https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
Uroš Bizjak changed:
What|Removed |Added
Status|UNCONFIRMED |RESOLVED
Resolution|---
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
Martin Liška changed:
What|Removed |Added
CC||marxin at gcc dot gnu.org
--- Comment #8
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #7 from Aldy Hernandez ---
Author: aldyh
Date: Wed Sep 13 17:16:18 2017
New Revision: 252513
URL: https://gcc.gnu.org/viewcvs?rev=252513&root=gcc&view=rev
Log:
PR target/46091
* config/i386/i386.md (*btsq_imm): Rename
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #6 from Aldy Hernandez ---
Author: aldyh
Date: Wed Sep 13 17:02:09 2017
New Revision: 252445
URL: https://gcc.gnu.org/viewcvs?rev=252445&root=gcc&view=rev
Log:
PR target/46091
* config/i386/i386.md (*anddi_1_btr): Cha
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #5 from Aldy Hernandez ---
Author: aldyh
Date: Wed Sep 13 16:57:52 2017
New Revision: 252427
URL: https://gcc.gnu.org/viewcvs?rev=252427&root=gcc&view=rev
Log:
PR target/46091
* config/i386/i386.md (*anddi_1_btr): New
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #4 from uros at gcc dot gnu.org ---
Author: uros
Date: Mon Aug 21 15:15:07 2017
New Revision: 251235
URL: https://gcc.gnu.org/viewcvs?rev=251235&root=gcc&view=rev
Log:
PR target/46091
* config/i386/i386.md (*btsq_imm):
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #3 from uros at gcc dot gnu.org ---
Author: uros
Date: Wed Aug 16 15:25:34 2017
New Revision: 251124
URL: https://gcc.gnu.org/viewcvs?rev=251124&root=gcc&view=rev
Log:
PR target/46091
* config/i386/i386.md (*anddi_1_bt
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #11 from Uroš Bizjak ---
(In reply to Uroš Bizjak from comment #10)
> I'll look into this a bit some more. However, these insn should be rare, so
> do not expect any noticeable application speed-up ...
From the Agner lists, it is n
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #10 from Uroš Bizjak ---
(In reply to Avi Kivity from comment #9)
> I believe the comment is wrong. Here's what the manual says:
>
> "This instruction can be used with a LOCK prefix to allow the instruction to
> be executed atomicall
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #9 from Avi Kivity ---
I believe the comment is wrong. Here's what the manual says:
"This instruction can be used with a LOCK prefix to allow the instruction to be
executed atomically."
Implying that without the LOCK prefix, it is n
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #8 from Uroš Bizjak ---
(In reply to Uroš Bizjak from comment #7)
> From i386.md:
>
> ;; %%% bts, btr, btc, bt.
> ;; In general these instructions are *slow* when applied to memory,
> ;; since they enforce atomic operation. When app
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #7 from Uroš Bizjak ---
From i386.md:
;; %%% bts, btr, btc, bt.
;; In general these instructions are *slow* when applied to memory,
;; since they enforce atomic operation. When applied to registers,
;; it depends on the cpu implemen
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #6 from Avi Kivity ---
I believe bts/btc/btr can do more - they also calculate the word offset when
addressing memory, see first comment.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
Uroš Bizjak changed:
What|Removed |Added
Target||x86_64
Status|ASSIGNED
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #4 from uros at gcc dot gnu.org ---
Author: uros
Date: Mon Aug 14 16:42:15 2017
New Revision: 251095
URL: https://gcc.gnu.org/viewcvs?rev=251095&root=gcc&view=rev
Log:
PR target/46091
* config/i386/i386.md (*anddi_1_bt
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
Uroš Bizjak changed:
What|Removed |Added
Status|UNCONFIRMED |ASSIGNED
Last reconfirmed|
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
--- Comment #2 from Avi Kivity ---
Another instance:
unsigned long clear(unsigned long x) {
return x & ~ ((unsigned long)1 << 63);
}
This compiles to movabs+andq, while it could compile to a single btr
instruction.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
Avi Kivity changed:
What|Removed |Added
CC||a...@cloudius-systems.com
--- Comment #1 fr
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46091
Andrew Pinski changed:
What|Removed |Added
Keywords||missed-optimization
Severity|no
19 matches
Mail list logo
