Committed, thanks Kito.
Pan
-Original Message-
From: Kito Cheng
Sent: Friday, November 24, 2023 2:30 PM
To: Juzhe-Zhong
Cc: gcc-patches@gcc.gnu.org; kito.ch...@gmail.com; jeffreya...@gmail.com;
rdapp@gmail.com
Subject: Re: [PATCH V2] RISC-V: Optimize a special case of VLA SLP
The optimization is relatively small, so LGTM, thanks :)
On Fri, Nov 24, 2023 at 7:18 AM Juzhe-Zhong wrote:
>
> When working on fixing bugs of zvl1024b. I notice a special VLA SLP case
> can be better optimized.
>
> v = vec_perm (op1, op2, { nunits - 1, nunits, nunits + 1, ... })
>
> Before this
When working on fixing bugs of zvl1024b. I notice a special VLA SLP case
can be better optimized.
v = vec_perm (op1, op2, { nunits - 1, nunits, nunits + 1, ... })
Before this patch, we are using genriec approach (vrgather):
vid
vadd.vx
vrgather
vmsgeu
vrgather
With this patch, we use vec_extrac
