OPi Zero - why are frequencies above 1.008GHz unavailable?

[Adrian Cable]

Hi - I have been using Armbian buster stable on Orange Pi Zero for the past 12 months, starting with 5.92 last August and going up to 20.05.7 today. In all of these versions, clock speeds above 1.008GHz are unavailable, despite the board supporting 1.104GHz, 1.2GHz, 1.296GHz and 1.368GHz. They are not listed in armbian-config, cpufreq-set is unable to set them, and dmesg includes lines like:

 

[   10.030991] core: _opp_supported_by_regulators: OPP minuV: 1320000 maxuV: 1320000, not supported by regulator
[   10.031017] cpu cpu0: _opp_add: OPP not supported by regulators (1104000000)
[   10.031305] core: _opp_supported_by_regulators: OPP minuV: 1320000 maxuV: 1320000, not supported by regulator
[   10.031322] cpu cpu0: _opp_add: OPP not supported by regulators (1200000000)
[   10.031589] core: _opp_supported_by_regulators: OPP minuV: 1340000 maxuV: 1340000, not supported by regulator
[   10.031610] cpu cpu0: _opp_add: OPP not supported by regulators (1296000000)
[   10.031883] core: _opp_supported_by_regulators: OPP minuV: 1400000 maxuV: 1400000, not supported by regulator
[   10.031902] cpu cpu0: _opp_add: OPP not supported by regulators (1368000000)

 

Then:

 

/sys/devices/system/cpu/cpufreq/policy0# cat scaling_available_frequencies
480000 648000 816000 960000 1008000

 

My understanding is OPi Zero has only two regulator settings: 1.1V and 1.3V. So, not surprising if the DTB is trying to set the regulator to 1.32V or 1.4V things don't work. But why is this happening?

 

What am I missing? How do I use these frequencies on Armbian buster stable? Thank you so much!

 

-Adrian

[Werner]

Afaik there is no proper support for the regulator and that is why it is capped. It is the same for the OrangePi One. And most likelie for other H3 boards too.

[Adrian Cable]

Werner - so I guess the question I really wanted to ask was: why does the DTB for the Orange Pi Zero include CPU frequency settings that request voltages above 1.3V from the regulator, which it doesn't allow?

 

If I edit the DTS to reduce the regulator voltages from the "disallowed" values down to 1.3V, the higher frequencies seem to work. I can't comment on stability. But if they are unstable, why not remove those frequencies from the DTB completely, rather than leave them in with invalid regulator voltages?

 

-Adrian

[Werner]

Because probably noone ever took care about that

Feel free to test stability (and heat) on higher clocks and then either fix it to make it work or remove them from the dts  and make  a PR.

[Adrian Cable]

Werner - that's a great idea! In case you or others want to test as well, here are my corrected lines in the DTS for the OPi Zero:

 

 

                opp-1104000000 {
                        opp-hz = < 0x00 0x41cdb400 >;
                        opp-microvolt = < 0x13d620 0x13d620 0x13d620 >;
                        clock-latency-ns = < 0x3b9b0 >;
                };

                opp-1200000000 {
                        opp-hz = < 0x00 0x47868c00 >;
                        opp-microvolt = < 0x13d620 0x13d620 0x13d620 >;
                        clock-latency-ns = < 0x3b9b0 >;
                };

                opp-1296000000 {
                        opp-hz = < 0x00 0x4d3f6400 >;
                        opp-microvolt = < 0x13d620 0x13d620 0x13d620 >;
                        clock-latency-ns = < 0x3b9b0 >;
                };

                opp-1368000000 {
                        opp-hz = < 0x00 0x518a0600 >;
                        opp-microvolt = < 0x13d620 0x13d620 0x13d620 >;
                        clock-latency-ns = < 0x3b9b0 >;
                };

 

Running now at 1.368GHz and hasn't crashed. I'm going to try stress etc. and see what happens.

 

-Adrian

[Werner]

That is awesome. Will test on my OPi One.

 

Works. Let's burn it!

[sunzone]

I've seen some times OPi Zero crashing at 1.01GHz clock due to high heat.

I recommend running it at 816MHz for stable usage.

[Werner]

10 minutes ago, sunzone said:

I've seen some times OPi Zero crashing at 1.01GHz clock due to high heat.

I recommend running it at 816MHz for stable usage.

I never had issues with mine. Though this might be related to the high temperature issue which seem to have v1.4 and v1.5 LTS boards while mine is v1.1

 

  

I created a patch for this

Needs to be tested against H5 since I dont have any board with this SoC and see if this has bad side effects there.

From 94f434f28f1d468dfc895f4a1f7e2d807537a78f Mon Sep 17 00:00:00 2001
From: EvilOlaf <werner@armbian.de>
Date: Thu, 6 Aug 2020 07:53:14 +0200
Subject: [PATCH] fix higher clocks for H3

