Login
Username:

Password:

Remember me



Lost Password?

Register now!

Sections

Who's Online
92 user(s) are online (37 user(s) are browsing Forums)

Members: 3
Guests: 89

Murakami, emeck, kas1e, more...

Headlines

Forum Index


Board index » All Posts (Maijestro)




Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@whiteQuote:
white wrote:@Maijestro

Yes what you say is true
One user had managed to get Picasso IV working
but he didn't want to say how to do it and make it available
this a few years ago.

I guess with the Cirrus Driver probably like you did by editing the iso.


BALATON Zoltan also told me about it, we don't know if it's really true and being able to use 68k drivers under a PPC system emulation makes no sense, it's like when we could use SFS 68k, but it didn't bring any speed improvement. With the PPC native version of SFS and the right CPU there was a real boost in speed.

Nevertheless, I'm glad to have met you, at that time you helped me a lot with WinUae and I was able to show my gratitude and help you now

I will also support the Qemu emulation in the future because I already like using it with AmigaOs4.1

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@whiteQuote:
white wrote:@Maijestro

Yes, unfortunately it will take some time.
Too bad qemu has a fast cpu
but it has a SM502 graphics card comparable to the voodoo 3 but without "minigl" support but faster.

While WinUAE has slower cpu but not that slow.
When using UAEGFX...
Using UAEGFX all videos with YT are played in 1024x768
And also coffinOS can be selected at 1920x1080 in SDL I have any Workbench 3.xx

I tested the various applications

Eh it will take some time yes a pity if the two emulations were combined it would be a big step forward

Basically like any OS it is the graphics card that makes the difference.

As indeed it is for other systems


We could make this happen with crowdfunding, I would participate with a sum that is in the triple digits, but again there would not be much support as most Qemu Peg2 users have already had to pay once to use the emulation by buying the AmigaOs4.1 Pegasos 2 version for it.

Software development is very time consuming and especially when it comes to writing graphics card drivers, not everyone is able to do it. So things stay as they are....there was no one who tested Qemu with modified AmigaOs4.1 Peg2 until I did.

We could have had this emulation about 2 years ago. BALATON Zoltan announced this information much earlier, but nobody wanted to try it. I am satisfied with how things are already going and what will happen in the future remains to be seen.


Edited by Maijestro on 2023/5/27 21:11:35
Edited by Maijestro on 2023/5/27 21:17:59
MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@whiteQuote:
white wrote:@Maijestro

Here you can see E-UAE SDL with CoffinOS
it's simply a test works well but clearly has its limitations
also due to the video memory that can be allocated.

It is better to use the non-SDL version to see demos etc.

But it doesn't work badly
I don't know if you have enabled the JIT in your configuration
if you need a config file as an example let me know.



