Hello all.
I’m trying to bringup Android12 on a early version of ROCK5 board.
I’ll update the new status here when we make progress.
ROCK5 Android12 Bringup Status Update
2 Likes
Sucessfully boot today!!!
Antutu benchmark got 437053 score. We believe there are some space to optimize.
4 Likes
Great you got it running, scores are prob lower than expected but not a huge amount lower.
What DDR do you use on the Rock5 as is that effecting the scores?
89 LG V50S ThinQ 5G (8+256)124798 164890 69877 106938 466503
90 HONOR 30 (8+128)141258 134980 74397 108103 458738
91 Poco F1 (6+128)104227 176314 68488 89807 438836
92 OPPO Reno6 5G (8+128)121217 121828 81024 109379 433447
93 Mi 8 (6+128)103385 158699 65654 88231 415969
Prob would of expected it somewhere around, maybe above?
75 HONOR 50 (6+128) 157472 154861 77104 117494 506931
1 Like
DDR4 but we were having issues with memory stability that prevented us from booting into Android. As such we downclocked our ram to allow us getting into the system. That’s why our memory score is lower than other devices.
Yeah I thought it looked a little low and may be also effecting GPU score.
Sure you will get there as I am no good and hate early dev boards 
Also is the RK3588 CPU a 2+2 in that its 2 pairs with 1 pair faster than the other like some mobiles as keep seeing it quoted as 2.4/2.6 and is that a thing aswell that is downclocked a tad just to get things going?
I actually don’t know where did they get the quoted speed. It was not in the datasheet. However what is clear from the datasheet is that there is only 1 fast cluster, so all 4 A76 cores will have to be either 2.4 or 2.6 GHz. Hopefully @anon39001862 can confirm the exact spec on the processor.
As for downclock only memory was manually downclocked.
Hi, is vulkan api available on rock5 android ?
ncnn depends on vulkan api for accelerating NN inference on gpu
Power Comsumption.
Under a extreme stress test:
- Play 4K video
- CPU 100% loading
- GPU 100% loading
- Writing NVME SSD
- iperf test
The whole board power comsumption raise from an empty laoding 5 watts up to 15 watts.
3 Likes
lol !
So could you please build a recently updated ncnn benchncnn binary for android and run benchmark on cpu/gpu ?
I’m quite curious how the performance is compared with other soc that are reachable.
I can add rock5 onto the list if it is available --> https://github.com/nihui/ncnn-small-board
Reach me at qq group if help needed of any issues related to ncnn.
Cnxsoft and a few others quoted the speed in a similar way you did 2.4/2.6 which is sort of weird when usually there is just a max clock and it was just my confusion as started to wonder if this was 2+2.
I can not find a ref for clock speed in the datasheet max clock just has a TBA but things looking good if thats without heatsink and seems quite low on wattage.
Also still trying to find a rated max TDP for the rk3588 Tom posted some approx details and still the NPU is to run as also curious how much load/heat 6 TOPs will provide.
Would be interesting to see what the Mali can do with NCNN but guess you guys have enough to do, but also power draw vs the NPU as in the list for ncnn-small-board it seems to be purely GPU with the Maxwell of the nano leading which is approx a 472 GFLOPs device whilst the RK3588 supposedly has a 6 TOPs NPU which is awesome and would love that to be tested also.
Sawyer told me it was indeed 2+2 but both clusters are clocked at 2.4 GHz. Might need some optimizations to enable that extra 200 MHz.
2 Likes
I will leave you guys to that PMU as it looks great but boy with its own MCU looks a tad complex.
So prob the default offering will be 2.4/2.6 2+2 4 core, I guess? I presume because it does have a PMU MCU it is really flexible and nothing is set in stone.
I have absolutely no idea how to format a OPP table for 2+2 so will just leave you guys to it.
console:/data/benchmark # ./benchncnn 10 $(nproc) 0 -1
loop_count = 10
num_threads = 8
powersave = 0
gpu_device = -1
cooling_down = 1
squeezenet min = 10.75 max = 11.04 avg = 10.82
squeezenet_int8 min = 10.92 max = 11.75 avg = 11.19
mobilenet min = 11.60 max = 12.29 avg = 11.77
mobilenet_int8 min = 10.79 max = 11.10 avg = 10.95
mobilenet_v2 min = 11.36 max = 11.68 avg = 11.47
mobilenet_v3 min = 10.04 max = 11.15 avg = 10.27
shufflenet min = 11.36 max = 14.80 avg = 11.84
shufflenet_v2 min = 6.93 max = 7.84 avg = 7.27
mnasnet min = 9.81 max = 11.61 avg = 10.04
proxylessnasnet min = 12.14 max = 12.44 avg = 12.24
efficientnet_b0 min = 19.68 max = 20.08 avg = 19.81
efficientnetv2_b0 min = 31.52 max = 31.93 avg = 31.76
regnety_400m min = 13.84 max = 14.03 avg = 13.91
blazeface min = 4.30 max = 4.73 avg = 4.58
googlenet min = 34.22 max = 37.59 avg = 34.84
googlenet_int8 min = 36.66 max = 37.02 avg = 36.86
resnet18 min = 22.71 max = 25.21 avg = 23.25
resnet18_int8 min = 33.30 max = 33.79 avg = 33.52
alexnet min = 35.89 max = 37.76 avg = 36.30
vgg16 min = 150.28 max = 153.17 avg = 151.37
vgg16_int8 min = 222.55 max = 229.33 avg = 225.95
resnet50 min = 59.84 max = 65.78 avg = 60.80
resnet50_int8 min = 66.24 max = 68.79 avg = 66.95
squeezenet_ssd min = 43.07 max = 43.42 avg = 43.24
squeezenet_ssd_int8 min = 47.50 max = 50.78 avg = 48.28
mobilenet_ssd min = 32.95 max = 35.40 avg = 33.45
mobilenet_ssd_int8 min = 30.31 max = 30.92 avg = 30.57
mobilenet_yolo min = 65.22 max = 68.17 avg = 66.00
mobilenetv2_yolov3 min = 38.73 max = 41.90 avg = 39.34
yolov4-tiny min = 53.76 max = 58.01 avg = 54.81
nanodet_m min = 16.85 max = 20.38 avg = 18.14
yolo-fastest-1.1 min = 9.51 max = 9.90 avg = 9.59
yolo-fastestv2 min = 9.42 max = 10.02 avg = 9.64
console:/data/benchmark #
2 Likes
Thanks!
谢谢！
I have updated the data to the list.
The rock5b cpu runs faster than jetson nano gpu for this workload
Well that is certainly impressive and making us all jealous as we also get to see a RK3588_s in the wild.
That is a Rockchip EVB board isn’t it? Whats it clocked at?