Signed-off-by: EvilOlaf <werner@armbian.de>
---
 arch/arm/boot/dts/sunxi-h3-h5.dtsi | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
index b5dea77d4..fb5af20fa 100644
--- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi
+++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi
@@ -135,25 +135,25 @@

                opp-1104000000 {
                        opp-hz = /bits/ 64 <1104000000>;
-                       opp-microvolt = <1320000 1320000 1320000>;
+                       opp-microvolt = <1300000 1300000 1300000>;
                        clock-latency-ns = <244144>; /* 8 32k periods */
                };

                opp-1200000000 {
                        opp-hz = /bits/ 64 <1200000000>;
-                       opp-microvolt = <1320000 1320000 1320000>;
+                       opp-microvolt = <1300000 1300000 1300000>;
                        clock-latency-ns = <244144>; /* 8 32k periods */
                };

                opp-1296000000 {
                        opp-hz = /bits/ 64 <1296000000>;
-                       opp-microvolt = <1340000 1340000 1340000>;
+                       opp-microvolt = <1300000 1300000 1300000>;
                        clock-latency-ns = <244144>; /* 8 32k periods */
                };

                opp-1368000000 {
                        opp-hz = /bits/ 64 <1368000000>;
-                       opp-microvolt = <1400000 1400000 1400000>;
+                       opp-microvolt = <1300000 1300000 1300000>;
                        clock-latency-ns = <244144>; /* 8 32k periods */
                };
        };
--
Created with Armbian build tools https://github.com/armbian/build

 

[5kft]

9 hours ago, Adrian Cable said:

Werner - so I guess the question I really wanted to ask was: why does the DTB for the Orange Pi Zero include CPU frequency settings that request voltages above 1.3V from the regulator, which it doesn't allow?

 

Because the opp table in the DTs are common and used for all H3/H5 boards, not just your specific OPi Zero.  The CPU regulator voltage defines the maximum clock rate available, specific to each board.

 

9 hours ago, Werner said:

Because probably noone ever took care about that

Feel free to test stability (and heat) on higher clocks and then either fix it to make it work or remove them from the dts  and make  a PR.

 

Actually this behavior is completely correct - it's how the CPU clock system is defined.  You do not want to make a general PR to increase the default clocks for lower voltages here because this will introduce instabilities across all other AW-based boards (!).

 

There is a very easy way to enable this, however - you can use an overclock overlay.  I created a few of these a couple of years ago; see this thread for more information: 

 

 

Now I just noticed that this patch apparently didn't make it over to the new sunxi-current branch (5.7); I'll fix this.  I also used the H5 prefix for this - I haven't tried it on an H3, but given the common opp table it should work.  I'll take a look at cleaning this up now for sunxi-current and will post back.

[Adrian Cable]

5kft - this is great. If you have something you would like me to test on H2+/H3, happy to do so.

 

-Adrian

[5kft]

@Adrian Cable - I made the changes for sunxi-current and pushed to the repo:  https://github.com/armbian/build/commit/b2adb2935b4dcee57c982a1447de8cf75760dd2a.  This change adds a new boot overlay for the sun8i-h3 that enables a maximum of 1.3GHz at a CPU core voltage of 1.3v.  If you use this overlay, I strongly recommend you try driving the board hard to ensure stability (e.g., "stress --cpu 4", etc.)  Historically on most of my boards the maximum I could push to was 1.2GHz at 1.3v, which is why I added a 1.2GHz overlay for the H5 (and I could only get to 1.368GHz w/a 1.4v core voltage).  I can do the same for the H3, but am short on time atm.  I'll also add this overlay to sunxi-legacy as well, but I won't be able to get to this later.

 

I tested this on one of my H3 boards w/a max CPU voltage of 1.3v:

 

/boot/armbianEnv.txt (note the addition of "cpu-clock-1.3GHz-1.3v" to the "overlays=" line):

verbosity=7
logo=disabled
console=serial
disp_mode=1920x1080p60
overlay_prefix=sun8i-h3
overlays=usbhost0 usbhost1 usbhost2 uart1 cpu-clock-1.3GHz-1.3v
rootdev=UUID=3ad712a7-75cb-4ac1-8cfa-dbb67df8f239
rootfstype=f2fs
extraargs=net.ifnames=0
usbstoragequirks=0x2537:0x1066:u,0x2537:0x1068:u

 

After booting with this overlay, from "cpufreq-info", w/everything else at the defaults, maximum clock rate is now 1.30GHz:

analyzing CPU 0:
  driver: cpufreq-dt
  CPUs which run at the same hardware frequency: 0 1 2 3
  CPUs which need to have their frequency coordinated by software: 0 1 2 3
  maximum transition latency: 5.44 ms.
  hardware limits: 480 MHz - 1.30 GHz
  available frequency steps: 480 MHz, 648 MHz, 816 MHz, 960 MHz, 1.01 GHz, 1.06 GHz, 1.10 GHz, 1.15 GHz, 1.20 GHz, 1.22 GHz, 1.25 GHz, 1.30 GHz
  available cpufreq governors: conservative, userspace, powersave, ondemand, performance, schedutil
  current policy: frequency should be within 480 MHz and 1.30 GHz.
                  The governor "ondemand" may decide which speed to use
                  within this range.
  current CPU frequency is 480 MHz (asserted by call to hardware).
  cpufreq stats: 480 MHz:96.94%, 648 MHz:0.35%, 816 MHz:0.04%, 960 MHz:0.03%, 1.01 GHz:0.03%, 1.06 GHz:0.02%, 1.10 GHz:0.02%, 1.15 GHz:0.03%, 1.20 GHz:0.02%, 1.22 GHz:0.01%, 1.25 GHz:0.01%, 1.30 GHz:2.50%  (253)

Please give this a try and let me know how it goes   If 1.3GHz is unstable, I'll try to expedite adding the 1.2GHz overlay as well.

