• HomeBoards
  • RulesRules
  • HelpHelp
  • WikiWiki
  • Donate

Author Topic: RG350, RG350M, GCW0 benchmark results  (Read 5240 times)

elea (OP)

  • Posts: 63
RG350, RG350M, GCW0 benchmark results
« on: June 06, 2020, 10:20:59 am »
Here are some benchmark results comparing the different OS's via Retrogame Handheld discord

It looks like the BLITTING results can vary about plus or minus 50 every time the benchmark is run. That means differences under 100 points aren't necessarily significant.

The RG350 is showing results that are 4% to 5% faster than the RG350M. Video driver differences maybe?

Also interesting that the latest GCW 0 firmware scored so much higher. I wonder if that's legit or due to the buildroot? This version of GPMark was also from that time.



GPMark OPK: https://ozgur.kazancci.com/jutleys/02-GCW%20Zero/GCW%20APPS/gpmark.opk

 
« Last Edit: June 06, 2020, 10:27:33 am by elea »

pcercuei

  • Posts: 1706
    • My devblog
Re: RG350, RG350M, GCW0 benchmark results
« Reply #1 on: June 06, 2020, 04:06:42 pm »
With the 5.7 kernel on the GCW-Zero (996 MHz), I get (software):
900.9
485.0
470.0
550.9
297.0
89.8
13.5

elea (OP)

  • Posts: 63
Re: RG350, RG350M, GCW0 benchmark results
« Reply #2 on: June 06, 2020, 04:20:54 pm »
@pcercuei Thank you! Is that with this specific version of the GPMark?

pcercuei

  • Posts: 1706
    • My devblog
Re: RG350, RG350M, GCW0 benchmark results
« Reply #3 on: June 06, 2020, 04:39:52 pm »
Yes, with the OPK linked above.

elea (OP)

  • Posts: 63
Re: RG350, RG350M, GCW0 benchmark results
« Reply #4 on: June 06, 2020, 06:21:34 pm »
OK, excellent. We're on the same page, so to speak.

Since you only posted the software benchmark numbers, I take it you're still working out some stuff with the GPU (or IPU).

pcercuei

  • Posts: 1706
    • My devblog
Re: RG350, RG350M, GCW0 benchmark results
« Reply #5 on: June 06, 2020, 06:28:03 pm »
Since you only posted the software benchmark numbers, I take it you're still working out some stuff with the GPU (or IPU).
No, that has nothing to do with the GPU or IPU. "Hardware surface" means the app renders directly to the framebuffer. "Software surface" means that it renders to an intermediate buffer, that is then copied to the framebuffer. That's why it's slower.

elea (OP)

  • Posts: 63
Re: RG350, RG350M, GCW0 benchmark results
« Reply #6 on: June 06, 2020, 10:19:22 pm »
Ohhh, sorry! I completely glossed over that part of this discussion:

https://boards.dingoonity.org/dingux-releases/gpmark-for-opendingux/msg48095/#msg48095

So yeah, 3d acceleration tests have never been implemented in GPMark.

Ninoh-FOX

  • Posts: 128
Re: RG350, RG350M, GCW0 benchmark results
« Reply #7 on: June 07, 2020, 05:47:46 am »
the differences between RG350M and RG350 not is exactly the video driver, this is the same, is the panel driver, the driver for lcd screen.

elea (OP)

  • Posts: 63
Re: RG350, RG350M, GCW0 benchmark results
« Reply #8 on: June 07, 2020, 10:14:24 am »
When somebody says "video driver", I think it's usually obvious it includes code that drives a specific display. But it's OK I guess if you really want to consider the panel driver as something separate.

Anyhow, I wonder if there's any way to optimize the way data is processed by the RG350M's 640x480 NV3052C panel?

Or maybe the RG350M just has to have to live with a 4-5% performance decrease for sending 4 times as many pixels to the display.

pcercuei

  • Posts: 1706
    • My devblog
Re: RG350, RG350M, GCW0 benchmark results
« Reply #9 on: June 07, 2020, 12:15:38 pm »
When somebody says "video driver", I think it's usually obvious it includes code that drives a specific display. But it's OK I guess if you really want to consider the panel driver as something separate.
It *is* a separate thing.

