From: Jisheng Zhang <jszhang3@mail.ustc.edu.cn>
To: Greentime Hu <greentime.hu@sifive.com>
Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
aou@eecs.berkeley.edu, palmer@dabbelt.com,
paul.walmsley@sifive.com, vincent.chen@sifive.com
Subject: Re: [RFC PATCH v8 20/21] riscv: Optimize task switch codes of vector
Date: Wed, 15 Sep 2021 22:29:37 +0800 [thread overview]
Message-ID: <20210915222937.49066323@xhacker> (raw)
In-Reply-To: <3b2d4ff556d310ed73a6910b89566a195fc28861.1631121222.git.greentime.hu@sifive.com>
On Thu, 9 Sep 2021 01:45:32 +0800
Greentime Hu <greentime.hu@sifive.com> wrote:
> This patch replacees 2 instructions with 1 instruction to do the same thing
> . rs1=x0 with rd != x0 is a special form of the instruction that sets vl to
> MAXVL.
Similarly, the vector.S is newly introduced in this patch set, so could
this optimization be folded into the __vstate_save and __vstate_restore
introduction patch? Or it's better to keep this optimizaion in commit log?
>
> Suggested-by: Andrew Waterman <andrew@sifive.com>
> Co-developed-by: Vincent Chen <vincent.chen@sifive.com>
> Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
> Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
> ---
> arch/riscv/kernel/vector.S | 9 +++------
> 1 file changed, 3 insertions(+), 6 deletions(-)
>
> diff --git a/arch/riscv/kernel/vector.S b/arch/riscv/kernel/vector.S
> index 4f0c5a166e4e..f7223c81b11a 100644
> --- a/arch/riscv/kernel/vector.S
> +++ b/arch/riscv/kernel/vector.S
> @@ -27,8 +27,7 @@
> #define x_vl t2
> #define x_vcsr t3
> #define incr t4
> -#define m_one t5
> -#define status t6
> +#define status t5
>
> ENTRY(__vstate_save)
> li status, SR_VS
> @@ -38,8 +37,7 @@ ENTRY(__vstate_save)
> csrr x_vtype, CSR_VTYPE
> csrr x_vl, CSR_VL
> csrr x_vcsr, CSR_VCSR
> - li m_one, -1
> - vsetvli incr, m_one, e8, m8
> + vsetvli incr, x0, e8, m8
> vse8.v v0, (datap)
> add datap, datap, incr
> vse8.v v8, (datap)
> @@ -61,8 +59,7 @@ ENTRY(__vstate_restore)
> li status, SR_VS
> csrs CSR_STATUS, status
>
> - li m_one, -1
> - vsetvli incr, m_one, e8, m8
> + vsetvli incr, x0, e8, m8
> vle8.v v0, (datap)
> add datap, datap, incr
> vle8.v v8, (datap)
_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv
WARNING: multiple messages have this Message-ID (diff)
From: Jisheng Zhang <jszhang3@mail.ustc.edu.cn>
To: Greentime Hu <greentime.hu@sifive.com>
Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
aou@eecs.berkeley.edu, palmer@dabbelt.com,
paul.walmsley@sifive.com, vincent.chen@sifive.com
Subject: Re: [RFC PATCH v8 20/21] riscv: Optimize task switch codes of vector
Date: Wed, 15 Sep 2021 22:29:37 +0800 [thread overview]
Message-ID: <20210915222937.49066323@xhacker> (raw)
In-Reply-To: <3b2d4ff556d310ed73a6910b89566a195fc28861.1631121222.git.greentime.hu@sifive.com>
On Thu, 9 Sep 2021 01:45:32 +0800
Greentime Hu <greentime.hu@sifive.com> wrote:
> This patch replacees 2 instructions with 1 instruction to do the same thing
> . rs1=x0 with rd != x0 is a special form of the instruction that sets vl to
> MAXVL.