 

[5kft]

In case 1.3GHz isn't stable for you, I've added a 1.2GHz/1.3v overlay ("sun8i-h3-cpu-clock-1.2GHz-1.3v.dtbo") to sunxi-current (https://github.com/armbian/build/commit/e5cca8692fbe89f356e6acc5701ef8ac6c699f7e).  I tested it on an H3 board:

analyzing CPU 0:
  driver: cpufreq-dt
  CPUs which run at the same hardware frequency: 0 1 2 3
  CPUs which need to have their frequency coordinated by software: 0 1 2 3
  maximum transition latency: 5.44 ms.
  hardware limits: 480 MHz - 1.20 GHz
  available frequency steps: 480 MHz, 648 MHz, 816 MHz, 960 MHz, 1.01 GHz, 1.10 GHz, 1.20 GHz
  available cpufreq governors: conservative, userspace, powersave, ondemand, performance, schedutil
  current policy: frequency should be within 480 MHz and 1.20 GHz.
                  The governor "ondemand" may decide which speed to use
                  within this range.
  current CPU frequency is 1.20 GHz (asserted by call to hardware).
  cpufreq stats: 480 MHz:97.58%, 648 MHz:0.31%, 816 MHz:0.01%, 960 MHz:0.02%, 1.01 GHz:0.01%, 1.10 GHz:0.02%, 1.20 GHz:2.06%  (149)

 

[Adrian Cable]

5kft - your patch looks good except I would also consider adding the settings for 1368MHz. In my testing (basically stress -c 4 -n 600) the CPU temperature (OPi Zero 512 LTS) peaks at about 90 degrees C ... no crashes ... this is the real temperature (measured with FLIR) not the broken thermal readout register. Of course when overclocked by ~ 200MHz there might be significant variation in stability between boards. But I say: let people try themselves and have fun if they want.

 

Also, I believe you need to add to sun8i-h2-plus as well as sun8i-h3, to cover the OPi Zero (which is my platform).

 

-Adrian

[5kft]

1 hour ago, Adrian Cable said:

In my testing (basically stress -c 4 -n 600) the CPU temperature (OPi Zero 512 LTS) peaks at about 90 degrees C ... no crashes ...

 

Could you try running "openssl speed -multi 4" to completion at 1.3GHz (it takes quite a while), and let me know what happens?  If it survives, I'll look at adding 1.368GHz 

 

Also, cpuburn-a7 is a useful stability test as well - clone https://github.com/ssvb/cpuburn-arm, and just compile it and run it.  Be sure to watch your CPU temps when using these.

 

 

1 hour ago, Adrian Cable said:

Also, I believe you need to add to sun8i-h2-plus as well as sun8i-h3, to cover the OPi Zero (which is my platform).

 

I just did a full build for the Orange Pi Zero, and the overlay prefix is "sun8i-h3":

root@orangepizero:~# cat /boot/armbianEnv.txt
verbosity=1
bootlogo=false
console=serial
disp_mode=1920x1080p60
overlay_prefix=sun8i-h3
overlays=usbhost2 usbhost3
rootdev=UUID=83d54d78-1845-4266-9776-2fa013e0e1f6
rootfstype=ext4
usbstoragequirks=0x2537:0x1066:u,0x2537:0x1068:u
root@orangepizero:~#

 

Edited August 6, 2020 by 5kft
added reference to cpuburn; note regarding overlay prefix

[Adrian Cable]

5kft - my bad about the overlay prefix. Checked on my build and you're right. I think I got confused previously because the DTB files for OPi Zero do indeed start with sun8i-h2-plus not sun8i-h3.

 

So here are the results from openssl speed -multi 4:

 

1. The CPU gets very hot indeed! See attached pic.

2. It doesn't crash.

3. It completes just fine, ending ...

Got: +F5:18:384:34.665335:0.028847 from 3
Got: +F5:19:384:35.294118:0.028333 from 3
Got: +F5:20:512:26.047904:0.038391 from 3
Got: +F5:21:512:27.372627:0.036533 from 3
Got: +F5:22:253:486.600000:0.002055 from 3
Got: +F5:23:448:105.500000:0.009479 from 3
Got: +F6:0:253:Ed25519:1240.400000:431.900000 from 3
Got: +F6:1:456:Ed448:198.400000:99.700000 from 3

OpenSSL 1.1.1d  10 Sep 2019
built on: Mon Apr 20 20:23:01 2020 UTC
options:bn(64,32) rc4(char) des(long) aes(partial) blowfish(ptr)
compiler: gcc -fPIC -pthread -Wa,--noexecstack -Wall -Wa,--noexecstack -g -O2 -fdebug-prefix-map=/build/openssl-8NbErV/openssl-1.1.1d=. -fstack-protector-strong -Wformat -Werror=format-security -DOPENSSL_USE_NODELETE -DOPENSSL_PIC -DOPENSSL_CPUID_OBJ -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM_GF2m -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DKECCAK1600_ASM -DAES_ASM -DBSAES_ASM -DGHASH_ASM -DECP_NISTZ256_ASM -DPOLY1305_ASM -DNDEBUG -Wdate-time -D_FORTIFY_SOURCE=2

 

So I vote to include 1.368GHz.

 

-Adrian

[5kft]

42 minutes ago, Adrian Cable said:

So I vote to include 1.368GHz.

