public inbox for linuxppc-dev@ozlabs.org 
 help / color / mirror / Atom feed
From: Segher Boessenkool <segher@kernel•crashing.org>
To: Nicholas Piggin <npiggin@gmail•com>
Cc: linuxppc-dev@lists•ozlabs.org, Alan Modra <amodra@gmail•com>
Subject: Re: [RFC PATCH 5/7] powerpc/64s: update generic cpu option name and compiler flags
Date: Tue, 20 Sep 2022 17:16:08 -0500	[thread overview]
Message-ID: <20220920221608.GB25951@gate.crashing.org> (raw)
In-Reply-To: <20220919140149.4018927-6-npiggin@gmail.com>

Hi!

On Tue, Sep 20, 2022 at 12:01:47AM +1000, Nicholas Piggin wrote:
> Update the 64s GENERIC_CPU option. POWER4 support has been dropped, so
> make that clear in the option name.

AFAIR the minimum now is POWER4+ (ISA 2.01), not POWER5 (ISA 2.02).

> -mtune= before power8 is dropped because the minimum gcc version
> supports power8, and tuning is made consistent between big and little
> endian.

Tuning for p8 on e.g. 970 gives quite bad results.  No idea if anyone
cares, but this is a serious regression if so.

> Big endian drops -mcpu=power4 in favour of power5. Effectively the
> minimum compiler version means power5 was always being selected here,
> so this should not change anything. 970 / G5 code generation does not
> seem to have been a problem with -mcpu=power5, but it's possible we
> should go back to power4 to be really safe.

Yes, -mcpu=power5 code does *not* run on 970, if you are unlucky enough
that the compiler does something smart with popcntb (the sole non-float
insn new on p5, not counting hrfid).

> +# -mcpu=power5 should generate 970 compatible kernel code

It doesn't.  Even if it did, it would need more explanation!


Segher

  reply	other threads:[~2022-09-20 22:18 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-19 14:01 [RFC PATCH 0/7] powerpc: first hack at pcrel addressing Nicholas Piggin
2022-09-19 14:01 ` [RFC PATCH 1/7] powerpc: use 16-bit immediate for STACK_FRAME_REGS_MARKER Nicholas Piggin
2022-09-21 16:49   ` Christophe Leroy
2022-09-23  7:32     ` Michael Ellerman
2022-09-23  7:35       ` Christophe Leroy
2022-09-19 14:01 ` [RFC PATCH 2/7] powerpc/64: abstract asm global variable declaration and access Nicholas Piggin
2022-09-21 16:51   ` Christophe Leroy
2022-09-19 14:01 ` [RFC PATCH 3/7] powerpc/64: provide a helper macro to load r2 with the kernel TOC Nicholas Piggin
2022-09-21 16:52   ` Christophe Leroy
2022-09-19 14:01 ` [RFC PATCH 4/7] powerpc: add CFUNC assembly label annotation Nicholas Piggin
2022-09-19 14:01 ` [RFC PATCH 5/7] powerpc/64s: update generic cpu option name and compiler flags Nicholas Piggin
2022-09-20 22:16   ` Segher Boessenkool [this message]
2022-09-21  1:01     ` Nicholas Piggin
2022-09-21 15:22       ` Segher Boessenkool
2022-09-23  7:22         ` Nicholas Piggin
2022-09-19 14:01 ` [RFC PATCH 6/7] powerpc/64s: POWER10 CPU Kconfig build option Nicholas Piggin
2022-09-19 14:01 ` [RFC PATCH 7/7] powerpc/64s: Add option to build vmlinux with pcrel addressing Nicholas Piggin

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=20220920221608.GB25951@gate.crashing.org \
    --to=segher@kernel$(echo .)crashing.org \
    --cc=amodra@gmail$(echo .)com \
    --cc=linuxppc-dev@lists$(echo .)ozlabs.org \
    --cc=npiggin@gmail$(echo .)com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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