I'm not sure if I have Jit enabled either. Here is my uaerc configuration:config_description=UAE default configuration
config_hardware=false
config_host=false
config_version=0.8.29
amiga.rom_path=
amiga.floppy_path=
amiga.hardfile_path=
amiga.savestate_path=
amiga.cpu_idle=0
ppc.use_tbc=yes
amiga.screen_type=public
amiga.publicscreen=
amiga.use_dither=true
amiga.use_grey=false
use_gui=yes
use_debugger=no
kickstart_rom_file=Workbench:Emulation/RunInUAE/E-UAE-amigfx/kick3.1.rom
kickstart_ext_rom_file=
kickstart_key_file=
flash_file=
cart_file=
kickshifter=false
floppy0=
floppy0type=0
floppy1=
floppy1type=0
floppy2=
floppy2type=-1
floppy3=
floppy3type=-1
nr_floppies=2
floppy_speed=800
parallel_on_demand=false
serial_on_demand=false
serial_hardware_ctsrts=true
serial_direct=false
scsi=false
scsi_device=
sound_output=exact
sound_channels=stereo
sound_stereo_separation=7
sound_stereo_mixing_delay=0
sound_frequency=11025
sound_interpol=none
sound_adjust=0
sound_volume=0
sound_latency=100
joyport0=mouse
joyport1=kbd1
bsdsocket_emu=false
synchronize_clock=no
maprom=0x0
gfx_framerate=1
gfx_width=720
gfx_height=568
gfx_width_windowed=720
gfx_height_windowed=568
gfx_width_fullscreen=800
gfx_height_fullscreen=600
gfx_refreshrate=0
gfx_vsync=false
gfx_lores=false
gfx_linemode=double
gfx_correct_aspect=false
gfx_fullscreen_amiga=false
gfx_fullscreen_picasso=false
gfx_center_horizontal=none
gfx_center_vertical=none
gfx_colour_mode=8bit
immediate_blits=false
ntsc=false
hide_cursor=true
show_leds=false
keyboard_leds=numlock:none,capslock:none,scrolllock:none
chipset=aga
collision_level=playfields
fastmem_size=8
a3000mem_size=0
z3mem_size=128
bogomem_size=0
gfxcard_size=0
chipmem_size=4
cpu_speed=max
cpu_type=68040
cpu_compatible=true
cpu_cycle_exact=false
blitter_cycle_exact=false
log_illegal_mem=false
catweasel_io=0x0
kbd_lang=us
state_replay=no
state_replay_rate=250
state_replay_buffer=20971520
hardfile2=rw,Workbench:Download:System.hdf,0,0,0,512,0,
hardfile=rw,0,0,0,512,Download:System.hdf
input.config=0
input.joymouse_speed_analog=20
input.joymouse_speed_digital=10
input.joymouse_deadzone=33
input.joystick_deadzone=33
input.mouse_speed=100
input.autofire=10
input.1.mouse.0.disabled=0
input.1.mouse.0.axis.0=MOUSE1_HORIZ.0
input.1.mouse.0.axis.1=MOUSE1_VERT.0
input.1.mouse.0.axis.2=MOUSE1_WHEEL.0
input.1.mouse.0.button.0=JOY1_FIRE_BUTTON.0
input.1.mouse.0.button.1=JOY1_2ND_BUTTON.0
input.1.mouse.0.button.2=JOY1_3RD_BUTTON.0
input.2.mouse.0.disabled=0
input.2.mouse.0.axis.0=MOUSE1_HORIZ.0
input.2.mouse.0.axis.1=MOUSE1_VERT.0
input.2.mouse.0.axis.2=MOUSE1_WHEEL.0
input.2.mouse.0.button.0=JOY1_FIRE_BUTTON.0
input.2.mouse.0.button.1=JOY1_2ND_BUTTON.0
input.2.mouse.0.button.2=JOY1_3RD_BUTTON.0
input.3.mouse.0.disabled=0
input.3.mouse.0.axis.0=MOUSE1_HORIZ.0
input.3.mouse.0.axis.1=MOUSE1_VERT.0
input.3.mouse.0.axis.2=MOUSE1_WHEEL.0
input.3.mouse.0.button.0=JOY1_FIRE_BUTTON.0
input.3.mouse.0.button.1=JOY1_2ND_BUTTON.0
input.3.mouse.0.button.2=JOY1_3RD_BUTTON.0
input.4.mouse.0.disabled=0
input.4.mouse.0.axis.0=MOUSE1_HORIZ.0
input.4.mouse.0.axis.1=MOUSE1_VERT.0
input.4.mouse.0.axis.2=MOUSE1_WHEEL.0
input.4.mouse.0.button.0=JOY1_FIRE_BUTTON.0
input.4.mouse.0.button.1=JOY1_2ND_BUTTON.0
input.4.mouse.0.button.2=JOY1_3RD_BUTTON.0
cachesize=8192
cpu_compatible=false
cpu_cycle_exact=false
blitter_cycle_exact=false
comp_constjump=yes
comp_trustbyte=indirect
comp_trustword=indirect
comp_trustlong=indirect
comp_optimize=true

And here is the uaerc_RunInUAE configuration:

# UAE config for RunInUAE, which is designed to modify an existing working UAE config

# Use 3.1 Kickstart for Workbench, but allow ADF-booted games to still use an older Kickstart
kickstart_rom_file=kick3.1.rom

# Emulate an A1200, but still allow A500 emulation for ADF-booted games
cpu_type=68020
cpu_speed=max
chipmem_size=4

chipset=aga
#collision_level=none

# Emulate an expanded A1200 with 8MB of Fast Ram!
fastmem_size=8

# Set frame skipping (1=show all frames, 2=show every 2nd frame, 3=show every 3rd frame, etc)
#gfx_framerate=2

# Add floppy disk which can be used for saving games
floppy0=PROGDIR:SaveGames.adf

# Filesystem settings for virtual devices
filesystem2=rw,DH0:Workbench:Sys:Emulation/RunInUAE/WB31,1

#RUNINUAE: SCREENMODE=ScreenMode_HiRes.prefs
filesystem2=ro,Games_:Games:Games:,-1

Quote:

I'm testing qemu in general, apart from the graphics card, I'd say that there are excellent premises.

ZBalaton could easily implement Voodoo3 but prefers to spend his time on an ATI card.
Since the Voodoo3 then has limitations in OS 4.1.


BALATON Zoltan thinks that the Voodoo 3 support will not work in the long run, I agree with him an ATI support would be the better way and also future proof for Qemu and AmigaOs4.1. The Voodoo 3 cards are very limited with their limited memory.

Qemu Peg2 is an excellent emulation, but it has little to no support and so things will remain as they are at the moment. We have to make do with what we already have, even if it is very limited. There won't be any new drivers either, there just aren't enough developers to do that.

BALATON Zoltan will have the ATI emulation closed maybe in 3-4 years, he only works on it then and when he feels like it.

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@smarkusgQuote:
smarkusg wrote:@Maijestro
If you have the option, for games use uae-amigfx - it's much faster and more 'native'. It should work much better and runs on the QEMU G4.
uae-sdl only for graphics modes other than AGA/ECS/OCS (Picasso 96).



I have compared and tested both versions uae-amigfx sdl and without sdl are about the same from the speed. As @white already writes the difference is that the version without SDL can not use uaegfx card. The sdl version can, but only runs on CPU G3. For my purposes, the version without SDL is enough. Thanks for the tip.


Quote:
You asked recently how the boot speed is. The speed is similar to yours. I've been using OS4 for 2 months and have been making small improvements.