 

Done!  https://github.com/armbian/build/commit/91156f11922c00227211d1d765512f09b6398d1a

 

verbosity=1
bootlogo=false
console=serial
disp_mode=1920x1080p60
overlay_prefix=sun8i-h3
overlays=usbhost2 usbhost3 cpu-clock-1.368GHz-1.3v
rootdev=UUID=84d54d78-1a45-4366-9776-2fa013e0e1e6
rootfstype=ext4
usbstoragequirks=0x2537:0x1066:u,0x2537:0x1068:u

analyzing CPU 0:
  driver: cpufreq-dt
  CPUs which run at the same hardware frequency: 0 1 2 3
  CPUs which need to have their frequency coordinated by software: 0 1 2 3
  maximum transition latency: 5.44 ms.
  hardware limits: 480 MHz - 1.37 GHz
  available frequency steps: 480 MHz, 648 MHz, 816 MHz, 960 MHz, 1.01 GHz, 1.06 GHz, 1.10 GHz, 1.15 GHz, 1.20 GHz, 1.22 GHz, 1.25 GHz, 1.30 GHz, 1.37 GHz
  available cpufreq governors: conservative, userspace, powersave, ondemand, performance, schedutil
  current policy: frequency should be within 480 MHz and 1.37 GHz.
                  The governor "ondemand" may decide which speed to use
                  within this range.
  current CPU frequency is 480 MHz (asserted by call to hardware).
  cpufreq stats: 480 MHz:89.25%, 648 MHz:0.49%, 816 MHz:1.19%, 960 MHz:0.01%, 1.01 GHz:3.74%, 1.06 GHz:0.01%, 1.10 GHz:0.86%, 1.15 GHz:0.01%, 1.20 GHz:0.82%, 1.22 GHz:0.01%, 1.25 GHz:0.73%, 1.30 GHz:0.01%, 1.37 GHz:2.89%  (287)

 

[Adrian Cable]

Looks great to me!! Thank you!

 

-Adrian

[Werner]

This is awesome. I'll bench my OrangePi One with 1,368MHz too.

[lanefu]

Just confirming.   These overlays won’t work on the tritium boards which have a fixed voltage, correct?

[Werner]

5 hours ago, Adrian Cable said:

1. The CPU gets very hot indeed! See attached pic.

The OrangePi One seems to handle this even better. openssl is now running for 15 Minutes and the temperature barely exceeds 85*C without a heatsink at room temperature of about 22*C. Still waiting to finish atm.

Edit: Finished

 

 

Spoiler

...
Got: +F:28:aes-256 ige:18911482.67:21429610.67:22118656.00:22223872.00:22399658.                                  67:22020096.00 from 3
Got: +F:29:ghash:54132581.33:63982784.00:70057472.00:71748949.33:72668501.33:730                                  99946.67 from 3
Got: +F:30:rand:661786.67:2410218.67:7169962.67:13946197.33:19526997.33:20108629                                  .33 from 3
Got: +F2:0:512:1399.200799:18466.500000 from 3
Got: +F2:1:1024:311.200000:6980.500000 from 3
Got: +F2:2:2048:50.998004:2062.400000 from 3
Got: +F2:3:3072:17.447657:953.246753 from 3
Got: +F2:4:4096:7.638889:545.300000 from 3
Got: +F2:5:7680:1.298701:160.100000 from 3
Got: +F2:6:15360:0.176367:41.400000 from 3
Got: +F3:0:512:956.800000:1366.500000 from 3
Got: +F3:1:1024:455.300000:554.400000 from 3
Got: +F3:2:2048:152.900000:171.700000 from 3
Got: +F4:0:160:291.200000:371.000000 from 3
Got: +F4:1:192:198.900000:262.637363 from 3
Got: +F4:2:224:142.600000:190.309690 from 3
Got: +F4:3:256:1554.400000:529.200000 from 3
Got: +F4:4:384:40.200000:57.442557 from 3
Got: +F4:5:521:16.283716:24.575425 from 3
Got: +F4:6:163:276.900000:140.459540 from 3
Got: +F4:7:233:163.500000:82.700000 from 3
Got: +F4:8:283:92.407592:46.806387 from 3
Got: +F4:9:409:45.200000:22.900000 from 3
Got: +F4:10:571:19.641077:10.000000 from 3
Got: +F4:11:163:262.737263:132.900000 from 3
Got: +F4:12:233:152.900000:76.823177 from 3
Got: +F4:13:283:84.815185:43.013972 from 3
Got: +F4:14:409:40.800000:20.597015 from 3
Got: +F4:15:571:17.500000:8.910891 from 3
Got: +F4:16:256:138.900000:174.300000 from 3
Got: +F4:17:256:139.300000:184.600000 from 3
Got: +F4:18:384:41.375872:53.900000 from 3
Got: +F4:19:384:40.419162:58.283433 from 3
Got: +F4:20:512:31.636727:42.457542 from 3
Got: +F4:21:512:31.636727:46.100000 from 3
Got: +F5:0:160:311.500000:0.003210 from 3
Got: +F5:1:192:211.300000:0.004733 from 3
Got: +F5:2:224:151.900000:0.006583 from 3
Got: +F5:3:256:744.455544:0.001343 from 3
Got: +F5:4:384:41.816367:0.023914 from 3
Got: +F5:5:521:17.148554:0.058314 from 3
Got: +F5:6:163:295.000000:0.003390 from 3
Got: +F5:7:233:172.200000:0.005807 from 3
Got: +F5:8:283:97.402597:0.010267 from 3
Got: +F5:9:409:47.852148:0.020898 from 3
Got: +F5:10:571:20.779221:0.048125 from 3
Got: +F5:11:163:276.900000:0.003611 from 3
Got: +F5:12:233:159.540460:0.006268 from 3
Got: +F5:13:283:88.811189:0.011260 from 3
Got: +F5:14:409:42.814371:0.023357 from 3
Got: +F5:15:571:18.544367:0.053925 from 3
Got: +F5:16:256:147.800000:0.006766 from 3
Got: +F5:17:256:148.100000:0.006752 from 3
Got: +F5:18:384:43.000000:0.023256 from 3
Got: +F5:19:384:41.900000:0.023866 from 3
Got: +F5:20:512:33.000000:0.030303 from 3
Got: +F5:21:512:33.200000:0.030120 from 3
Got: +F5:22:253:580.619381:0.001722 from 3
Got: +F5:23:448:128.871129:0.007760 from 3
Got: +F6:0:253:Ed25519:1451.300000:511.500000 from 3
Got: +F6:1:456:Ed448:238.100000:113.000000 from 3
OpenSSL 1.1.1f  31 Mar 2020
built on: Mon Apr 20 11:53:50 2020 UTC
options:bn(64,32) rc4(char) des(long) aes(partial) blowfish(ptr)
compiler: gcc -fPIC -pthread -Wa,--noexecstack -Wall -Wa,--noexecstack -g -O2 -f                                  debug-prefix-map=/build/openssl-uC90dH/openssl-1.1.1f=. -fstack-protector-strong                                   -Wformat -Werror=format-security -DOPENSSL_TLS_SECURITY_LEVEL=2 -DOPENSSL_USE_N                                  ODELETE -DOPENSSL_PIC -DOPENSSL_CPUID_OBJ -DOPENSSL_BN_ASM_MONT -DOPENSSL_BN_ASM                                  _GF2m -DSHA1_ASM -DSHA256_ASM -DSHA512_ASM -DKECCAK1600_ASM -DAES_ASM -DBSAES_AS                                  M -DGHASH_ASM -DECP_NISTZ256_ASM -DPOLY1305_ASM -DNDEBUG -Wdate-time -D_FORTIFY_                                  SOURCE=2
root@orangepione:~#

