public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug tree-optimization/94864] New: Failure to combine vunpckhpd+movsd into single vunpckhpd
@ 2020-04-29 21:59 gabravier at gmail dot com
2020-04-29 22:03 ` [Bug tree-optimization/94864] " gabravier at gmail dot com
` (6 more replies)
0 siblings, 7 replies; 8+ messages in thread
From: gabravier at gmail dot com @ 2020-04-29 21:59 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94864
Bug ID: 94864
Summary: Failure to combine vunpckhpd+movsd into single
vunpckhpd
Product: gcc
Version: 10.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: gabravier at gmail dot com
Target Milestone: ---
typedef double v2df __attribute__((vector_size(16)));
v2df move_sd(v2df a, v2df b)
{
v2df result = a;
result[0] = b[1];
return result;
}
LLVM outputs this :
move_sd(double __vector(2), double __vector(2)): # @move_sd(double __vector(2),
double __vector(2))
vunpckhpd xmm0, xmm1, xmm0 # xmm0 = xmm1[1],xmm0[1]
ret
GCC outputs this :
move_sd(double __vector(2), double __vector(2)):
vunpckhpd xmm1, xmm1, xmm1
vmovsd xmm0, xmm0, xmm1
ret
^ permalink raw reply [flat|nested] 8+ messages in thread
* [Bug tree-optimization/94864] Failure to combine vunpckhpd+movsd into single vunpckhpd
2020-04-29 21:59 [Bug tree-optimization/94864] New: Failure to combine vunpckhpd+movsd into single vunpckhpd gabravier at gmail dot com
@ 2020-04-29 22:03 ` gabravier at gmail dot com
2020-04-30 7:03 ` [Bug rtl-optimization/94864] " rguenth at gcc dot gnu.org
` (5 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: gabravier at gmail dot com @ 2020-04-29 22:03 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94864
--- Comment #1 from Gabriel Ravier <gabravier at gmail dot com> ---
Note : The compilation options were `-O3 -mavx`
^ permalink raw reply [flat|nested] 8+ messages in thread
* [Bug rtl-optimization/94864] Failure to combine vunpckhpd+movsd into single vunpckhpd
2020-04-29 21:59 [Bug tree-optimization/94864] New: Failure to combine vunpckhpd+movsd into single vunpckhpd gabravier at gmail dot com
2020-04-29 22:03 ` [Bug tree-optimization/94864] " gabravier at gmail dot com
@ 2020-04-30 7:03 ` rguenth at gcc dot gnu.org
2020-05-04 15:17 ` segher at gcc dot gnu.org
` (4 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: rguenth at gcc dot gnu.org @ 2020-04-30 7:03 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94864
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Ever confirmed|0 |1
Last reconfirmed| |2020-04-30
Component|target |rtl-optimization
CC| |rguenth at gcc dot gnu.org,
| |segher at gcc dot gnu.org,
| |uros at gcc dot gnu.org
Status|UNCONFIRMED |NEW
--- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> ---
We're feeding combine with
(insn 7 4 9 2 (set (reg:DF 87)
(vec_select:DF (reg:V2DF 90)
(parallel [
(const_int 1 [0x1])
]))) "y.c":6:26 3195 {sse2_storehpd}
(expr_list:REG_DEAD (reg:V2DF 90)
(nil)))
(insn 9 7 14 2 (set (reg:V2DF 88 [ result ])
(vec_merge:V2DF (vec_duplicate:V2DF (reg:DF 87))
(reg:V2DF 89)
(const_int 1 [0x1]))) "y.c":6:21 2918 {vec_setv2df_0}
(expr_list:REG_DEAD (reg:V2DF 89)
(expr_list:REG_DEAD (reg:DF 87)
(nil))))
which makes
(set (reg:V2DF 88 [ result ])
(vec_merge:V2DF (vec_duplicate:V2DF (vec_select:DF (reg:V2DF 90)
(parallel [
(const_int 1 [0x1])
])))
(reg:V2DF 89)
(const_int 1 [0x1])))
out of this which does not match anything because x86 chooses to use
vec_merge in some and vec_select/vec_concat in other patterns:
(define_insn "*vec_interleave_highv2df"
[(set (match_operand:V2DF 0 "nonimmediate_operand" "=x,v,v,x,v,m")
(vec_select:V2DF
(vec_concat:V4DF
(match_operand:V2DF 1 "nonimmediate_operand" " 0,v,o,o,o,v")
(match_operand:V2DF 2 "nonimmediate_operand" " x,v,1,0,v,0"))
(parallel [(const_int 1)
(const_int 3)])))]
"TARGET_SSE2 && ix86_vec_interleave_v2df_operator_ok (operands, 1)"
"@
unpckhpd\t{%2, %0|%0, %2}
not sure if combine should try to exchange vec_merge for vec_select/vec_concat
or if this is simply the backends fault (or GCCs for even having two ways
to express the same thing...)