Impressive that it runs so well even under the MacMini with M1, I would still be interested in a benchmark, could you run this benchmark by Hans? I would like to capture the differences to my Mac Studio.

https://www.amigans.net/modules/newbb/ ... php?topic_id=9226&start=0

Also to be able to execute Qemu over a start script I did not succeed, I see you could solve this very well, is there a possibility that I can throw your start script also for my machine, you could send it to me and I adapt then my paths to this script. It should be possible that you can edit it again after the creation?

Greetings

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: QEMU Emulation vs Hardware CPU Benchmarks
Quite a regular
Quite a regular


Here are a few benchmarks posted on Amiga-News.de.

QEmu Pagasos II Emulation auf:
Intel i5 6600k 3.7Ghz
32GB DDR4 RAM
GTX 1050Ti

code:
CPUBench v1.0


RageMem:

RAGEMEM v0.37 - compiled 11/06/2010

CPU: Motorola MPC 7447/7457 Apollo 1.1 @ 1533 Mhz
Caches Sizes: L1: 32 KB - L2: 512 KB - L3: none
Cache Line: 32

---> CPU <---
MAX MIPS: 4516

---> L1 <---
READ32: 3370 MB/Sec
READ64: 5291 MB/Sec
WRITE32: 3304 MB/Sec
WRITE64: 5323 MB/Sec

---> L2 <---
READ32: 3453 MB/Sec
READ64: 5273 MB/Sec
WRITE32: 3320 MB/Sec
WRITE64: 5426 MB/Sec

---> RAM <---
READ32: 2559 MB/Sec
READ64: 3602 MB/Sec
WRITE32: 2420 MB/Sec
WRITE64: 3263 MB/Sec
WRITE: 1433 MB/Sec (Tricky)

---> VIDEO BUS <---
READ: 5142 MB/Sec
WRITE: 4913 MB/Sec



SortBench:
-------------------------------------------------------------
SORTBENCH 1.1 (Gunnar von Boehn)
Its a CPU benchmark that stresses CPU, DCache and branch prediction.
-------------------------------------------------------------
1 K Element : 1562.84 MB/sec
2 K Element : 1560.56 MB/sec
4 K Element : 1568.15 MB/sec
8 K Element : 1558.63 MB/sec
16 K Element : 1508.89 MB/sec
32 K Element : 1510.86 MB/sec


BogoMIPS:
Calibrating delay loop..

Ok - 400.00 BogoMips



Dhrystone:
Dhrystone Benchmark, Version 2.1 (Language: C)
Program compiled without 'register' attribute

Execution starts, 50000000 runs through Dhrystone
Execution ends

Final values of the variables used in the benchmark:

Int_Glob: 5
should be: 5
Bool_Glob: 1
should be: 1
Ch_1_Glob: A
should be: A
Ch_2_Glob: B
should be: B
Arr_1_Glob[8]: 7
should be: 7
Arr_2_Glob[8][7]: 50000010
should be: Number_Of_Runs + 10
Ptr_Glob->
Ptr_Comp: 1716026968
should be: (implementation-dependent)
Discr: 0
should be: 0
Enum_Comp: 2
should be: 2
Int_Comp: 17
should be: 17
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Next_Ptr_Glob->
Ptr_Comp: 1716026968
should be: (implementation-dependent), same as above
Discr: 0
should be: 0
Enum_Comp: 1
should be: 1
Int_Comp: 18
should be: 18
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Int_1_Loc: 5
should be: 5
Int_2_Loc: 13
should be: 13
Int_3_Loc: 7
should be: 7
Enum_Loc: 1
should be: 1
Str_1_Loc: DHRYSTONE PROGRAM, 1'ST STRING
should be: DHRYSTONE PROGRAM, 1'ST STRING
Str_2_Loc: DHRYSTONE PROGRAM, 2'ND STRING
should be: DHRYSTONE PROGRAM, 2'ND STRING

Duration in seconds: 55.1
Microseconds for one run through Dhrystone: 1.1
Dhrystones per Second: 908227.3
Dhrystone MIPS (DMIPS) 516



Quicksort:
Elaborating quicksort of 1000 numbers repeated for 10 times
Unsorted array:
Total time taken by CPU: 4.42


Sieve:

Sieve of Eratosthenes (Scaled to 10 Iterations)
Version 1.2, 03 April 1992

Array Size Number Last Prime Linear RunTime MIPS
(Bytes) of Primes Time(sec) (Sec)
8191 1899 16381 0.001259 0.001259 1317.0
10000 2261 19997 0.001537 0.001564 1299.1
20000 4202 39989 0.003074 0.066833 61.6
40000 7836 79999 0.006147 0.073547 113.3
80000 14683 160001 0.012295 0.014038 1201.0
160000 27607 319993 0.024590 0.029907 1139.8
320000 52073 639997 0.049180 0.062256 1106.4
640000 98609 1279997 0.098360 0.151367 919.1
1280000 187133 2559989 0.196719 0.834961 336.4
2560000 356243 5119997 0.393439 0.673828 841.1
5120000 679460 10239989 0.786877 1.406250 813.0
10240000 1299068 20479999 1.573755 3.593750 641.5
20480000 2488465 40960001 3.147510 8.203125 566.5

Relative to 10 Iterations and the 8191 Array Size:
Average RunTime = 0.005183 (sec)
High MIPS = 1317.0
Low MIPS = 61.6



Whetstone:

Please wait...