 

 

And the temps from beginning to end:

 

Spoiler

04:49:00: 1368MHz  0.00   0%   0%   0%   0%   0%   0% 33.2°C  0/8
04:49:06: 1368MHz  0.32  59%   0%  59%   0%   0%   0% 50.6°C  0/8
04:49:12: 1368MHz  0.62 100%   0%  99%   0%   0%   0% 56.3°C  0/8
04:49:19: 1368MHz  0.89  99%   0%  99%   0%   0%   0% 58.6°C  0/8
04:49:27: 1368MHz  1.44 100%   0%  99%   0%   0%   0% 61.0°C  0/8
04:49:34: 1368MHz  1.64  99%   0%  99%   0%   0%   0% 62.4°C  0/8
04:49:42: 1368MHz  2.08 100%   0%  99%   0%   0%   0% 64.2°C  0/8
04:49:49: 1368MHz  2.23  99%   0%  99%   0%   0%   0% 65.0°C  0/8
04:49:55: 1368MHz  2.58 100%   0%  99%   0%   0%   0% 65.9°C  0/8
04:50:01: 1368MHz  2.69 100%   0%  99%   0%   0%   0% 64.9°C  0/8
04:50:08: 1368MHz  2.80 100%   0%  99%   0%   0%   0% 65.3°C  0/8
04:50:15: 1368MHz  3.06  99%   0%  99%   0%   0%   0% 66.6°C  0/8
04:50:24: 1368MHz  3.13 100%   0%  99%   0%   0%   0% 66.4°C  0/8
04:50:32: 1368MHz  3.34 100%   0%  99%   0%   0%   0% 66.7°C  0/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
04:50:39: 1368MHz  3.52 100%   0%  99%   0%   0%   0% 73.4°C  0/8
04:50:44: 1368MHz  3.56 100%   0%  99%   0%   0%   0% 72.9°C  0/8
04:50:51: 1368MHz  3.59 100%   0%  99%   0%   0%   0% 75.0°C  0/8
04:50:57: 1296MHz  3.62  99%   0%  99%   0%   0%   0% 76.3°C  1/8
04:51:05: 1296MHz  3.65 100%   0%  99%   0%   0%   0% 78.0°C  1/8
04:51:13: 1368MHz  3.78 100%   0%  99%   0%   0%   0% 75.2°C  0/8
04:51:21: 1368MHz  3.89 100%   0%  99%   0%   0%   0% 75.2°C  0/8
04:51:29: 1368MHz  3.90 100%   0%  99%   0%   0%   0% 74.5°C  0/8
04:51:34: 1368MHz  3.99 100%   0%  99%   0%   0%   0% 74.5°C  0/8
04:51:41: 1368MHz  3.99 100%   0%  99%   0%   0%   0% 74.8°C  0/8
04:51:48: 1296MHz  3.99  99%   0%  99%   0%   0%   0% 76.9°C  1/8
04:51:57: 1296MHz  4.07 100%   0%  99%   0%   0%   0% 78.5°C  1/8
04:52:03: 1296MHz  4.13 100%   0%  99%   0%   0%   0% 78.9°C  1/8
04:52:11: 1296MHz  4.12 100%   0%  99%   0%   0%   0% 79.9°C  2/8
04:52:18: 1296MHz  4.11 100%   0%  99%   0%   0%   0% 80.8°C  2/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
04:52:25: 1296MHz  4.17 100%   0%  99%   0%   0%   0% 80.4°C  2/8
04:52:31: 1296MHz  4.16 100%   0%  99%   0%   0%   0% 79.7°C  1/8
04:52:37: 1200MHz  4.14 100%   0%  99%   0%   0%   0% 80.3°C  2/8
04:52:44: 1200MHz  4.13 100%   0%  99%   0%   0%   0% 80.4°C  2/8
04:52:51: 1200MHz  4.19 100%   0%  99%   0%   0%   0% 80.6°C  2/8
04:52:59: 1200MHz  4.17 100%   0%  99%   0%   0%   0% 80.9°C  2/8
04:53:05: 1200MHz  4.22  99%   0%  99%   0%   0%   0% 81.1°C  2/8
04:53:12: 1200MHz  4.20 100%   0%  99%   0%   0%   0% 81.4°C  2/8
04:53:20: 1200MHz  4.24 100%   0%  99%   0%   0%   0% 81.6°C  2/8
04:53:28: 1200MHz  4.22 100%   0%  99%   0%   0%   0% 82.1°C  2/8
04:53:37: 1200MHz  4.26 100%   0%  99%   0%   0%   0% 81.9°C  2/8
04:53:45: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 82.7°C  2/8
04:53:53: 1200MHz  4.27  99%   0%  99%   0%   0%   0% 82.1°C  2/8
04:54:01: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 83.3°C  2/8
04:54:08: 1200MHz  4.28 100%   0%  99%   0%   0%   0% 83.8°C  2/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
04:54:14: 1200MHz  4.31 100%   0%  99%   0%   0%   0% 79.9°C  1/8
04:54:21: 1296MHz  4.29 100%   0%  99%   0%   0%   0% 79.9°C  1/8
04:54:30: 1200MHz  4.26 100%   0%  99%   0%   0%   0% 80.9°C  2/8
04:54:37: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 81.5°C  2/8
04:54:45: 1200MHz  4.27 100%   0%  99%   0%   0%   0% 82.8°C  2/8
04:54:52: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 82.8°C  2/8
04:55:00: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 83.2°C  2/8
04:55:07: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 82.7°C  2/8
04:55:14: 1200MHz  4.28 100%   0%  99%   0%   0%   0% 83.1°C  2/8
04:55:21: 1200MHz  4.31 100%   0%  99%   0%   0%   0% 82.6°C  2/8
04:55:30: 1200MHz  4.29 100%   0%  99%   0%   0%   0% 80.9°C  2/8
04:55:38: 1200MHz  4.31 100%   0%  99%   0%   0%   0% 80.2°C  1/8
04:55:46: 1296MHz  4.34 100%   0%  99%   0%   0%   0% 77.6°C  1/8
04:55:52: 1296MHz  4.31  99%   0%  99%   0%   0%   0% 77.4°C  1/8
04:55:59: 1296MHz  4.29 100%   0%  99%   0%   0%   0% 80.6°C  2/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
04:56:05: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 81.2°C  2/8
04:56:12: 1200MHz  4.29 100%   0%  99%   0%   0%   0% 82.6°C  2/8
04:56:21: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 81.1°C  2/8
04:56:28: 1200MHz  4.29 100%   0%  99%   0%   0%   0% 81.1°C  2/8
04:56:35: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 82.0°C  2/8
04:56:44: 1200MHz  4.30 100%   1%  98%   0%   0%   0% 82.8°C  2/8
04:56:52: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 82.9°C  2/8
04:57:01: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 82.6°C  2/8
