\\t%<vw2>0<Vmwtype>, %<v>2<Vmtype>, %3.<Vetype>[0]"
+ [(set_attr "type" "neon_sat_mla_<Vetype>_scalar_long")]
+)
+
+(define_insn "aarch64_sqdmlal2_n<mode>_internal"
+ [(set (match_operand:<VWIDE> 0 "register_operand" "=w")
+ (ss_plus:<VWIDE>
+ (ss_ashift:<VWIDE>
+ (mult:<VWIDE>
+ (sign_extend:<VWIDE>
+ (vec_select:<VHALF>
+ (match_operand:VQ_HSI 2 "register_operand" "w")
+ (match_operand:VQ_HSI 4 "vect_par_cnst_hi_half" "")))
+ (sign_extend:<VWIDE>
+ (vec_duplicate:<VHALF>
+ (match_operand:<VEL> 3 "register_operand" "<vwx>"))))
+ (const_int 1))
+ (match_operand:<VWIDE> 1 "register_operand" "0")))]
+ "TARGET_SIMD"
+ "sqdmlal2\\t%<vw2>0<Vmwtype>, %<v>2<Vmtype>, %3.<Vetype>[0]"
[(set_attr "type" "neon_sat_mla_<Vetype>_scalar_long")]
)
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2021-05-14 14:31 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-05-14 14:31 [gcc r12-802] aarch64: Make sqdmlal2 patterns match canonical RTL Kyrylo Tkachov
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).