Loops: 50000 Iterations: 1 Duration: 27.2 seconds
C Converted Double Precision Whetstones: 184.0 MIPS


All tests done.

and this:


QEmu Pegasos II Emulation auf:
Intel i7 9700 3.0Ghz
16GB DDR4 RAM
Radeon RX 6600XT
Windows 10

code:
CPUBench v1.0


RageMem:

RAGEMEM v0.37 - compiled 11/06/2010

CPU: Motorola MPC 7447/7457 Apollo 1.1 @ 1533 Mhz
Caches Sizes: L1: 32 KB - L2: 512 KB - L3: none
Cache Line: 32

---> CPU <---
MAX MIPS: 5903

---> L1 <---
READ32: 4290 MB/Sec
READ64: 6764 MB/Sec
WRITE32: 4004 MB/Sec
WRITE64: 6615 MB/Sec

---> L2 <---
READ32: 4317 MB/Sec
READ64: 6696 MB/Sec
WRITE32: 4160 MB/Sec
WRITE64: 6728 MB/Sec

---> RAM <---
READ32: 3210 MB/Sec
READ64: 4465 MB/Sec
WRITE32: 3046 MB/Sec
WRITE64: 6432 MB/Sec
WRITE: 1832 MB/Sec (Tricky)

---> VIDEO BUS <---
READ: 5918 MB/Sec
WRITE: 6602 MB/Sec



SortBench:
-------------------------------------------------------------
SORTBENCH 1.1 (Gunnar von Boehn)
Its a CPU benchmark that stresses CPU, DCache and branch prediction.
-------------------------------------------------------------
1 K Element : 1883.10 MB/sec
2 K Element : 1914.08 MB/sec
4 K Element : 1932.43 MB/sec
8 K Element : 1938.04 MB/sec
16 K Element : 1941.31 MB/sec
32 K Element : 1943.28 MB/sec


BogoMIPS:
Calibrating delay loop..

Ok - 512.00 BogoMips



Dhrystone:
Dhrystone Benchmark, Version 2.1 (Language: C)
Program compiled without 'register' attribute

Execution starts, 50000000 runs through Dhrystone
Execution ends

Final values of the variables used in the benchmark:

Int_Glob: 5
should be: 5
Bool_Glob: 1
should be: 1
Ch_1_Glob: A
should be: A
Ch_2_Glob: B
should be: B
Arr_1_Glob[8]: 7
should be: 7
Arr_2_Glob[8][7]: 50000010
should be: Number_Of_Runs + 10
Ptr_Glob->
Ptr_Comp: 1724221040
should be: (implementation-dependent)
Discr: 0
should be: 0
Enum_Comp: 2
should be: 2
Int_Comp: 17
should be: 17
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Next_Ptr_Glob->
Ptr_Comp: 1724221040
should be: (implementation-dependent), same as above
Discr: 0
should be: 0
Enum_Comp: 1
should be: 1
Int_Comp: 18
should be: 18
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Int_1_Loc: 5
should be: 5
Int_2_Loc: 13
should be: 13
Int_3_Loc: 7
should be: 7
Enum_Loc: 1
should be: 1
Str_1_Loc: DHRYSTONE PROGRAM, 1'ST STRING
should be: DHRYSTONE PROGRAM, 1'ST STRING
Str_2_Loc: DHRYSTONE PROGRAM, 2'ND STRING
should be: DHRYSTONE PROGRAM, 2'ND STRING

Duration in seconds: 46.8
Microseconds for one run through Dhrystone: 0.9
Dhrystones per Second: 1067439.8
Dhrystone MIPS (DMIPS) 607



Quicksort:
Elaborating quicksort of 1000 numbers repeated for 10 times
Unsorted array:
Total time taken by CPU: 3.50


Sieve:

Sieve of Eratosthenes (Scaled to 10 Iterations)
Version 1.2, 03 April 1992

Array Size Number Last Prime Linear RunTime MIPS
(Bytes) of Primes Time(sec) (Sec)
8191 1899 16381 0.000973 0.000973 1704.4
10000 2261 19997 0.001188 0.001259 1614.0
20000 4202 39989 0.002375 0.002556 1610.6
40000 7836 79999 0.004750 0.005035 1654.9
80000 14683 160001 0.009501 0.010986 1534.6
160000 27607 319993 0.019001 0.021973 1551.3
320000 52073 639997 0.038003 0.043335 1589.5
640000 98609 1279997 0.076005 0.092773 1499.6
1280000 187133 2559989 0.152010 0.200195 1403.0
2560000 356243 5119997 0.304021 0.400391 1415.6
5120000 679460 10239989 0.608042 0.800781 1427.7
10240000 1299068 20479999 1.216083 3.886719 593.1
20480000 2488465 40960001 2.432166 10.390625 447.2

Relative to 10 Iterations and the 8191 Array Size:
Average RunTime = 0.001518 (sec)
High MIPS = 1704.4
Low MIPS = 447.2



Whetstone:

Please wait...