^ permalink raw reply [flat|nested] 8+ messages in thread
* [Bug rtl-optimization/94864] Failure to combine vunpckhpd+movsd into single vunpckhpd
2020-04-29 21:59 [Bug tree-optimization/94864] New: Failure to combine vunpckhpd+movsd into single vunpckhpd gabravier at gmail dot com
2020-04-29 22:03 ` [Bug tree-optimization/94864] " gabravier at gmail dot com
2020-04-30 7:03 ` [Bug rtl-optimization/94864] " rguenth at gcc dot gnu.org
@ 2020-05-04 15:17 ` segher at gcc dot gnu.org
2020-05-07 11:04 ` rguenth at gcc dot gnu.org
` (3 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: segher at gcc dot gnu.org @ 2020-05-04 15:17 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94864
--- Comment #3 from Segher Boessenkool <segher at gcc dot gnu.org> ---
vec_duplicate of vec_select is just a vec_select. Any vec_merge is a
vec_select as well, as you say.
Canonicalisation should make vec_select always.
We probably should have canonicalisation rules for this, so that we do
not get all those rtxes in the instruction stream at all.
^ permalink raw reply [flat|nested] 8+ messages in thread
* [Bug rtl-optimization/94864] Failure to combine vunpckhpd+movsd into single vunpckhpd
2020-04-29 21:59 [Bug tree-optimization/94864] New: Failure to combine vunpckhpd+movsd into single vunpckhpd gabravier at gmail dot com
` (2 preceding siblings ...)
2020-05-04 15:17 ` segher at gcc dot gnu.org
@ 2020-05-07 11:04 ` rguenth at gcc dot gnu.org
2023-07-31 11:31 ` rguenth at gcc dot gnu.org
` (2 subsequent siblings)
6 siblings, 0 replies; 8+ messages in thread
From: rguenth at gcc dot gnu.org @ 2020-05-07 11:04 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94864
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Assignee|unassigned at gcc dot gnu.org |rguenth at gcc dot gnu.org
Status|NEW |ASSIGNED
--- Comment #4 from Richard Biener <rguenth at gcc dot gnu.org> ---
Addressed by the patch for PR94865.
^ permalink raw reply [flat|nested] 8+ messages in thread
* [Bug rtl-optimization/94864] Failure to combine vunpckhpd+movsd into single vunpckhpd
2020-04-29 21:59 [Bug tree-optimization/94864] New: Failure to combine vunpckhpd+movsd into single vunpckhpd gabravier at gmail dot com
` (3 preceding siblings ...)
2020-05-07 11:04 ` rguenth at gcc dot gnu.org
@ 2023-07-31 11:31 ` rguenth at gcc dot gnu.org
2023-08-22 9:34 ` cvs-commit at gcc dot gnu.org
2023-08-22 9:35 ` rguenth at gcc dot gnu.org
6 siblings, 0 replies; 8+ messages in thread
From: rguenth at gcc dot gnu.org @ 2023-07-31 11:31 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94864
Bug 94864 depends on bug 88540, which changed state.
Bug 88540 Summary: Issues with vectorization of min/max operations
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88540
What |Removed |Added
----------------------------------------------------------------------------
Status|ASSIGNED |RESOLVED
Resolution|--- |FIXED
^ permalink raw reply [flat|nested] 8+ messages in thread
* [Bug rtl-optimization/94864] Failure to combine vunpckhpd+movsd into single vunpckhpd
2020-04-29 21:59 [Bug tree-optimization/94864] New: Failure to combine vunpckhpd+movsd into single vunpckhpd gabravier at gmail dot com
` (4 preceding siblings ...)