04:57:09: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 83.2°C  2/8
04:57:16: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 84.3°C  2/8
04:57:23: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 84.9°C  2/8
04:57:28: 1200MHz  4.29 100%   0%  99%   0%   0%   0% 84.8°C  2/8
04:57:36: 1200MHz  4.32  99%   0%  99%   0%   0%   0% 84.8°C  2/8
04:57:43: 1200MHz  4.29 100%   0%  99%   0%   0%   0% 84.8°C  2/8
04:57:51: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 85.0°C  2/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
04:57:59: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 84.8°C  2/8
04:58:07: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 83.9°C  2/8
04:58:16: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 84.3°C  4/8
04:58:25: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 86.1°C  4/8
04:58:35: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 84.8°C  2/8
04:58:44: 1008MHz  4.37 100%   0%  99%   0%   0%   0% 85.0°C  4/8
04:58:51: 1008MHz  4.38 100%   0%  99%   0%   0%   0% 86.2°C  4/8
04:59:00: 1008MHz  4.35 100%   0%  99%   0%   0%   0% 84.8°C  4/8
04:59:09: 1008MHz  4.37 100%   0%  99%   0%   0%   0% 86.9°C  4/8
04:59:16: 1200MHz  4.39 100%   0%  99%   0%   0%   0% 85.4°C  4/8
04:59:24: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 84.3°C  2/8
04:59:32: 1200MHz  4.38 100%   0%  99%   0%   0%   0% 83.7°C  2/8
04:59:40: 1200MHz  4.39 100%   0%  99%   0%   0%   0% 84.3°C  2/8
04:59:46: 1200MHz  4.36  99%   0%  99%   0%   0%   0% 84.9°C  2/8
04:59:54: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 85.1°C  2/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
05:00:02: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 84.4°C  2/8
05:00:11: 1200MHz  4.37 100%   0%  99%   0%   0%   0% 85.5°C  4/8
05:00:19: 1200MHz  4.34  99%   0%  99%   0%   0%   0% 84.2°C  4/8
05:00:28: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 84.9°C  2/8
05:00:37: 1200MHz  4.38 100%   0%  99%   0%   0%   0% 85.1°C  4/8
05:00:46: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 85.1°C  4/8
05:00:54: 1200MHz  4.37 100%   0%  99%   0%   0%   0% 85.0°C  2/8
05:01:01: 1200MHz  4.39 100%   0%  99%   0%   0%   0% 85.4°C  4/8
05:01:08: 1008MHz  4.36 100%   0%  99%   0%   0%   0% 85.0°C  2/8
05:01:17: 1200MHz  4.37 100%   0%  99%   0%   0%   0% 84.2°C  4/8
05:01:26: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 83.8°C  2/8
05:01:33: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 83.1°C  2/8
05:01:41: 1200MHz  4.46  99%   0%  99%   0%   0%   0% 84.8°C  2/8
05:01:48: 1200MHz  4.42 100%   0%  99%   0%   0%   0% 84.8°C  2/8
05:01:56: 1200MHz  4.43 100%   0%  99%   0%   0%   0% 84.3°C  4/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
05:02:06: 1200MHz  4.39 100%   0%  99%   0%   0%   0% 84.8°C  4/8
05:02:14: 1200MHz  4.41 100%   0%  99%   0%   0%   0% 84.5°C  2/8
05:02:23: 1200MHz  4.49 100%   0%  99%   0%   0%   0% 83.4°C  2/8
05:02:31: 1200MHz  4.49 100%   0%  99%   0%   0%   0% 82.2°C  2/8
05:02:40: 1200MHz  4.45 100%   0%  99%   0%   0%   0% 82.8°C  2/8
05:02:49: 1200MHz  4.45 100%   0%  99%   0%   0%   0% 82.2°C  2/8
05:02:56: 1200MHz  4.46 100%   0%  99%   0%   0%   0% 82.3°C  2/8
05:03:04: 1200MHz  4.42 100%   0%  99%   0%   0%   0% 82.3°C  2/8
05:03:11: 1200MHz  4.43 100%   0%  99%   0%   0%   0% 82.1°C  2/8
05:03:17: 1200MHz  4.40 100%   0%  99%   0%   0%   0% 82.5°C  2/8
05:03:24: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 82.5°C  2/8
05:03:33: 1200MHz  4.38 100%   0%  99%   0%   0%   0% 82.3°C  2/8
05:03:40: 1200MHz  4.40 100%   0%  99%   0%   0%   0% 82.9°C  2/8
05:03:47: 1200MHz  4.36  99%   0%  99%   0%   0%   0% 82.5°C  2/8
05:03:54: 1200MHz  4.39 100%   0%  99%   0%   0%   0% 82.7°C  2/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
05:04:01: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 82.2°C  2/8
05:04:10: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 81.6°C  2/8
05:04:18: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 81.9°C  2/8
05:04:27: 1200MHz  4.37 100%   0%  99%   0%   0%   0% 81.5°C  2/8
05:04:35: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 82.1°C  2/8
05:04:42: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 81.9°C  2/8
05:04:50: 1200MHz  4.38 100%   0%  99%   0%   0%   0% 81.4°C  2/8
05:04:57: 1200MHz  4.35  99%   0%  99%   0%   0%   0% 81.0°C  2/8
05:05:04: 1200MHz  4.37 100%   0%  99%   0%   0%   0% 81.7°C  2/8
05:05:12: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 81.4°C  2/8
05:05:20: 1200MHz  4.31 100%   0%  99%   0%   0%   0% 82.0°C  2/8
05:05:27: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 82.2°C  2/8
05:05:35: 1200MHz  4.31  99%   0%  99%   0%   0%   0% 81.9°C  2/8