Similarly, the vector.S is newly introduced in this patch set, so could
this optimization be folded into the __vstate_save and __vstate_restore
introduction patch? Or it's better to keep this optimizaion in commit log?
>
> Suggested-by: Andrew Waterman <andrew@sifive.com>
> Co-developed-by: Vincent Chen <vincent.chen@sifive.com>
> Signed-off-by: Vincent Chen <vincent.chen@sifive.com>
> Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
> ---
> arch/riscv/kernel/vector.S | 9 +++------
> 1 file changed, 3 insertions(+), 6 deletions(-)
>
> diff --git a/arch/riscv/kernel/vector.S b/arch/riscv/kernel/vector.S
> index 4f0c5a166e4e..f7223c81b11a 100644
> --- a/arch/riscv/kernel/vector.S
> +++ b/arch/riscv/kernel/vector.S
> @@ -27,8 +27,7 @@
> #define x_vl t2
> #define x_vcsr t3
> #define incr t4
> -#define m_one t5
> -#define status t6
> +#define status t5
>
> ENTRY(__vstate_save)
> li status, SR_VS
> @@ -38,8 +37,7 @@ ENTRY(__vstate_save)
> csrr x_vtype, CSR_VTYPE
> csrr x_vl, CSR_VL
> csrr x_vcsr, CSR_VCSR
> - li m_one, -1
> - vsetvli incr, m_one, e8, m8
> + vsetvli incr, x0, e8, m8
> vse8.v v0, (datap)
> add datap, datap, incr
> vse8.v v8, (datap)
> @@ -61,8 +59,7 @@ ENTRY(__vstate_restore)
> li status, SR_VS
> csrs CSR_STATUS, status
>
> - li m_one, -1
> - vsetvli incr, m_one, e8, m8
> + vsetvli incr, x0, e8, m8
> vle8.v v0, (datap)
> add datap, datap, incr
> vle8.v v8, (datap)
next prev parent reply other threads:[~2021-09-15 14:36 UTC|newest]
Thread overview: 112+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-08 17:45 [RFC PATCH v8 00/21] riscv: Add vector ISA support Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 01/21] riscv: Separate patch for cflags and aflags Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 02/21] riscv: Rename __switch_to_aux -> fpu Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 03/21] riscv: Extending cpufeature.c to detect V-extension Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 04/21] riscv: Add new csr defines related to vector extension Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 05/21] riscv: Add vector feature to compile Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 06/21] riscv: Add has_vector/riscv_vsize to save vector features Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 07/21] riscv: Reset vector register Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 08/21] riscv: Add vector struct and assembler definitions Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 09/21] riscv: Add task switch support for vector Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 20:47 ` kernel test robot
2021-09-08 20:47 ` kernel test robot
2021-09-13 12:21 ` Darius Rad
2021-09-13 12:21 ` Darius Rad
2021-09-28 14:56 ` Greentime Hu
2021-09-28 14:56 ` Greentime Hu
2021-09-29 13:28 ` Darius Rad
2021-09-29 13:28 ` Darius Rad
2021-10-01 2:46 ` Ley Foon Tan
2021-10-01 2:46 ` Ley Foon Tan
2021-10-04 12:41 ` Greentime Hu
2021-10-04 12:41 ` Greentime Hu
2021-10-05 2:12 ` Ley Foon Tan
2021-10-05 2:12 ` Ley Foon Tan
2021-10-05 15:46 ` Greentime Hu
2021-10-05 15:46 ` Greentime Hu
2021-10-07 10:10 ` Ley Foon Tan
2021-10-07 10:10 ` Ley Foon Tan
2021-10-04 12:36 ` Greentime Hu
2021-10-04 12:36 ` Greentime Hu
2021-10-05 13:57 ` Darius Rad
2021-10-05 13:57 ` Darius Rad
2021-10-21 1:01 ` Paul Walmsley
2021-10-21 1:01 ` Paul Walmsley
