From: David Edelsohn <dje.gcc@gmail.com>
To: Michael Meissner <meissner@linux.vnet.ibm.com>,
GCC Patches <gcc-patches@gcc.gnu.org>,
David Edelsohn <dje.gcc@gmail.com>,
Pat Haugen <pthaugen@us.ibm.com>,
Peter Bergner <bergner@vnet.ibm.com>
Subject: Re: [PATCH, rs6000] power8 patches, patch #8, power8 load fusion + misc.
Date: Tue, 18 Jun 2013 18:30:00 -0000 [thread overview]
Message-ID: <CAGWvnymmrzNTRetXT6gWu2AHNpCrkui1koKLNB-PSCt=eG_RXw@mail.gmail.com> (raw)
In-Reply-To: <20130522205258.GA11470@ibm-tiger.the-meissners.org>
On Wed, May 22, 2013 at 4:52 PM, Michael Meissner
<meissner@linux.vnet.ibm.com> wrote:
> 2013-05-22 Michael Meissner <meissner@linux.vnet.ibm.com>
>
> * config/rs6000/predicates.md (fusion_gpr_addis): New predicates
> to support power8 load fusion.
> (fusion_gpr_mem_load): Likewise.
>
> * config/rs6000/rs6000-modes.def (PTImode): Update a comment.
>
> * config/rs6000/rs6000-protos.h (fusion_gpr_load_p): New
> declarations for power8 load fusion.
> (emit_fusion_gpr_load): Likewise.
>
> * config/rs6000/rs6000.opt (-mlra): New undocumented switch to
> turn on using the LRA register allocator.
> (-mconstrain-regs): New undocumented switch to constrain
> non-integer values from being loaded into the LR or CTR registers.
This really should have been a separate patch.
> * config/rs6000/rs6000.c (TARGET_LRA_P): If -mlra, turn on using
> the LRA register allocator.
> (rs6000_lra_p): Likewise.
> (rs6000_hard_regno_mode_ok): Allow DI/DD/SF/SD modes in altivec
> registers if power8. If -mconstrain-regs, only allow int modes
> into LR, CTR, and special purpose registers.
> (rs6000_debug_reg_global): Print -mlra, -mconstrain-regs status if
> debugging.
> (rs6000_init_hard_regno_mode_ok): Mark that SFmode can use Altivec
> registers in the future.
> (rs6000_option_override_internal): If tuning for power8, turn on
> fusion mode by default. Turn on sign extending fusion mode if
> normal fusion mode is on, and we are at -O2 or -O3.
> (rs6000_opt_masks): Add -mlra, -mconstrain-regs.
> (fusion_gpr_load_p): New function, return true if we can fuse an
> addis instruction with a dependent load to a GPR.
> (emit_fusion_gpr_load): Emit the instructions for power8 load
> fusion to GPRs.
>
> * config/rs6000/vsx.md (VSX load fusion peepholes): Add peepholes
> to fuse together an addi instruction with a VSX load instruction.
>
> * config/rs6000/rs6000.md (GPR load fusion peepholes): Add
> peepholes to fuse an addis instruction with a load to a GPR base
> register, if the addis instruction is dead after the load, by
> using the register to be loaded for the addis. If we are
> supporting sign extending fusions, convert sign extending loads to
> zero extending loads and an explicit sign extension.
+ /* 32-bit is not done yet. */
+ if (TARGET_ELF && !TARGET_POWERPC64)
+ return 0;
What does "32-bit is not done yet." mean? This means PPC32 Linux is
not supported but PPC32 AIX is supported?
+ if (TARGET_ELF && !TARGET_POWERPC64)
+ return 0;
Please return "true" and "false" from new predicates, not "1" and "0".
+
+ case DImode:
+ if (TARGET_POWERPC64)
+ {
+ mode_name = "long";
+ load_str = "ld";
+ }
+ break;
What happens for DImode when not TARGET_POWERPC64? This should be
gcc_unreachable()?
