(04-07-2016, 10:40 AM)stealthbanana Wrote: Rather than starting a new thread, though I would just add to this.
When I get a new comp, I like to run a basic benchmark, using the simple primes test from sysbench, keeping the command line the same.
sysbench --test=cpu --cpu-max-prime=20000 run
(as per the the example in the man page.)
Must admit I am either well impressed, or dubious about the Pine64 result, could someone else recheck it for me?
As can be seen by the results below, the Pine is over 40x faster at computing primes than an original Raspberry Pi B and even faster than my laptop. Not in anyway scientific, but all tests ran using Debian, or a Debian derived distro.
Raspberry Pi B (single core)
total time taken by event execution: 1321.6702
Raspberry Pi 2 (quad core)
total time taken by event execution: 769.8208
Banana Pi (Dual Core)
total time taken by event execution: 734.1427
Orange Pi Plus (Quad Core)
total time taken by event execution: 477.5902
Orange Pi PC (Quad core)
total time taken by event execution: 456.3728
And the Pine64 (quad core 2GB)
total time taken by event execution: 31.7711 (ran several times to verify the result)
(And as a test, on a few x86 systems
Netbook - (Intel Atom N270)
total time taken by event execution: 186.9946
Desktop (AMD FX-8350 - 8 core)
total time taken by event execution: 14.0435
Laptop - (Intel i3 Dual core with Hyperthreading)
total time taken by event execution: 39.7917
Nice, but you ran everything only on one core, if you add parametr: --num-threads=4 (number of cores), you will see even more gap between RaspiX and Pine =) some basic benchmark was on KS pages...
#From KS discussion:
sysbench --test=cpu --cpu-max-prime=1000 run --num-threads=4
pi1 15.4134s
pi2 3.8831s
pi3 1.9542s
Pine64 0.1962s
EC2 HIMEM Instance 0.1473s
Intel i5-5200 0.1142s
If I posted something helpful, please rate +
(04-15-2016, 01:17 PM)TeaPack Wrote: (04-07-2016, 10:40 AM)stealthbanana Wrote: When I get a new comp, I like to run a basic benchmark, using the simple primes test from sysbench
Nice
Nope, just numbers without meaning as it's mostly the case when people play 'benchmarking gone wrong'. If you calculate prime numbers for a living sysbench is still the tool of choice.
If you want to learn what's essential when doing benchmarks (that means: almost all the times either throwing the results in the bin or tools and methodology) then start to read from here on: http://forum.odroid.com/viewtopic.php?f=136&t=19158
TL;DR: Using sysbench's cpu test based on calculating prime numbers to compare different architectures is simply fooling yourself.
(04-15-2016, 02:14 PM)tkaiser Wrote: (04-15-2016, 01:17 PM)TeaPack Wrote: (04-07-2016, 10:40 AM)stealthbanana Wrote: When I get a new comp, I like to run a basic benchmark, using the simple primes test from sysbench
Nice
Nope, just numbers without meaning as it's mostly the case when people play 'benchmarking gone wrong'. If you calculate prime numbers for a living sysbench is still the tool of choice.
If you want to learn what's essential when doing benchmarks (that means: almost all the times either throwing the results in the bin or tools and methodology) then start to read from here on: http://forum.odroid.com/viewtopic.php?f=136&t=19158
TL;DR: Using sysbench's cpu test based on calculating prime numbers to compare different architectures is simply fooling yourself.
Well, this was only in reaction to prime numbers sysbench post before. I have own methods to test computing power of boards based on application, for which I'm using it.
If I posted something helpful, please rate +
(04-15-2016, 02:32 PM)TeaPack Wrote: tkaiser
(04-15-2016, 01:17 PM)TeaPack Wrote: (04-07-2016, 10:40 AM)stealthbanana Wrote: When I get a new comp, I like to run a basic benchmark, using the simple primes test from sysbench
Nice Well, this was only in reaction to prime numbers sysbench post before. I have own methods to test computing power of boards based on application, for which I'm using it.
Sure, but meaningless numbers remain meaningless regardless what you do. 'Benchmarks' that run fractions of seconds are just a joke while this **whole** thread including external references might be pretty interesting when it's about the Pine64's or any more recent SBC's performance (and the many relationships between performance, temperatures, voltages, dvfs/cpufreq operating points, throttling strategies and all the many other relevant things people don't like to think about)
This thread is still pretty interesting as long as you're interested in 'real world' performance and not comparing numbers without meaning.
(04-15-2016, 02:45 PM)tkaiser Wrote: (04-15-2016, 02:32 PM)TeaPack Wrote: tkaiser
(04-15-2016, 01:17 PM)TeaPack Wrote: (04-07-2016, 10:40 AM)stealthbanana Wrote: When I get a new comp, I like to run a basic benchmark, using the simple primes test from sysbench
Nice Well, this was only in reaction to prime numbers sysbench post before. I have own methods to test computing power of boards based on application, for which I'm using it.
