From: Jeff Law <jeffreyalaw@gmail.com>
To: Vineet Gupta <vineetg@rivosinc.com>, gcc@gcc.gnu.org
Cc: Kito Cheng <kito.cheng@sifive.com>,
Philipp Tomsich <philipp.tomsich@vrull.eu>
Subject: Re: Redundant constants in coremark crc8 for RISCV/aarch64 (no-if-conversion)
Date: Tue, 18 Oct 2022 21:42:25 -0600 [thread overview]
Message-ID: <8cbea421-5130-6d37-06a2-42ec7daef5cc@gmail.com> (raw)
In-Reply-To: <f97b82d4-305e-6e38-ffac-6c214ad310b4@rivosinc.com>
On 10/18/22 20:09, Vineet Gupta wrote:
>
> On 10/18/22 16:36, Jeff Law wrote:
>>>> There isn't a great place in GCC to handle this right now. If the
>>>> constraints were relaxed in PRE, then we'd have a chance, but
>>>> getting the cost model right is going to be tough.
>>>
>>> It would have been better (for this specific case) if loop unrolling
>>> was not being done so early. The tree pass cunroll is flattening it
>>> out and leaving for rest of the all tree/rtl passes to pick up the
>>> pieces and remove any redundancies, if at all. It obviously needs to
>>> be early if we are injecting 7x more instructions, but seems like a
>>> lot to unravel.
>>
>> Yup. If that loop gets unrolled, it's going to be a mess. It will
>> almost certainly make this problem worse as each iteration is going
>> to have a pair of constants loaded and no good way to remove them.
>
> Thats the original problem that I started this thread with. I'd
> snipped the disassembly as it would have been too much text but
> basically on RV, Coremark crc8 loop of const 8 iterations gets
> unrolled including extraneous 8 insns pairs to load the same constant
> - which is preposterous. Other arches side-step by using if-conversion
> / cond moves, latter currently WIP in RV International. x86 w/o
> if-convert seems OK since the const can be encoded in the xor insn.
>
> OTOH given that gimple/tree-pass cunroll is doing the culprit loop
> unrolling and introducing redundant const 8 times, can it ne addressed
> there somehow.
> tree_estimate_loop_size() seems to identify constant expression, not
> just an operand. Can it be taught to identify a "non-trivial const"
> and hoist/code-move the expression. Sorry just rambling here, most
> likely non-sense.
Oh, cunroll. There might be a distinct flag for complete unrolling.
I really expect something like Click's work is the way forward.
Essentially when you VN the function you'll identify those constants and
collapse them all down to a single instance. Then the GCM phase will
kick in and find a place to put the evaluation so that you have one and
only one.
Some of Bodik's work might catch it as well, though implementing his
ideas is likely a lot more work.
Jeff
next prev parent reply other threads:[~2022-10-19 3:42 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-14 15:56 Vineet Gupta
2022-10-14 16:54 ` Jeff Law
2022-10-18 21:51 ` Vineet Gupta
2022-10-18 23:36 ` Jeff Law
2022-10-19 2:09 ` Vineet Gupta
2022-10-19 3:42 ` Jeff Law [this message]
2022-10-19 7:46 ` Richard Biener
2022-10-19 13:30 ` Jeff Law
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=8cbea421-5130-6d37-06a2-42ec7daef5cc@gmail.com \
--to=jeffreyalaw@gmail.com \
--cc=gcc@gcc.gnu.org \
--cc=kito.cheng@sifive.com \
--cc=philipp.tomsich@vrull.eu \
--cc=vineetg@rivosinc.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).