From: Daniel Drake <ddrake@baylibre.com>
To: Jiaxing Hu <gahing@gahingwoo.com>,
tomeu@tomeuvizoso.net, heiko@sntech.de, robh@kernel.org,
krzk+dt@kernel.org, conor+dt@kernel.org, joro@8bytes.org,
will@kernel.org, robin.murphy@arm.com, p.zabel@pengutronix.de,
ogabbay@kernel.org, zhangqing@rock-chips.com
Cc: royalnet026@gmail.com, ulf.hansson@oss.qualcomm.com,
abel.vesa@oss.qualcomm.com, sebastian.reichel@collabora.com,
sidong.yang@furiosa.ai, u.kleine-koenig@baylibre.com,
chaoyi.chen@rock-chips.com, shawn.lin@rock-chips.com,
finley.xiao@rock-chips.com, diederik@cknow-tech.com,
alchark@flipper.net, leonard@lausen.nl, vlwwwwww@gmail.com,
jeff.hugo@oss.qualcomm.com, rfoss@kernel.org,
dri-devel@lists.freedesktop.org,
linux-rockchip@lists.infradead.org, iommu@lists.linux.dev,
devicetree@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v17 11/12] arm64: dts: rockchip: add NPU (RKNN) nodes to rk3576
Date: Wed, 18 Nov 2026 12:28:19 +0000 [thread overview]
Message-ID: <49a9337f-6808-4f30-b826-9a280849a51c@baylibre.com> (raw)
In-Reply-To: <f9f4f43cd1c4c8c6cee0371b4b92badf37e68832.1794615323.git.gahing@gahingwoo.com>
Hi,
On 14/11/2026 03:05, Jiaxing Hu wrote:
> Each core is on its own power domain only: core 0 on PD_NPU0, core 1 on
> PD_NPU1. Measured with both cores running, the results are correct, and
> the nputop and npu domains above them are powered through the domain
> hierarchy.
No need to include lab notes; we assume you tested this work and found
it to be working before submission.
> Label PD_NPU so a board can connect the NPU supply. The IOMMUs use four
> clocks.
>
> Also set CLK_RKNN_DSU0 to 594 MHz. Mainline sets neither its rate nor the
> NPU voltage. On the ROCK 4D the DSU runs at 786 MHz by default and the
> rail boots at 750 mV; with both cores running, each pass of the 5400-row
> test has 11 to 25 wrong words. At 594 MHz the test is all correct. In the
> vendor OPP table, the 500 MHz and 600 MHz steps both need 725 mV.
I found this wording a bit confusing. I think you're saying, the system
boots into Linux with 786MHz & 750mV, and that configuration gives bad
results.
I'm not clear why you picked 594 Hz then. What does the vendor kernel
do, are you matching that behaviour?
next prev parent reply other threads:[~2026-11-18 12:28 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-14 3:05 [PATCH v17 00/12] accel/rocket: RK3576 NPU (RKNN) enablement Jiaxing Hu
2026-11-14 3:05 ` [PATCH v17 01/12] accel/rocket: request the core clocks by name Jiaxing Hu
2026-11-14 3:05 ` [PATCH v17 02/12] accel/rocket: take the completion register writes under job_lock Jiaxing Hu
2026-11-14 3:05 ` [PATCH v17 03/12] accel/rocket: wait for a running IRQ handler before resetting a core Jiaxing Hu
2026-11-15 13:16 ` Heiko Stübner
2026-11-14 3:05 ` [PATCH v17 04/12] accel/rocket: let the core suspend after a reset Jiaxing Hu
2026-11-18 12:27 ` Daniel Drake
2026-11-14 3:05 ` [PATCH v17 05/12] accel/rocket: factor the completion tail out of the IRQ handler Jiaxing Hu
2026-11-14 3:05 ` [PATCH v17 06/12] dt-bindings: npu: rockchip: add rockchip,rk3576-rknn-core Jiaxing Hu
2026-11-14 3:05 ` [PATCH v17 07/12] dt-bindings: iommu: rockchip: describe the RK3576 NPU MMU Jiaxing Hu
2026-11-14 3:05 ` [PATCH v17 08/12] accel/rocket: select the per-core clock and reset counts from match data Jiaxing Hu
2026-11-18 12:27 ` Daniel Drake
2026-11-14 3:05 ` [PATCH v17 09/12] accel/rocket: add RK3576 NPU (RKNN) support Jiaxing Hu
2026-11-18 12:28 ` Daniel Drake
2026-11-14 3:05 ` [PATCH v17 10/12] accel/rocket: add a GET_PARAM ioctl for the hardware version Jiaxing Hu
2026-11-18 12:28 ` Daniel Drake
2026-11-14 3:05 ` [PATCH v17 11/12] arm64: dts: rockchip: add NPU (RKNN) nodes to rk3576 Jiaxing Hu
2026-11-18 12:28 ` Daniel Drake [this message]
2026-11-14 3:05 ` [PATCH v17 12/12] arm64: dts: rockchip: enable the NPU on rk3576-rock-4d Jiaxing Hu
2026-11-18 12:28 ` Daniel Drake
2026-11-14 12:54 ` [PATCH v17 00/12] accel/rocket: RK3576 NPU (RKNN) enablement Sidong Yang
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=49a9337f-6808-4f30-b826-9a280849a51c@baylibre.com \
--to=ddrake@baylibre.com \
--cc=abel.vesa@oss.qualcomm.com \
--cc=alchark@flipper.net \
--cc=chaoyi.chen@rock-chips.com \
--cc=conor+dt@kernel.org \
--cc=devicetree@vger.kernel.org \
--cc=diederik@cknow-tech.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=finley.xiao@rock-chips.com \
--cc=gahing@gahingwoo.com \
--cc=heiko@sntech.de \
--cc=iommu@lists.linux.dev \
--cc=jeff.hugo@oss.qualcomm.com \
--cc=joro@8bytes.org \
--cc=krzk+dt@kernel.org \
--cc=leonard@lausen.nl \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rockchip@lists.infradead.org \
--cc=ogabbay@kernel.org \
--cc=p.zabel@pengutronix.de \
--cc=rfoss@kernel.org \
--cc=robh@kernel.org \
--cc=robin.murphy@arm.com \
--cc=royalnet026@gmail.com \
--cc=sebastian.reichel@collabora.com \
--cc=shawn.lin@rock-chips.com \
--cc=sidong.yang@furiosa.ai \
--cc=tomeu@tomeuvizoso.net \
--cc=u.kleine-koenig@baylibre.com \
--cc=ulf.hansson@oss.qualcomm.com \
--cc=vlwwwwww@gmail.com \
--cc=will@kernel.org \
--cc=zhangqing@rock-chips.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
all inboxes | Powered by JetHome®