Loops: 50000 Iterations: 1 Duration: 20.0 seconds
C Converted Double Precision Whetstones: 250.2 MIPS


All tests done.


Source:

https://www.amiga-news.de/de/forum/thr ... 36423&start=211&BoardID=6

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@white

Ok, I did some quick tests with their linked E-Uae version, running the game "Heirs of Earth" it has been a very computationally intensive game under Amiga 1200. It runs perfectly without any lags. I never played this game on my Amiga 1200, but I thought the intro was awesome with that voice-over. Thanks




MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@whiteQuote:
white wrote:@Maijestro

most likely you are having the error I had with pythonSSL.

Do this download AmiSSL
aminet for OS 4.1

install
https://aminet.net/util/libs/AmiSSL-4.12.lha
or
https://github.com/jens-maus/amissl/releases/4.7


restart and then install the latest version of AmiSSL again
5.8
now it should work.


you can see the thread here:

https://www.amigans.net/modules/newbb/viewtopic.php?post_id=139158


Thanks my friend that solved my problem, PhytonSSL is not compatible with Newer AmiSSL over 5.x versions especially on first time setup, TwitchTV works perfectly now

@jeorg @ktadd

APPDIR is fantastic, I didn't know that AmigaOs4.1 can remember the paths automatically too. It of course saves some time with the otherwise manual setting of paths where that program is located, great feature. Again something learned and thanks again for the fast help, you are great!

@walkero

Thanks for the script compilation of AioStream

Greetings

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@whiteQuote:
white wrote:@Maijestro

TwitchTV:
add in Odyssey menus:

LINK TWICHTV python Amiga:Utilities/aiostreams/twitch.py -u %l -ssh

if you have "Emotion" in Utilities you don't need to do anything else

python-ssl files should be copied to:
Amiga:System/Python/Lib/dynload

https://aiostreams.amiga-projects.net/

thanks again to "walkero" for this great program


You're probably right I sent you the version that starts FFPLAY

if so, just edit the file in the aiostreams folder:

cfg.py

is edit the lines;

sPlayer = your path of Emotion

and then:
sPlayerArgs = ""


Ok thanks for UAE and also the explanation of TwitchTV.

Unfortunately I can't get it to run...Phyton SSL is installed properly as described, Emotion is in Utilities for me and the path in Odyssey is set. I am not sure what I am doing wrong and need more help. These are the paths I changed in the cfg.py file:

# Set the path to your preffered video player. This is going to be used on recorded streams only.
# This is used only if autoplay is set to True.
#vPlayer = "APPDIR:Work:Player/Emotion/Emotion"
vPlayer = "APPDIR:SYS:Utilities/MickjT-MPlayer/mplayer-nonaltivec"
# Set the arguments that are going to be used with your preffered video player.
#vPlayerArgs = ""
vPlayerArgs = "-vo sdl -quiet -really-quiet"

# Set the path to your preffered video player. This is going to be used mostly on live streams,
# but depending the network, might be used on recorder streams as well.
# This is used only if autoplay is set to True.
sPlayer = "APPDIR:SYS:Utilities/Emotion/Emotion"
# Set the arguments that are going to be used with your preffered streaming player.
sPlayerArgs = ""
aPlayer = "APPDIR:Work:AmigaAMP3/AmigaAMP3"
aPlayerArgs = ""

Nevertheless I get this error message:

Resized Image

Resized Image

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@HansQuote:
Hans wrote:@geennaam

Quote:
As far as I understand, the KVM based virtual machine uses the CPU directly. This means that the kernel must be able to handle the specific CPU of the host. And I doubt that ExecSG "speaks" e6500, PPC970 or POWER9 yet.

Correct. And, as Joerg points out, each kernel is tailored to a specific CPU. The A1-X1000's kernel is most likely to run on a G5, although its likely that the differences are just big enough that it won't work.

This is something that the ExecSG team could address.

In the meantime, there's nothing stopping anyone from using Qemu in emulation mode on a G5... with all the overhead that entails.

Hans



BALATON Zoltan reads here from time to time and especially when it is directly about Qemu. Since I am in good contact with him he wrote me this, I am not sure if it is helpful.

Quote:
I've seen some discussion about KVM on the amigans.net thread. I've
updated the FAQ entry about this at https://qmiga.osdn.io/#faq with the
info I have so far. If somebody has a G4 host with Linux that has the
highest chance to work, I've also heard about people being able to run
something on G5 but using 32 bit kernel and even MacOS on POWER9 should be
possible so it may work with AmigaOS too but it needs somebody to
experiment with it and report the poroblems to the qemu-ppc list or
appropriate Linux list. I don't have PPC hardware to help much with that
but interested to hear the results anyway.

I don't know if this is still up to date but somebody trying to debug KVM
on PPC might need something like this:
https://www.linux-kvm.org/page/Perf_events

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: QEMU-Emulation vs. Hardware-CPU-Benchmarks
Quite a regular
Quite a regular


@joergQuote:
joerg wrote:@Maijestro
Quote:

---> VIDEOBUS <---
READ: 8767 MB/S.
WRITE: 10102 MB/sec.

