From: Eric Biggers <ebiggers@kernel.org>
To: Paolo Savini <paolo.savini@embecosm.com>
Cc: qemu-devel@nongnu.org, qemu-riscv@nongnu.org,
Richard Handerson <richard.henderson@linaro.org>,
Palmer Dabbelt <palmer@dabbelt.com>,
Alistair Francis <alistair.francis@wdc.com>,
Bin Meng <bmeng.cn@gmail.com>, Weiwei Li <liwei1518@gmail.com>,
Daniel Henrique Barboza <dbarboza@ventanamicro.com>,
Liu Zhiwei <zhiwei_liu@linux.alibaba.com>,
Helene Chelin <helene.chelin@embecosm.com>,
Nathan Egge <negge@google.com>, Max Chou <max.chou@sifive.com>,
Jeremy Bennett <jeremy.bennett@embecosm.com>,
Craig Blackmore <craig.blackmore@embecosm.com>,
Ard Biesheuvel <ardb@kernel.org>,
"Jason A. Donenfeld" <Jason@zx2c4.com>
Subject: Re: [PATCH 1/1 v2] [RISC-V/RVV] Generate strided vector loads/stores with tcg nodes.
Date: Wed, 9 Jul 2025 22:28:24 -0700 [thread overview]
Message-ID: <20250710052824.GA608727@sol> (raw)
In-Reply-To: <20250312155547.289642-2-paolo.savini@embecosm.com>
Hi,
On Wed, Mar 12, 2025 at 03:55:47PM +0000, Paolo Savini wrote:
> This commit improves the performance of QEMU when emulating strided vector
> loads and stores by substituting the call for the helper function with the
> generation of equivalent TCG operations.
>
> Signed-off-by: Paolo Savini <paolo.savini@embecosm.com>
> Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
> ---
> target/riscv/insn_trans/trans_rvv.c.inc | 323 ++++++++++++++++++++----
> 1 file changed, 273 insertions(+), 50 deletions(-)
This recent QEMU patch broke the RISC-V vector optimized ChaCha20 code
in the Linux kernel. I simplified the reproducer to the following,
which had its behavior changed:
rvv_test_func:
vsetivli zero, 1, e32, m1, ta, ma
li t0, 64
vlsseg8e32.v v0, (a0), t0
addi a0, a0, 32
vlsseg8e32.v v8, (a0), t0
vssseg8e32.v v0, (a1), t0
addi a1, a1, 32
vssseg8e32.v v8, (a1), t0
ret
Before this patch, it copied 64 bytes from a0 to a1. After this patch,
the bytes at 32..47 also incorrectly get copied to 16..31.
Please fix this, or else revert the patch.
- Eric
next prev parent reply other threads:[~2025-07-10 12:58 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-12 15:55 [PATCH 0/1 v2] [RISCV/RVV] Generate strided vector loads/stores with tcg nodes Paolo Savini
2025-03-12 15:55 ` [PATCH 1/1 v2] [RISC-V/RVV] " Paolo Savini
2025-07-10 5:28 ` Eric Biggers [this message]
2025-07-10 9:54 ` Daniel Henrique Barboza
2025-07-10 12:40 ` Paolo Savini
2025-04-04 1:46 ` [PATCH 0/1 v2] [RISCV/RVV] " Alistair Francis
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=20250710052824.GA608727@sol \
--to=ebiggers@kernel.org \
--cc=Jason@zx2c4.com \
--cc=alistair.francis@wdc.com \
--cc=ardb@kernel.org \
--cc=bmeng.cn@gmail.com \
--cc=craig.blackmore@embecosm.com \
--cc=dbarboza@ventanamicro.com \
--cc=helene.chelin@embecosm.com \
--cc=jeremy.bennett@embecosm.com \
--cc=liwei1518@gmail.com \
--cc=max.chou@sifive.com \
--cc=negge@google.com \
--cc=palmer@dabbelt.com \
--cc=paolo.savini@embecosm.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-riscv@nongnu.org \
--cc=richard.henderson@linaro.org \
--cc=zhiwei_liu@linux.alibaba.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.