From: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> To: robh+dt@kernel.org Cc: krzysztof.kozlowski+dt@linaro.org, matthias.bgg@gmail.com, tinghan.shen@mediatek.com, seiya.wang@mediatek.com, angelogioacchino.delregno@collabora.com, devicetree@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-mediatek@lists.infradead.org, linux-kernel@vger.kernel.org Subject: [PATCH] arm64: dts: mediatek: mt8195: Fix CPUs capacity-dmips-mhz Date: Wed, 5 Oct 2022 11:34:03 +0200 [thread overview] Message-ID: <20221005093404.33102-1-angelogioacchino.delregno@collabora.com> (raw) The capacity-dmips-mhz parameter was miscalculated: this SoC runs the first (Cortex-A55) cluster at a maximum of 2000MHz and the second (Cortex-A78) cluster at a maximum of 3000MHz. In order to calculate the right capacity-dmips-mhz, the following test was performed: 1. CPUFREQ governor was set to 'performance' on both clusters 2. Ran dhrystone with 500000000 iterations for 10 times on each cluster 3. Calculate the mean result for each cluster 4. Calculate DMIPS/MHz: dmips_mhz = dmips_per_second / cpu_mhz 5. Scale results to 1024: result_c0 = (dmips_mhz_c0 - min_dmips_mhz(c0, c1)) / (max_dmips_mhz(c0, c1) - min_dmips_mhz(c0, c1)) * 1024 The mean results for this SoC are: Cluster 0 (LITTLE): 11990400 Dhry/s Cluster 1 (BIG): 59809036 Dhry/s The calculated scaled results are: Cluster 0: 307,934312801831 (rounded to 308) Cluster 1: 1024 Fixes: 37f2582883be ("arm64: dts: Add mediatek SoC mt8195 and evaluation board") Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> --- arch/arm64/boot/dts/mediatek/mt8195.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index 905d1a90b406..0b85b5874a4f 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -36,7 +36,7 @@ cpu0: cpu@0 { enable-method = "psci"; performance-domains = <&performance 0>; clock-frequency = <1701000000>; - capacity-dmips-mhz = <578>; + capacity-dmips-mhz = <308>; cpu-idle-states = <&cpu_off_l &cluster_off_l>; next-level-cache = <&l2_0>; #cooling-cells = <2>; @@ -49,7 +49,7 @@ cpu1: cpu@100 { enable-method = "psci"; performance-domains = <&performance 0>; clock-frequency = <1701000000>; - capacity-dmips-mhz = <578>; + capacity-dmips-mhz = <308>; cpu-idle-states = <&cpu_off_l &cluster_off_l>; next-level-cache = <&l2_0>; #cooling-cells = <2>; @@ -62,7 +62,7 @@ cpu2: cpu@200 { enable-method = "psci"; performance-domains = <&performance 0>; clock-frequency = <1701000000>; - capacity-dmips-mhz = <578>; + capacity-dmips-mhz = <308>; cpu-idle-states = <&cpu_off_l &cluster_off_l>; next-level-cache = <&l2_0>; #cooling-cells = <2>; @@ -75,7 +75,7 @@ cpu3: cpu@300 { enable-method = "psci"; performance-domains = <&performance 0>; clock-frequency = <1701000000>; - capacity-dmips-mhz = <578>; + capacity-dmips-mhz = <308>; cpu-idle-states = <&cpu_off_l &cluster_off_l>; next-level-cache = <&l2_0>; #cooling-cells = <2>; -- 2.37.2
WARNING: multiple messages have this Message-ID (diff)