05:05:43: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 82.6°C  2/8
05:05:50: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 81.6°C  2/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
05:05:58: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 81.7°C  2/8
05:06:06: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 82.1°C  2/8
05:06:15: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 82.2°C  2/8
05:06:23: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 84.8°C  2/8
05:06:32: 1200MHz  4.37 100%   0%  99%   0%   0%   0% 83.9°C  2/8
05:06:41: 1008MHz  4.34 100%   0%  99%   0%   0%   0% 84.8°C  4/8
05:06:50: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 85.1°C  4/8
05:06:58: 1200MHz  4.38 100%   0%  99%   0%   0%   0% 85.1°C  4/8
05:07:04: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 85.0°C  4/8
05:07:09: 1200MHz  4.37 100%   0%  99%   0%   0%   0% 84.4°C  2/8
05:07:17: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 84.4°C  2/8
05:07:23: 1200MHz  4.31  99%   0%  99%   0%   0%   0% 83.1°C  2/8
05:07:31: 1200MHz  4.29 100%   0%  99%   0%   0%   0% 84.6°C  2/8
05:07:40: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 85.1°C  4/8
05:07:49: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 84.8°C  2/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
05:07:56: 1200MHz  4.37  99%   0%  99%   0%   0%   0% 83.5°C  2/8
05:08:04: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 85.1°C  4/8
05:08:12: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 85.6°C  2/8
05:08:19: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 82.7°C  2/8
05:08:27: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 85.4°C  4/8
05:08:34: 1200MHz  4.33  99%   0%  99%   0%   0%   0% 84.4°C  2/8
05:08:42: 1008MHz  4.35 100%   0%  99%   0%   0%   0% 84.8°C  2/8
05:08:51: 1200MHz  4.37 100%   0%  99%   0%   0%   0% 83.1°C  2/8
05:08:59: 1200MHz  4.34  99%   0%  99%   0%   0%   0% 83.1°C  2/8
05:09:08: 1200MHz  4.36 100%   0%  99%   0%   0%   0% 82.6°C  2/8
05:09:15: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 82.5°C  2/8
05:09:22: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 82.7°C  2/8
05:09:27: 1200MHz  4.33  99%   0%  99%   0%   0%   0% 82.6°C  2/8
05:09:35: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 81.9°C  2/8
05:09:42: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 82.5°C  2/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
05:09:49: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 82.3°C  2/8
05:09:56: 1200MHz  4.33  99%   0%  99%   0%   0%   0% 82.1°C  2/8
05:10:05: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 82.1°C  2/8
05:10:12: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 82.7°C  2/8
05:10:18: 1200MHz  4.30 100%   0%  99%   0%   0%   0% 82.6°C  2/8
05:10:25: 1200MHz  4.28 100%   0%  99%   0%   0%   0% 83.3°C  2/8
05:10:32: 1200MHz  4.31 100%   0%  99%   0%   0%   0% 82.7°C  2/8
05:10:41: 1200MHz  4.28 100%   0%  99%   0%   0%   0% 83.5°C  2/8
05:10:48: 1200MHz  4.31 100%   0%  99%   0%   0%   0% 84.9°C  2/8
05:10:56: 1200MHz  4.29  99%   0%  99%   0%   0%   0% 84.4°C  2/8
05:11:03: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 86.1°C  4/8
05:11:11: 1200MHz  4.29 100%   0%  99%   0%   0%   0% 84.3°C  2/8
05:11:18: 1200MHz  4.32 100%   0%  99%   0%   0%   0% 84.6°C  2/8
05:11:25: 1200MHz  4.29 100%   0%  99%   0%   0%   0% 85.1°C  4/8
05:11:33: 1008MHz  4.32 100%   0%  99%   0%   0%   0% 85.6°C  4/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
05:11:40: 1008MHz  4.30  99%   0%  99%   0%   0%   0% 85.8°C  2/8
05:11:49: 1200MHz  4.33 100%   0%  99%   0%   0%   0% 84.5°C  4/8
05:11:58: 1200MHz  4.35 100%   0%  99%   0%   0%   0% 84.5°C  4/8
05:12:05: 1200MHz  4.37 100%   0%  99%   0%   0%   0% 84.5°C  2/8
05:12:12: 1200MHz  4.34 100%   0%  99%   0%   0%   0% 83.9°C  4/8
05:12:22: 1008MHz  4.36 100%   0%  99%   0%   0%   0% 86.3°C  2/8
05:12:28:  480MHz  4.33  48%   0%  48%   0%   0%   0% 62.1°C  0/8
05:12:33:  480MHz  3.98   0%   0%   0%   0%   0%   0% 56.9°C  0/8
05:12:38:  480MHz  3.66   0%   0%   0%   0%   0%   0% 54.5°C  0/8
05:12:44:  480MHz  3.37   0%   0%   0%   0%   0%   0% 52.7°C  0/8
05:12:49:  480MHz  3.10   0%   0%   0%   0%   0%   0% 51.5°C  0/8
05:12:54:  480MHz  2.70   1%   0%   0%   0%   0%   0% 50.6°C  0/8
05:12:59:  480MHz  2.48   0%   0%   0%   0%   0%   0% 49.4°C  0/8
05:13:04:  480MHz  2.28   0%   0%   0%   0%   0%   0% 48.9°C  0/8
05:13:09:  480MHz  2.10   0%   0%   0%   0%   0%   0% 47.9°C  0/8
Time        CPU    load %cpu %sys %usr %nice %io %irq   CPU  C.St.
05:13:15:  480MHz  1.93   0%   0%   0%   0%   0%   0% 47.8°C  0/8
05:13:20:  480MHz  1.78   0%   0%   0%   0%   0%   0% 47.3°C  0/8
05:13:25:  480MHz  1.63   0%   0%   0%   0%   0%   0% 46.9°C  0/8