That impressed me the most, how does that come about,
Because you are testing mainboard RAM accesses, the part of it used for the SM501 emulation, not gfx card RAM accesses.
The RageMem L1/L2 cache results compared to RAM ones are of course wrong as well, your host CPU has much larger L1 and L2 caches than the emulated 32/512 KB.

Unlike QEmu UAE seems to support direct access to the gfx card, for example compare derfs QEmu results (11034/5330 MB/s) with the UAE (51/49 MB/s) ones.

Quote:
Now can I please get a 32 bit driver for AmigaOs4.1 so we can move on to the GPU benchmark ? Don't take it seriously it's just a joke...
To get usable gfx speed you need an AmigaOS gfx driver for QEmu, just like the uaegfx driver used in UAE.
Best way for implementing a QEmu gfx driver would probably be one using Cairo and/or OpenGL, that way it would work with any host gfx card.
The currently used SM501/2 emulation is the worst possible way, because of it's strange 4 byte 24 bit modes neither supported by AmigaOS nor host gfx cards, and even emulating a Permedia 2 or a Voodoo 3/5 would be much better than that.


Thank you for the explanation. And yes the sm501 emulation is a dead end, only 2d acceleration, 16 bit and the limited resolutions. Your solution sounds promising in theory, it will surely be a lot of work and for that probably no one will be willing to do that.

Anyway I got more help here than I would have expected and also some bugs in SDL2 were fixed because I reported them or were uncovered by using them in 16 bit and for that I am already very grateful.

Also we both had a bad start but I think that you understand some things better now and I am not a troll but it is important to me that I want to use AmigaOs4.1 best possible on my hardware.

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: QEMU Emulation vs Hardware CPU Benchmarks
Quite a regular
Quite a regular


@Hans

First of all, thanks for the great compilation and the script which works very well.

Here now also my result under Qemu, the hardware they please take from my signature.

CPUBench v1.0


RageMem:

RAGEMEM v0.37 - compiled 11/06/2010

CPU: Motorola MPC 7447/7457 Apollo 1.2 @ 1533 Mhz
Caches Sizes: L1: 32 KB - L2: 512 KB - L3: none
Cache Line: 32

---> CPU <---
MAX MIPS: 9845

---> L1 <---
READ32: 5848 MB/Sec
READ64: 8829 MB/Sec
WRITE32: 6469 MB/Sec
WRITE64: 10205 MB/Sec

---> L2 <---
READ32: 5812 MB/Sec
READ64: 8822 MB/Sec
WRITE32: 6452 MB/Sec
WRITE64: 10234 MB/Sec

---> RAM <---
READ32: 5172 MB/Sec
READ64: 7506 MB/Sec
WRITE32: 5408 MB/Sec
WRITE64: 10191 MB/Sec
WRITE: 2943 MB/Sec (Tricky)

---> VIDEO BUS <---
READ: 8767 MB/Sec
WRITE: 10102 MB/Sec



SortBench:
-------------------------------------------------------------
SORTBENCH 1.1 (Gunnar von Boehn)
Its a CPU benchmark that stresses CPU, DCache and branch prediction.
-------------------------------------------------------------
1 K Element : 3091.48 MB/sec
2 K Element : 3103.53 MB/sec
4 K Element : 3110.91 MB/sec
8 K Element : 3102.89 MB/sec
16 K Element : 3110.96 MB/sec
32 K Element : 3109.41 MB/sec


BogoMIPS:
Calibrating delay loop..

Ok - 656.00 BogoMips



Dhrystone:
Dhrystone Benchmark, Version 2.1 (Language: C)
Program compiled without 'register' attribute

Execution starts, 50000000 runs through Dhrystone
Execution ends

Duration in seconds: 28.1
Microseconds for one run through Dhrystone: 0.6
Dhrystones per Second: 1778409.9
Dhrystone MIPS (DMIPS) 1012



Quicksort:
Elaborating quicksort of 1000 numbers repeated for 10 times
Unsorted array:

Total time taken by CPU: 2.44


Sieve:

Sieve of Eratosthenes (Scaled to 10 Iterations)
Version 1.2, 03 April 1992

Array Size Number Last Prime Linear RunTime MIPS
(Bytes) of Primes Time(sec) (Sec)
8191 1899 16381 0.000684 0.000684 2425.1
10000 2261 19997 0.000835 0.000879 2311.8
20000 4202 39989 0.001669 0.001758 2341.8
40000 7836 79999 0.003339 0.003515 2370.4
80000 14683 160001 0.006677 0.007813 2157.9
160000 27607 319993 0.013354 0.015624 2181.8
320000 52073 639997 0.026709 0.031252 2204.1
640000 98609 1279997 0.053418 0.056248 2473.5
1280000 187133 2559989 0.106836 0.125008 2246.8
2560000 356243 5119997 0.213671 0.250015 2267.0
5120000 679460 10239989 0.427343 0.499954 2286.8
10240000 1299068 20479999 0.854686 1.399994 1646.7
20480000 2488465 40960001 1.709372 4.400024 1056.1

Relative to 10 Iterations and the 8191 Array Size:
Average RunTime = 0.000865 (sec)
High MIPS = 2473.5
Low MIPS = 1056.1



Whetstone:

Please wait...