Thanks, David
next prev parent reply other threads:[~2013-06-18 18:30 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-05-20 20:41 [PATCH, rs6000] power8 patches Michael Meissner
2013-05-20 20:49 ` [PATCH, rs6000] power8 patch #1, infrastructure changes Michael Meissner
2013-05-20 21:34 ` [PATCH, rs6000] power8 patch #1, infrastructure changes (revised patch) Michael Meissner
2013-05-22 3:29 ` David Edelsohn
2013-05-20 23:13 ` [PATCH, rs6000] power8 patches, patch #2, add crypto builtins Michael Meissner
2013-05-22 3:30 ` David Edelsohn
2013-05-23 3:41 ` David Edelsohn
2013-05-23 3:59 ` Michael Meissner
2013-05-25 4:07 ` David Edelsohn
2013-05-30 21:04 ` Michael Meissner
2013-05-21 2:11 ` [PATCH, rs6000] power8 patches Peter Bergner
2013-05-21 15:51 ` [PATCH, rs6000] power8 patches, patch #3, add V2DI vector support Michael Meissner
2013-05-23 16:31 ` David Edelsohn
2013-05-21 23:47 ` [PATCH, rs6000] power8 patches, patch #4, new power8 builtins Michael Meissner
2013-05-25 4:03 ` David Edelsohn
2013-05-30 23:26 ` Michael Meissner
2013-05-31 9:14 ` Segher Boessenkool
2013-05-31 15:11 ` Michael Meissner
2013-06-04 18:49 ` [PATCH, rs6000] power8 patches, patch #4 (revised), " Michael Meissner
2013-06-05 14:28 ` David Edelsohn
2013-06-05 15:50 ` Segher Boessenkool
2013-06-05 16:05 ` Michael Meissner
2013-06-05 20:06 ` Segher Boessenkool
2013-06-05 20:24 ` Michael Meissner
2013-06-05 16:13 ` Michael Meissner
2013-06-05 17:28 ` David Edelsohn
2013-06-06 15:57 ` David Edelsohn
2013-06-06 21:42 ` Michael Meissner
2013-07-15 21:48 ` Michael Meissner
2013-07-20 19:12 ` David Edelsohn
2013-07-23 21:24 ` Michael Meissner
2013-05-21 23:49 ` [PATCH, rs6000] power8 patches, patch #5, new vector tests Michael Meissner
2013-06-06 21:51 ` Michael Meissner
2013-05-22 14:26 ` [PATCH, rs6000] power8 patches, patch #6, direct move & basic quad load/store Michael Meissner
2013-05-29 19:53 ` David Edelsohn
2013-05-29 20:32 ` Michael Meissner
2013-06-10 15:41 ` David Edelsohn
2013-06-10 20:26 ` Michael Meissner
2013-05-22 16:51 ` [PATCH, rs6000] power8 patches, patch #7, quad/byte/half-word atomic instructions Michael Meissner
2013-05-29 20:29 ` David Edelsohn
2013-05-29 20:36 ` Michael Meissner
2013-06-11 23:56 ` Michael Meissner
2013-06-12 21:55 ` David Edelsohn
2013-05-22 20:53 ` [PATCH, rs6000] power8 patches, patch #8, power8 load fusion + misc Michael Meissner
2013-06-18 18:30 ` David Edelsohn [this message]
2013-06-24 16:32 ` Michael Meissner
2013-06-24 19:43 ` David Edelsohn
2013-07-29 18:46 ` [PATCH, rs6000] power8 patches, revised patch #8, power8 load fusion Michael Meissner
2013-07-31 16:00 ` David Edelsohn
2013-11-23 16:48 ` Alan Modra
2013-06-07 19:22 ` [PATCH, rs6000] power8 patches, patch #9, power8 scheduling Pat Haugen
2013-06-19 13:00 ` David Edelsohn
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAGWvnymmrzNTRetXT6gWu2AHNpCrkui1koKLNB-PSCt=eG_RXw@mail.gmail.com' \
--to=dje.gcc@gmail.com \
--cc=bergner@vnet.ibm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=meissner@linux.vnet.ibm.com \
--cc=pthaugen@us.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).