Sure, ...
This thread is still pretty interesting as long as you're interested in 'real world' performance and not comparing numbers without meaning.
=) I'll do some tests after receiving camera board. Is anywhere list of working/not working peripherals? And what is state of camera board?
If I posted something helpful, please rate +
(03-15-2016, 07:52 PM)tllim Wrote: (03-15-2016, 04:46 PM)janjwerner Wrote: http://www.aliexpress.com/item/FREE-Ship...50220.html
http://www.aliexpress.com/item/2-pcs-lot...87879.html
this is reasonable alternative if you can wait few days for shipping.
If you can wait a bit longer I would wait for heatsink that @tllim is working on. A large heatsink covering the SoC, memory and PMIC (with or without a larger fan) would be the best solution.
Here are the heat sink samples photos, Aluminum with copper plated. We will need to characterize the heat sink and will takes few week.
TL Lim, I was hoping you have any updates on the heat sink you were working on?
Also, 2 of my boards are defective apparently as I can't connect to the internet with them. Which is the procedure I'll have to follow?
(05-28-2016, 11:23 AM)g_t_j Wrote: (03-15-2016, 07:52 PM)tllim Wrote: (03-15-2016, 04:46 PM)janjwerner Wrote: http://www.aliexpress.com/item/FREE-Ship...50220.html
http://www.aliexpress.com/item/2-pcs-lot...87879.html
this is reasonable alternative if you can wait few days for shipping.
If you can wait a bit longer I would wait for heatsink that @tllim is working on. A large heatsink covering the SoC, memory and PMIC (with or without a larger fan) would be the best solution.
Here are the heat sink samples photos, Aluminum with copper plated. We will need to characterize the heat sink and will takes few week.
TL Lim, I was hoping you have any updates on the heat sink you were working on?
Also, 2 of my boards are defective apparently as I can't connect to the internet with them. Which is the procedure I'll have to follow?
The heatsink samples already build and tested. I have ship some out for try out and wait for respond.
How many boards that you have? Surprise to know that 2 of your boards are defective?
(05-28-2016, 07:31 PM)tllim Wrote: (05-28-2016, 11:23 AM)g_t_j Wrote: (03-15-2016, 07:52 PM)tllim Wrote: (03-15-2016, 04:46 PM)janjwerner Wrote: http://www.aliexpress.com/item/FREE-Ship...50220.html
http://www.aliexpress.com/item/2-pcs-lot...87879.html
this is reasonable alternative if you can wait few days for shipping.
If you can wait a bit longer I would wait for heatsink that @tllim is working on. A large heatsink covering the SoC, memory and PMIC (with or without a larger fan) would be the best solution.
Here are the heat sink samples photos, Aluminum with copper plated. We will need to characterize the heat sink and will takes few week.
TL Lim, I was hoping you have any updates on the heat sink you were working on?
Also, 2 of my boards are defective apparently as I can't connect to the internet with them. Which is the procedure I'll have to follow?
The heatsink samples already build and tested. I have ship some out for try out and wait for respond.
How many boards that you have? Surprise to know that 2 of your boards are defective?
2 out of 4 boards have problem with Internet.
I tested them under the same conditions (same cables Psu's, same sd card etc).
2 Of them perform just fine while on the other 2 Internet is extremely slow or non existent.
I would be keen on trying the heat sink.
(05-29-2016, 01:23 AM)g_t_j Wrote: (05-28-2016, 07:31 PM)tllim Wrote: (05-28-2016, 11:23 AM)g_t_j Wrote: (03-15-2016, 07:52 PM)tllim Wrote: (03-15-2016, 04:46 PM)janjwerner Wrote: http://www.aliexpress.com/item/FREE-Ship...50220.html
http://www.aliexpress.com/item/2-pcs-lot...87879.html
this is reasonable alternative if you can wait few days for shipping.
If you can wait a bit longer I would wait for heatsink that @tllim is working on. A large heatsink covering the SoC, memory and PMIC (with or without a larger fan) would be the best solution.
Here are the heat sink samples photos, Aluminum with copper plated. We will need to characterize the heat sink and will takes few week.
TL Lim, I was hoping you have any updates on the heat sink you were working on?
Also, 2 of my boards are defective apparently as I can't connect to the internet with them. Which is the procedure I'll have to follow?
The heatsink samples already build and tested. I have ship some out for try out and wait for respond.
How many boards that you have? Surprise to know that 2 of your boards are defective?
2 out of 4 boards have problem with Internet.
I tested them under the same conditions (same cables Psu's, same sd card etc).
2 Of them perform just fine while on the other 2 Internet is extremely slow or non existent.
I would be keen on trying the heat sink. Please check and make sure that on your setup there is no mac address duplication condition which can "confuse" router or switch.
|