Or maybe the RG350M just has to have to live with a 4-5% performance decrease for sending 4 times as many pixels to the display.
The extra overhead is probably caused by memory bus pressure when the data is sent from the IPU to the LCD controller. There is nothing to be done here.

elea (OP)

  • Posts: 63
Re: RG350, RG350M, GCW0 benchmark results
« Reply #10 on: June 07, 2020, 08:45:48 pm »
OK, I gladly stand corrected on the video driver vs panel driver terminology. Learn something new every day!

As for performance, I'll be curious to benchmark the JZ4770-based RG280M with its 2.8" 320x480 display (just like the RG300 2.8" IPS):

<a href="https://www.youtube.com/watch?v=fWYR9h2US0w" target="_blank">https://www.youtube.com/watch?v=fWYR9h2US0w</a>
« Last Edit: June 07, 2020, 08:47:33 pm by elea »

Statscowski

  • Posts: 1
Re: RG350, RG350M, GCW0 benchmark results
« Reply #11 on: July 25, 2020, 07:12:46 pm »
I recently got my RG280M. This is my very first retro handheld device, but I was very enamored by the form factor.

The build quality is great - but I was very unsatisfied by the PS1 and GBA performance. Thus I tested my device to compare it:

Hardware
Blitting 2081
Plasma 657
Rotozoomer 643
Rotozoomer Near 794
Rotozoomer Far 353
Radial Blur 94
Bunny 13

Software
Blitting 609
Plasma 399
Rotozoomer 382
Rotozoomer Near 441
Rotozoomer Far 252
Radial Blur 86
Bunny 13

Results are within range of the 350, although maybe around 10% slower.

This is kind of disappointing. I was hoping to find out there was something wrong with my device. I guss all the reviewers just have lower standards when they say it runs most games without problems.

8bit

  • Posts: 17
Re: RG350, RG350M, GCW0 benchmark results
« Reply #12 on: July 26, 2020, 12:07:41 am »
Quote
This is kind of disappointing. I was hoping to find out there was something wrong with my device. I guss all the reviewers just have lower standards when they say it runs most games without problems.

This isn't a personal attack, so please don't read it as such but I've never been able to understand people who buy these devices, expecting them to run every emulator for every console completely flawlessly.

Want (close to) flawless and portable PS1 performance?, buy a PSP. Want cycle-accurate GBA emulation?, pick up a GBA micro or a New 3DS.

People who tell you emulation on a (comparatively) cheap off-brand device, which is (by this point), based off ageing JZ technology are judging these devices for what they are; a Jack of all trades [and a master of none].

These will be the same people who tell you the Odroid Go Advanced is a "Portable Dreamcast". SPOILER: It ISN'T. They're either dis-illusioned, lying for views or have never used the real hardware and are judging emulation from watching let's plays on YouTube.

Personally, I buy these devices as fun distraction, knowing the emulation is "close enough". I don't expect them to be 100% cycle accurate. That'd be a foolish assumption on my part.

I've purchased a number of these Chinese devices in the past, as well as modding original portable hardware to allow home brew emulation.

None (and I mean NONE) provide 100% cycle accurate emulation of non-native hardware. You don't buy a PSP to play SNES ROMs. It's just a happy coincidence that an emulator has been ported to the device and you just happen to have a folder full of ROMs (which, [of course] you happen to also own the originals of).

Having recently watched a handful of those "Is the PSP still relevant in 2020?" Videos on YouTube, I decided to dust off my PSPs and update their CFW to test how far emulation has come on such mature hardware.

One YouTuber said recent updates in N64 emulation made the N64 playable on PSP (and yes, this was a recent update).

Playing Mario Kart 64 under emulation on PSP is... um... ...interesting, to say the least.

