From: Richard Acayan <mailingradian@gmail.com>
To: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Cc: Bjorn Andersson <andersson@kernel.org>,
Konrad Dybcio <konradybcio@kernel.org>,
Conor Dooley <conor@kernel.org>,
Jonathan Cameron <jonathan.cameron@huawei.com>,
Rob Herring <robh@kernel.org>,
Krzysztof Kozlowski <krzk+dt@kernel.org>,
linux-arm-msm@vger.kernel.org, devicetree@vger.kernel.org
Subject: Re: [PATCH 2/3] soc: qcom: llcc: Add configuration data for SDM670
Date: Wed, 11 Feb 2026 14:21:12 -0500 [thread overview]
Message-ID: <aYzWqFybymwd17Dx@rdacayan> (raw)
In-Reply-To: <026ce34c-c880-4832-a791-656fb245a495@oss.qualcomm.com>
On Tue, Feb 10, 2026 at 10:27:40AM +0100, Konrad Dybcio wrote:
> On 2/10/26 3:19 AM, Richard Acayan wrote:
> > Add system cache table and configs for the SDM670 SoC.
> >
> > Signed-off-by: Richard Acayan <mailingradian@gmail.com>
> > ---
>
> I have a clone of some msm-4.9 on my ssd and it roughly matches this
> patch
>
> However
>
> In docs, I see a version with only CPU_SS, MODEM and MMUHWT left
> (your settings here seem to match), dated later than the last commit
> to llcc-sdm670.c in that downstream kernel clone..
>
> Because this SoC seems to only have 512KiB of LLC in total, it may
> be that it was found in testing for that configuration to have a
> better perf profile
>
> Could you please give it a shot and check if you see any immediate
> gains/losses?
I don't notice a difference outside the margin of error. The Unixbench
workload reported 4550.4 with all configs, and 4550.9 with only
LLCC_CPUSS, LLCC_MDM, and LLCC_MMUHWT. My 15-second workload on
Hexagon/CDSP was half a second faster when commenting out the cache use
cases.
I don't see better startup times either.
next prev parent reply other threads:[~2026-02-11 19:20 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-10 2:19 [PATCH 0/3] SDM670 cache controller support Richard Acayan
2026-02-10 2:19 ` [PATCH 1/3] dt-bindings: cache: qcom,llcc: Add SDM670 compatible Richard Acayan
2026-02-10 9:27 ` Krzysztof Kozlowski
2026-02-10 2:19 ` [PATCH 2/3] soc: qcom: llcc: Add configuration data for SDM670 Richard Acayan
2026-02-10 9:27 ` Konrad Dybcio
2026-02-11 19:21 ` Richard Acayan [this message]
2026-02-12 10:06 ` Konrad Dybcio
2026-02-10 9:29 ` Konrad Dybcio
2026-02-11 0:32 ` Richard Acayan
2026-02-10 2:19 ` [PATCH 3/3] arm64: dts: qcom: sdm670: add llcc Richard Acayan
2026-02-10 9:28 ` Konrad Dybcio
2026-03-16 2:02 ` (subset) [PATCH 0/3] SDM670 cache controller support Bjorn Andersson
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=aYzWqFybymwd17Dx@rdacayan \
--to=mailingradian@gmail.com \
--cc=andersson@kernel.org \
--cc=conor@kernel.org \
--cc=devicetree@vger.kernel.org \
--cc=jonathan.cameron@huawei.com \
--cc=konrad.dybcio@oss.qualcomm.com \
--cc=konradybcio@kernel.org \
--cc=krzk+dt@kernel.org \
--cc=linux-arm-msm@vger.kernel.org \
--cc=robh@kernel.org \
/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