2023-07-31 11:31 ` rguenth at gcc dot gnu.org
@ 2023-08-22 9:34 ` cvs-commit at gcc dot gnu.org
2023-08-22 9:35 ` rguenth at gcc dot gnu.org
6 siblings, 0 replies; 8+ messages in thread
From: cvs-commit at gcc dot gnu.org @ 2023-08-22 9:34 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94864
--- Comment #5 from CVS Commits <cvs-commit at gcc dot gnu.org> ---
The master branch has been updated by Richard Biener <rguenth@gcc.gnu.org>:
https://gcc.gnu.org/g:27de9aa152141e7f3ee66372647d0f2cd94c4b90
commit r14-3381-g27de9aa152141e7f3ee66372647d0f2cd94c4b90
Author: Richard Biener <rguenther@suse.de>
Date: Wed Jul 12 15:01:47 2023 +0200
tree-optimization/94864 - vector insert of vector extract simplification
The PRs ask for optimizing of
_1 = BIT_FIELD_REF <b_3(D), 64, 64>;
result_4 = BIT_INSERT_EXPR <a_2(D), _1, 64>;
to a vector permutation. The following implements this as
match.pd pattern, improving code generation on x86_64.
On the RTL level we face the issue that backend patterns inconsistently
use vec_merge and vec_select of vec_concat to represent permutes.
I think using a (supported) permute is almost always better
than an extract plus insert, maybe excluding the case we extract
element zero and that's aliased to a register that can be used
directly for insertion (not sure how to query that).
The patch FAILs one case in gcc.target/i386/avx512fp16-vmovsh-1a.c
where we now expand from
__A_28 = VEC_PERM_EXPR <x2.8_9, x1.9_10, { 0, 9, 10, 11, 12, 13, 14, 15
}>;
instead of
_28 = BIT_FIELD_REF <x2.8_9, 16, 0>;
__A_29 = BIT_INSERT_EXPR <x1.9_10, _28, 0>;
producing a vpblendw instruction instead of the expected vmovsh. That's
either a missed vec_perm_const expansion optimization or even better,
an improvement - Zen4 for example has 4 ports to execute vpblendw
but only 3 for executing vmovsh and both instructions have the same size.
The patch XFAILs the sub-testcase.
PR tree-optimization/94864
PR tree-optimization/94865
PR tree-optimization/93080
* match.pd (bit_insert @0 (BIT_FIELD_REF @1 ..) ..): New pattern
for vector insertion from vector extraction.
* gcc.target/i386/pr94864.c: New testcase.
* gcc.target/i386/pr94865.c: Likewise.
* gcc.target/i386/avx512fp16-vmovsh-1a.c: XFAIL.
* gcc.dg/tree-ssa/forwprop-40.c: Likewise.
* gcc.dg/tree-ssa/forwprop-41.c: Likewise.
^ permalink raw reply [flat|nested] 8+ messages in thread
* [Bug rtl-optimization/94864] Failure to combine vunpckhpd+movsd into single vunpckhpd
2020-04-29 21:59 [Bug tree-optimization/94864] New: Failure to combine vunpckhpd+movsd into single vunpckhpd gabravier at gmail dot com
` (5 preceding siblings ...)
2023-08-22 9:34 ` cvs-commit at gcc dot gnu.org
@ 2023-08-22 9:35 ` rguenth at gcc dot gnu.org
6 siblings, 0 replies; 8+ messages in thread
From: rguenth at gcc dot gnu.org @ 2023-08-22 9:35 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94864
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Resolution|--- |FIXED
Status|ASSIGNED |RESOLVED
Target Milestone|--- |14.0
--- Comment #6 from Richard Biener <rguenth at gcc dot gnu.org> ---
Fixed.
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2023-08-22 9:35 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-04-29 21:59 [Bug tree-optimization/94864] New: Failure to combine vunpckhpd+movsd into single vunpckhpd gabravier at gmail dot com
2020-04-29 22:03 ` [Bug tree-optimization/94864] " gabravier at gmail dot com
2020-04-30 7:03 ` [Bug rtl-optimization/94864] " rguenth at gcc dot gnu.org
2020-05-04 15:17 ` segher at gcc dot gnu.org
2020-05-07 11:04 ` rguenth at gcc dot gnu.org
2023-07-31 11:31 ` rguenth at gcc dot gnu.org
2023-08-22 9:34 ` cvs-commit at gcc dot gnu.org
2023-08-22 9:35 ` rguenth at gcc dot gnu.org
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).