"Optimisations" mean your kart sometimes appears to go around the track without sprite rotation; meaning your kart might at some stage, look like it's driving backwards. These aren't optimisations, these are unacceptable workarounds to bring the perceived FPS up to that "close enough" level.

The closest I've come to an all-in-one emulation device is a New 3DS with *ahem* "customisations". Certainly for Nintendo handheld emulation. Using third-party software, it's possible to put a wrapper around certain ROMs to make them playable on the device. DS (via an R4 cart), GBA, GBC, GB, and to an extent, SNES and NES all run well. Certainly better than on the RG350 or OGA...

The 3DS is my go-to for any pre-Switch Pokemon games. I'm able to have access to ALL on one device with better emulation than any of the JZ devices

You mention this is your first emulation device. I hope this experience proves a valuable learning lesson and it won't put you off an otherwise fun hobby?
« Last Edit: July 26, 2020, 12:29:06 am by 8bit »

HercTNT

  • Posts: 700
Re: RG350, RG350M, GCW0 benchmark results
« Reply #13 on: July 26, 2020, 04:48:00 am »
I have to second what 8-bit has said. Not personal at all, but a learning expirience. People expect to much from them. They are amazing devices though. Think how much more than can do now with custom firmware and community support compared to stock.
To summarize what 8-bit said, if you want perfection you need the original units. Otherwise these reasonably cheap consoles provide "good enough" quality for most retrogamers that just want to enjoy the classics on the go.
Truly hope you enjoy your device and learn to love it for it's quirky appeal.

elea (OP)

  • Posts: 63
Re: RG350, RG350M, GCW0 benchmark results
« Reply #14 on: July 26, 2020, 11:41:19 am »
@Statscowski you need to run the benchmark at least 3 times to get an idea what the highest results are.

pcercuei

  • Posts: 1706
    • My devblog
Re: RG350, RG350M, GCW0 benchmark results
« Reply #15 on: July 26, 2020, 11:42:43 am »
Statscowski is right that the numbers are really low, which is not normal for that handheld. It uses the same SoC as the RG350 and the GCW-Zero after all, so it should get similar numbers.

elea (OP)

  • Posts: 63
Re: RG350, RG350M, GCW0 benchmark results
« Reply #16 on: July 26, 2020, 06:44:13 pm »
fwiw I've occasionally seen some very low outlying benchmarks with GPMark, which is why I suggested to run it 3 times.

It could have just been a fluke occurrence.

pcercuei

  • Posts: 1706
    • My devblog
Re: RG350, RG350M, GCW0 benchmark results
« Reply #17 on: July 26, 2020, 09:51:20 pm »
fwiw I've occasionally seen some very low outlying benchmarks with GPMark, which is why I suggested to run it 3 times.

It could have just been a fluke occurrence.
Well that's not normal. It shouldn't fluctuate more than a few (~2) percents of the mean value.

SML

  • Posts: 16
Re: RG350, RG350M, GCW0 benchmark results
« Reply #18 on: August 20, 2020, 03:07:58 pm »
Here's what the .opk in the OP returns on my 280m:

GPMARK Hardware

1st
2057.6
661.5
646.6
793.4
355.6
94.5
13.0

2nd
2124.6
665.6
647.0
798.0
355.8
94.6
13.0

3rd
2139.8
665.9
649.8
798.0
356.4
94.6
13.0

4th
2115.7
664.6
645.4
794.9
355.2
94.6
13.0


GPMARK Software

1st
597.4
390.5
376.4
434.6
251.3
85.6
12.8

2nd
669.0
404.0
384.8
450.3
254.6
85.6
12.6

3rd
637.9
399.5
380.7
444.4
253.9
85.6
12.8

4th
615.4
393.0
373.1
436.0
249.8
85.6
12.8

SML

  • Posts: 16
Re: RG350, RG350M, GCW0 benchmark results
« Reply #19 on: August 20, 2020, 04:16:58 pm »
For what it's worth, my 280m feels inconsistent in comparison to my 350m. I'm using stock everything and Super Punchout had slowdown in the middle of a fight for no apparent reason.