2021-10-21 10:50 ` Darius Rad
2021-10-21 10:50 ` Darius Rad
2021-10-22 3:52 ` Vincent Chen
2021-10-22 3:52 ` Vincent Chen
2021-10-22 10:40 ` Darius Rad
2021-10-22 10:40 ` Darius Rad
2021-10-25 4:47 ` Greentime Hu
2021-10-25 4:47 ` Greentime Hu
2021-10-25 16:22 ` Darius Rad
2021-10-25 16:22 ` Darius Rad
2021-10-26 4:44 ` Greentime Hu
2021-10-26 4:44 ` Greentime Hu
2021-10-27 12:58 ` Darius Rad
2021-10-27 12:58 ` Darius Rad
2021-11-09 9:49 ` Greentime Hu
2021-11-09 9:49 ` Greentime Hu
2021-11-09 19:21 ` Darius Rad
2021-11-09 19:21 ` Darius Rad
2021-10-26 14:58 ` Heiko Stübner
2021-10-26 14:58 ` Heiko Stübner
2021-09-08 17:45 ` [RFC PATCH v8 10/21] riscv: Add ptrace vector support Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 11/21] riscv: Add sigcontext save/restore for vector Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-30 2:37 ` Ley Foon Tan
2021-09-30 2:37 ` Ley Foon Tan
2021-09-08 17:45 ` [RFC PATCH v8 12/21] riscv: signal: Report signal frame size to userspace via auxv Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 13/21] riscv: Add support for kernel mode vector Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-09 6:17 ` Christoph Hellwig
2021-09-09 6:17 ` Christoph Hellwig
2021-09-08 17:45 ` [RFC PATCH v8 14/21] riscv: Use CSR_STATUS to replace sstatus in vector.S Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 15/21] riscv: Add vector extension XOR implementation Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-09 6:12 ` Christoph Hellwig
2021-09-09 6:12 ` Christoph Hellwig
2021-09-28 7:00 ` Greentime Hu
2021-09-28 7:00 ` Greentime Hu
2021-09-14 8:29 ` Ley Foon Tan
2021-09-14 8:29 ` Ley Foon Tan
2021-09-28 7:01 ` Greentime Hu
2021-09-28 7:01 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 16/21] riscv: Initialize vector registers with proper vsetvli then it can work normally Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 17/21] riscv: Optimize vector registers initialization Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 18/21] riscv: Fix an illegal instruction exception when accessing vlenb without enable vector first Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 19/21] riscv: Allocate space for vector registers in start_thread() Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 20/21] riscv: Optimize task switch codes of vector Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-15 14:29 ` Jisheng Zhang [this message]
2021-09-15 14:29 ` Jisheng Zhang
2021-10-04 14:13 ` Greentime Hu
2021-10-04 14:13 ` Greentime Hu
2021-09-08 17:45 ` [RFC PATCH v8 21/21] riscv: Turn has_vector into a static key if VECTOR=y Greentime Hu
2021-09-08 17:45 ` Greentime Hu
2021-09-15 14:24 ` Jisheng Zhang
2021-09-15 14:24 ` Jisheng Zhang
2021-10-04 15:04 ` Greentime Hu
2021-10-04 15:04 ` Greentime Hu
2021-09-13 1:47 ` [RFC PATCH v8 00/21] riscv: Add vector ISA support Vincent Chen
2021-09-13 1:47 ` Vincent Chen
2021-09-13 17:18 ` Vineet Gupta
2021-09-13 17:18 ` Vineet Gupta
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=20210915222937.49066323@xhacker \
--to=jszhang3@mail.ustc.edu.cn \
--cc=aou@eecs.berkeley.edu \
--cc=greentime.hu@sifive.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-riscv@lists.infradead.org \
--cc=palmer@dabbelt.com \
--cc=paul.walmsley@sifive.com \
--cc=vincent.chen@sifive.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.