From: "juzhe.zhong@rivai.ai" <juzhe.zhong@rivai.ai>
To: richard.sandiford <richard.sandiford@arm.com>
Cc: gcc-patches <gcc-patches@gcc.gnu.org>,
rguenther <rguenther@suse.de>, linkw <linkw@linux.ibm.com>
Subject: Re: Re: [PATCH] VECT: Change flow of decrement IV
Date: Tue, 30 May 2023 19:36:28 +0800 [thread overview]
Message-ID: <BA06748B70B6FC07+20230530193628082710370@rivai.ai> (raw)
In-Reply-To: <mptedmy838e.fsf@arm.com>
[-- Attachment #1: Type: text/plain, Size: 1732 bytes --]
Before this patch:
foo:
ble a2,zero,.L5
csrr a3,vlenb
srli a4,a3,2
.L3:
minu a5,a2,a4
vsetvli zero,a5,e32,m1,ta,ma
vle32.v v2,0(a1)
vle32.v v1,0(a0)
vsetvli t1,zero,e32,m1,ta,ma
vadd.vv v1,v1,v2
vsetvli zero,a5,e32,m1,ta,ma
vse32.v v1,0(a0)
add a1,a1,a3
add a0,a0,a3
sub a2,a2,a5
bne a2,zero,.L3
.L5:
ret
After this patch:
foo:
ble a2,zero,.L5
csrr a3,vlenb
srli a4,a3,2
neg a7,a4 -->>>additional instruction
.L3:
minu a5,a2,a4
vsetvli zero,a5,e32,m1,ta,ma
vle32.v v2,0(a1)
vle32.v v1,0(a0)
vsetvli t1,zero,e32,m1,ta,ma
mv a6,a2 -->>>additional instruction
vadd.vv v1,v1,v2
vsetvli zero,a5,e32,m1,ta,ma
vse32.v v1,0(a0)
add a1,a1,a3
add a0,a0,a3
add a2,a2,a7
bgtu a6,a4,.L3
.L5:
ret
There is 1 more instruction in preheader and 1 more instruction in loop.
But I think it's OK for RVV since we will definitely be using SELECT_VL so this issue will gone.
As long as this flow is better to power (SCEV)。
juzhe.zhong@rivai.ai
From: Richard Sandiford
Date: 2023-05-30 19:31
To: juzhe.zhong
CC: gcc-patches; rguenther; linkw
Subject: Re: [PATCH] VECT: Change flow of decrement IV
juzhe.zhong@rivai.ai writes:
> From: Ju-Zhe Zhong <juzhe.zhong@rivai.ai>
>
> Follow Richi's suggestion, I change current decrement IV flow from:
>
> do {
> remain -= MIN (vf, remain);
> } while (remain != 0);
>
> into:
>
> do {
> old_remain = remain;
> len = MIN (vf, remain);
> remain -= vf;
> } while (old_remain >= vf);
>
> to enhance SCEV.
>
> ALL tests (decrement IV) of RVV are passed.
How does it affect RVV code quality? I thought you specifically chose
the previous approach because code quality was better that way.
Richard
next prev parent reply other threads:[~2023-05-30 11:36 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-30 11:28 juzhe.zhong
2023-05-30 11:31 ` Richard Sandiford
2023-05-30 11:36 ` juzhe.zhong [this message]
2023-05-30 11:41 ` Richard Sandiford
[not found] ` <5C7770CA9FB40F7E+8BE427DD-97DA-4B93-A73A-8CDD1D92089B@rivai.ai>
2023-05-30 12:01 ` Richard Sandiford
[not found] ` <685EE879E20B3272+6338EB42-0A9D-4147-993D-99DC8FF7C832@rivai.ai>
2023-05-30 12:33 ` Richard Biener
2023-05-30 12:37 ` 钟居哲
[not found] ` <FA43CAC5-BCCE-42AF-8A6B-E69F1A496F5C@suse.de>
2023-05-30 22:51 ` 钟居哲
2023-05-30 14:13 ` 钟居哲
2023-05-30 14:47 ` 钟居哲
2023-05-30 15:05 ` 钟居哲
2023-05-31 1:42 ` juzhe.zhong
2023-05-31 6:41 ` Richard Biener
2023-05-31 6:50 ` juzhe.zhong
2023-05-31 7:38 ` Kewen.Lin
2023-05-31 7:50 ` juzhe.zhong
2023-05-31 7:28 ` Richard Sandiford
2023-05-31 7:36 ` juzhe.zhong
2023-05-31 8:44 ` Richard Biener
2023-05-31 7:38 ` Richard Biener
2023-05-31 7:49 ` juzhe.zhong
2023-05-31 9:01 ` Richard Sandiford
2023-05-31 9:30 ` juzhe.zhong
2023-05-31 10:53 ` Richard Biener
2023-05-31 12:16 ` 钟居哲
2023-05-30 11:38 ` juzhe.zhong
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=BA06748B70B6FC07+20230530193628082710370@rivai.ai \
--to=juzhe.zhong@rivai.ai \
--cc=gcc-patches@gcc.gnu.org \
--cc=linkw@linux.ibm.com \
--cc=rguenther@suse.de \
--cc=richard.sandiford@arm.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).