Loops: 50000 Iterations: 1 Duration: 9.6 seconds
C Converted Double Precision Whetstones: 523.2 MIPS


All tests done.

Now can I please get a 32 bit driver for AmigaOs4.1 so we can move on to the GPU benchmark ? Don't take it seriously it's just a joke...

Thanks again for the script and merging the CPU benchmarks.

I am somewhat pleasantly surprised that these results are so different.....es shows once again how strong this ARM Cpu is, but also shows its weaknesses in some areas.

---> VIDEOBUS <---
READ: 8767 MB/S.
WRITE: 10102 MB/sec.

That impressed me the most, how does that come about, maybe it's because the main memory as well as the garficard memory are used as shared memory.

With the benchmark you can imagine how well AmigaOs4.1 with Qemu runs on my machine. That is the point why I chose this emulation, it gives me a good feeling to be able to use AmigaOs4.1 under it. AmigaOs4.1 runs albeit somewhat limited as my 2nd operating system thanks to Qemu.

Numbers can be manipulated, with videos it becomes very difficult, if they would like I can also create a video about it again.


Edited by Maijestro on 2023/5/24 23:43:54
Edited by Maijestro on 2023/5/24 23:49:05
Edited by Maijestro on 2023/5/24 23:51:53
Edited by Maijestro on 2023/5/25 0:09:01
MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@white[quote]white wrote:this is the version of kas1e (1.0) E-UAE
works very well at 16bit with UAEGFX

From where did you get this version os4depot? I would like to play with it too.

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@whiteQuote:
white wrote:@Maijestro

here is the link should be the right version:

a little good will if you can send me the code for "fpu" so I compile it


Thank you my friend....also I have something for you. Run a few tests to confirm that it has improved in speed. I forgot how to install Twitch Tv under AmigaOs4.1 I need clear instructions please. aiostreams and phytonssl I already copied in utilities. How to continue ?

I have never been able to get TwitchTv to work under AmigaOs4.1.

https://www.mediafire.com/file/p5o4s0r ... qemuFPUOptimiert.zip/file

Please compile it like this and let me know if it works on your machine.

./configure --target-list=ppc-softmmu --disable-dbus-display --enable-slirp --enable-lto


Edited by Maijestro on 2023/5/24 22:39:27
MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@whiteQuote:
white wrote:I tried one of the E-UAE "betas" compiled by


@Maijestro
twitchTV is in the package I sent you, just select the Emotion player path and add the commands to the Odyssey menu.
Create an account with mediafire it's free and you have 10gb of space available it's easier to exchange files.


If you no longer have them let me know.


I have it stashed away somewhere and can't find it anymore :(

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@HansQuote:
Hans wrote:@Maijestro

Are there any easy CPU benchmarks that could be used to compare with real hardware? I'd be interested in how raw CPU performance compares to the Pegasos II (amongst others).

Hans


You could use this bench it contains several tools that directly access the cpu under the emulation and real hardware.

WhetDhryStone

Otherwise, perhaps this tool would be interesting and there are already some entries on Os4Depot of it.

sortbench

As @smarkusg mentioned, it currently runs really well on Mac with M1 chipset, apparently the ARM cpu is perfectly suited to handle the emulation. I have made a short video from the complete kernel boot process to the AmigaOs4.1 workbench.





And the Sortbench via SysMon, since it probably also directly accesses the CPU.

Resized Image

I would be interested in your benchmarks that you perform directly under the emulation to be able to determine the percentage difference between the CPUs.

I don't want to offend anyone here it's mainly about AmigaOs4.1 and not about the emulation, if you feel bothered by me just let me know and I'll stop.

AmigaOs4.1 gives me a lot of pleasure and what I tried to convey is that it can work well under certain circumstances and with the right hardware (even if limited).

Greetings


Edited by Maijestro on 2023/5/24 10:45:27
MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@HansQuote:
Hans wrote:@Majestro


My laptop isn't the newest, bit it is a Core i7 running at 2.6 GHz.


Not the latest hardware, but it should still be at least about as fast as a Pegasos.


Quote:

qemu-system-ppc -M pegasos2 -cpu 7447 -bios pegasos2.rom -vga none -device sm501 -drive media=disk,file=./hd.img,format=raw -device rtl8139,netdev=net0 -netdev user,id=net0 -rtc base=localtime -serial stdio


Under which system are you using Qemu since you have no window output assigned. Qemu supports:

-display sdl
-display gtk
-display cocoa (only available on MacOs)

You can also allocate more memory with:

-m 1024

The rest looks ok for now, as an example I use this start line:

-M pegasos2 -cpu 7457 -accel tcg -bios /Volumes/BackUP/PegasosQemuDatein/pegasos2.rom -vga none -device sm501 -drive if=none,id=cd -m 1024 -device ide-cd,drive=cd,bus=ide.1 -drive if=none,id=hd,file=/Users/reneengel/hd2SFS.img,format=raw -device ide-hd,drive=hd,bus=ide.0 -device rtl8139,netdev=network01 -netdev user,id=network01 -rtc base=localtime -display cocoa -serial stdio

It won't reach the nivou of your AmigaOne x5000, but the speed should still be noticeably better compared to WinUae and AmigaOs4.1 Classic under your hardware.