 

 

Edited August 7, 2020 by Werner
Add result

[5kft]

9 hours ago, lanefu said:

Just confirming.   These overlays won’t work on the tritium boards which have a fixed voltage, correct?

 

I'm not deeply familiar with those boards, but in doing some really quick checks it looks like indeed the hardware doesn't provide any means to get more voltage to the CPU, which means they wouldn't work...

 

8 hours ago, Werner said:

The OrangePi One seems to handle this even better. openssl is now running for 15 Minutes and the temperature barely exceeds 85*C without a heatsink at room temperature of about 22*C. Still waiting to finish atm.

 

Yes, I've found in testing that it appears that the H2+/H3 can be pushed harder than the H5...  I tested 1.3GHz on a couple H5s and couldn't get them stable above 1.2GHz (some other ones are fine, however).  My OPi Zero has no issue, however...it's interesting.  Also, note that with the way I created these overlays the passive cooling maps work properly, which means that the boards will clock down at the appropriate temperature thresholds, improving stability.  You'll note that while your board clocked to 1368MHz early on, it spent the bulk of its time at 1200MHz due to thermals.  This is good - it provides stability and will allow the board to clock to the maximum when it can.

[Adrian Cable]

5kft - just to confirm - I rolled back my hack and added your new DTBO compiled from your patch commit. All works great, on H2+. You might also want to add a note in README.sun8i-h3-overlays.

 

-Adrian

[lanefu]

Fyi here's SBCBench results on Opi Zero v1.1 inside a case, using 1.3ghz dtb

http://ix.io/2twM