From: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> To: robh+dt@kernel.org Cc: krzysztof.kozlowski+dt@linaro.org, matthias.bgg@gmail.com, tinghan.shen@mediatek.com, seiya.wang@mediatek.com, angelogioacchino.delregno@collabora.com, devicetree@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-mediatek@lists.infradead.org, linux-kernel@vger.kernel.org Subject: [PATCH] arm64: dts: mediatek: mt8195: Fix CPUs capacity-dmips-mhz Date: Wed, 5 Oct 2022 11:34:03 +0200 [thread overview] Message-ID: <20221005093404.33102-1-angelogioacchino.delregno@collabora.com> (raw) The capacity-dmips-mhz parameter was miscalculated: this SoC runs the first (Cortex-A55) cluster at a maximum of 2000MHz and the second (Cortex-A78) cluster at a maximum of 3000MHz. In order to calculate the right capacity-dmips-mhz, the following test was performed: 1. CPUFREQ governor was set to 'performance' on both clusters 2. Ran dhrystone with 500000000 iterations for 10 times on each cluster 3. Calculate the mean result for each cluster 4. Calculate DMIPS/MHz: dmips_mhz = dmips_per_second / cpu_mhz 5. Scale results to 1024: result_c0 = (dmips_mhz_c0 - min_dmips_mhz(c0, c1)) / (max_dmips_mhz(c0, c1) - min_dmips_mhz(c0, c1)) * 1024 The mean results for this SoC are: Cluster 0 (LITTLE): 11990400 Dhry/s Cluster 1 (BIG): 59809036 Dhry/s The calculated scaled results are: Cluster 0: 307,934312801831 (rounded to 308) Cluster 1: 1024 Fixes: 37f2582883be ("arm64: dts: Add mediatek SoC mt8195 and evaluation board") Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> --- arch/arm64/boot/dts/mediatek/mt8195.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index 905d1a90b406..0b85b5874a4f 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -36,7 +36,7 @@ cpu0: cpu@0 { enable-method = "psci"; performance-domains = <&performance 0>; clock-frequency = <1701000000>; - capacity-dmips-mhz = <578>; + capacity-dmips-mhz = <308>; cpu-idle-states = <&cpu_off_l &cluster_off_l>; next-level-cache = <&l2_0>; #cooling-cells = <2>; @@ -49,7 +49,7 @@ cpu1: cpu@100 { enable-method = "psci"; performance-domains = <&performance 0>; clock-frequency = <1701000000>; - capacity-dmips-mhz = <578>; + capacity-dmips-mhz = <308>; cpu-idle-states = <&cpu_off_l &cluster_off_l>; next-level-cache = <&l2_0>; #cooling-cells = <2>; @@ -62,7 +62,7 @@ cpu2: cpu@200 { enable-method = "psci"; performance-domains = <&performance 0>; clock-frequency = <1701000000>; - capacity-dmips-mhz = <578>; + capacity-dmips-mhz = <308>; cpu-idle-states = <&cpu_off_l &cluster_off_l>; next-level-cache = <&l2_0>; #cooling-cells = <2>; @@ -75,7 +75,7 @@ cpu3: cpu@300 { enable-method = "psci"; performance-domains = <&performance 0>; clock-frequency = <1701000000>; - capacity-dmips-mhz = <578>; + capacity-dmips-mhz = <308>; cpu-idle-states = <&cpu_off_l &cluster_off_l>; next-level-cache = <&l2_0>; #cooling-cells = <2>; -- 2.37.2 _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next reply other threads:[~2022-10-05 9:34 UTC|newest] Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top 2022-10-05 9:34 AngeloGioacchino Del Regno [this message] 2022-10-05 9:34 ` [PATCH] arm64: dts: mediatek: mt8195: Fix CPUs capacity-dmips-mhz AngeloGioacchino Del Regno 2022-11-21 11:53 ` Matthias Brugger 2022-11-21 11:53 ` Matthias Brugger
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=20221005093404.33102-1-angelogioacchino.delregno@collabora.com \ --to=angelogioacchino.delregno@collabora.com \ --cc=devicetree@vger.kernel.org \ --cc=krzysztof.kozlowski+dt@linaro.org \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mediatek@lists.infradead.org \ --cc=matthias.bgg@gmail.com \ --cc=robh+dt@kernel.org \ --cc=seiya.wang@mediatek.com \ --cc=tinghan.shen@mediatek.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: linkBe 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.