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: Was ist heute der schnellstmögliche x64-Emulationsweg von OS4?
Quite a regular
Quite a regular


@m3xQuote:
m3x wrote:@Hans

Quote:
I wasn't aware of that. So the SM502's blitter won't copy or use the alpha channel? That's a weird thing to do.

The chip uses a different 16-bit layer for alpha. Maybe these is a way to implemet some sort of alpha support compatible with graphic.library...

Anyway, I've a new driver version which, on real hardware (not emulated) greatly improve CPU and DMA trasfer speed.


Thanks for the valuable information, that explains a lot. Under the Qemu Pegasos 2 emulation we also tested MorphOs with the sm501 driver and there were 24 bit screens available, apparently this driver is supported a bit better there.

It confirms that the emulation of the sm501/2 works correctly and the limitations come from the guest system, in our case from the Graphic.library used by AmigaOs 4.1 which does not fully support this driver.

Your updated sm502 driver could also improve the AmigaOs4.1 Pegasos 2 emulation under certain circumstances.

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@HansQuote:
Hans wrote:@Maijestro
Following up on this, the problem is that the emulated hardware is an SM501, which is limited to 16-bit colour output. We're lucky that the SM502 driver can handle the SM501, or it wouldn't work at all. We could get 32-bit if the SM502 were emulated instead.


This is of course very interesting and I was wondering why everyone talks about "sm502" but qemu uses the line "sm501". Since this driver already works, maybe we could add the missing part of the 32 bit output. sm501/2 should be very similar and the adjustments would certainly be done with little effort. Is there any documentation for this chipset?

You can find the written driver under:
"Qemu/hw/display/sm501.c"
Should you want to have a look at it.

Quote:
there any settings that you guys use for better performance? Or have things improved in the latest betas? I'm using the latest stable release (8.0.0.0).


Normally, Qemu 8 Final should work very well. Of course, the decisive factor is your hardware, the faster the better.

I'm currently using a Qemu 8.0 custom build where a ppc-hardfloat-fpu patch is included which makes the FPU emulation even faster. I could provide the build with the patches, but it has to be compiled by yourself.

Zoltan BALATON has also submitted a new "bitops" patch that will increase the FPU emulation, with luck this change will be available in Qemu 8.1.

On which hardware do you use Qemu?

I don't even dare to ask since you are developing under AmigaOs4.1, you have set up the installation under SFS?

Maybe you could also post your startup line of Qemu just so we can match it. Probably it is due to your hardware being a bit too weak.

@white is running Qemu on a Ryzen 5800x
@smarkusg uses a MacMini M1 for it

My hardware is below in the signature

lg Rene


Edited by Maijestro on 2023/5/23 10:23:37
Edited by Maijestro on 2023/5/23 11:24:52
MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@MaijestroQuote:
Maijestro wrote:@whiteQuote:
white wrote:here I made a test using only the -cpu G3
for me it is a new very fast emulation.

I have not yet "assembled" the whole OS 4.1 system to use it definitively.

But here I did some tests with Scumm Grim Fandango etc.
Internet some TwitchTV music and other things with E-UAE

But I'm very happy it's really nice for me to see that 4.1 is usable now.

I plan to dedicate an SSD partition to it now that sfs works.

https://youtu.be/T4jRjC_4iO4


Your workbench looks a bit chaotic

Thanks for the video it still clearly shows how fast the whole thing runs. And don't worry about the current problems that are still there, many things have already been improved and there will be some more.

As already mentioned I use Qemu under MacOs and here there is no pulseaudio or so but coreaudio, but I will also do some tests if I can reproduce the errors under my system.

Could you explain me again how you set up twitch tv under AmigaOs4.1 ?


When I watched your video I was surprised that you could watch YouTube in a pretty big window and smoothly.

I don't know what I changed, but it works just as well on my machine. Before I saw your video, I had always kept the window content quite small, which is not necessary. Thanks again for your video.

Here again the comparison:




MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top


Re: What the fastest possible x64 emulation way of OS4 today ?
Quite a regular
Quite a regular


@smarkusgQuote:
smarkusg wrote:@Maijestro
In the video there is a compilation with "khval" without SDL only with AmiGFX. It is with "JIT"

Here is the thread: https://www.amigans.net/modules/newbb/viewtopic.php?topic_id=8397

Amiga OS 3.2.x takes a long time to boot. On a real classic Amiga it is the same.

The speed is like on a bare A4000, so you can say it's a real hardware emulation

I won't share the files of this compilation, because it's a bit buggy

The e-uae project I think "khval" has been terminated as I wrote and I regret it terribly.


You could ask here if you can get help if you have already compiled it and it already works even if it has bugs, there are also many nice AmigaOs developers here.

I was also helped with MilckyTracker, SDL2, ScummVM we are still AmigaOs4.1 users even if it runs over an emulation.

MacStudio ARM M1 Max Qemu//Pegasos2 AmigaOs4.1 FE
Go to top



TopTop
« 1 ... 36 37 38 (39) 40 41 42 ... 45 »




Powered by XOOPS 2.0 © 2001-2023 The XOOPS Project