log in | register | forums
Show:
Go:
Forums
Username:

Password:

User accounts
Register new account
Forgot password
Forum stats
List of members
Search the forums

Advanced search
Recent discussions
- WROCC Newsletter Volume 41:11 reviewed (News:)
- WROCC March 2024 meeting o... Hughes and Peter Richmond (News:1)
- Rougol March 2024 meeting on monday with Bernard Boase (News:)
- Drag'n'Drop 13i2 edition reviewed (News:)
- South-West Show 2024 talks (News:4)
- February 2024 News Summary (News:1)
- Next developer fireside chat (News:)
- DDE31d released (News:)
- South-West Show 2024 Report (News:)
- South-West Show 2024 in pictures (News:)
Related articles
- Native versus emulation in 2016 (Part 2)
- Native versus emulation for running RISC OS in 2017 (Part 1)
- What are your RISC OS new years resolutions???
- RISC OS 'Advent' Calendar 2023 - Andre Timmermans
- RISC OS 'Advent' Calendar 2023 - ROOL
- RISC OS 'Advent' Calendar 2023 - Gavin Crawley
- RISC OS 'Advent' Calendar 2023 - Peter Howkins
- RISC OS 'Advent' Calendar 2023 - Amcog Games
- RISC OS 'Advent' Calendar 2023 - Chris Hall
- RISC OS 'Advent' Calendar 2023 - Michael Grunditz
Latest postings RSS Feeds
RSS 2.0 | 1.0 | 0.9
Atom 0.3
Misc RDF | CDF
 
View on Mastodon
@www.iconbar.com@rss-parrot.net
Site Search
 
Article archives
The Icon Bar: News and features: Native versus emulation in 2016 (Part 3)
 

Native versus emulation in 2016 (Part 3)

Posted by Mark Stephens on 11:39, 24/12/2016 | ,
 
In Part2 of our speed comparison, I wondered whether there would be a signficant change to the figures from Emulation if we tried a different processor or screen resolution. So in Part 3, let us see...
 
1680 x 1050 in 32M, 32K and 256 colours for test 4
Processor - Looped instructions (cache)
489562 275% 480160 269% 502375 282%
Memory - Multiple register transfer
8569 5289% 8349 5153% 8828 5449%
Rectangle Copy - Graphics acceleration test
2842 1174% 5033 2079% 8751 3616%
Icon Plotting - 16 colour sprite with mask
23098 1154% 19288 964% 23032 1151%
Draw Path - Stroke narrow line
4950 317% 5209 333% 5309 340%
Draw Fill - Plot filled shape
5533 379% 6111 418% 6814 467%
HD Read - Block load 8MB file
586290 19660% 616427 20671% 618415 20738%
HD Write - Block save 8MB file
554164 18223% 502875 16536% 535318 17603%
FS Read - Byte stream file in
2613 1262% 2678 1293% 2681 1295%
FS Write - Byte stream file out
1188 618% 1190 619% 1190 619%
 
It looks like Retangle Copy is significantly faster in 32K mode compared to 16M but otherwise we see little advantage on these tests (remember we get slightly different results every time we run the tests so we should not be concerned at small differences).
 
710 ARM versus StrongArm Processor emulation
Processor - Looped instructions (cache)
501300 281% 498030 279%
Memory - Multiple register transfer
8916 5503% 8723 5384%
Rectangle Copy - Graphics acceleration test
2776 1147% 2726 1126%
Icon Plotting - 16 colour sprite with mask
23293 1164% 24660 1233%
Draw Path - Stroke narrow line
5196 333% 4969 318%
Draw Fill - Plot filled shape
5633 386% 5684 389%
HD Read - Block load 8MB file
583984 19583% 583984 19583%
HD Write - Block save 8MB file
510986 16803% 546133 17958%
FS Read - Byte stream file in
2687 1298% 2643 1276%
FS Write - Byte stream file out
1165 606% 1187 618%
 
So it looks like if your usage is similar to that measured in these tests, there is not a significant difference running on MacPro. As we suggested last time, this is a valid test but it may not be a fair comparison for your usage. And it only looks at raw speed not other factors which may be important to you such as power usage (Titanium easily wins), portability (you will want a laptop and should be comparing PiTop versus Mac) or ability to run macOS, Linux, Windows (MacPro is only contender).
 
There are other settings in the VirtualAcorn configuration file (VA.cfg) which may also be worth experimenting with. So what is your personal experience? And what settings are you tweaking for maximum performance on your Mac or Windows box?
 
Log in to comment on this article

The Icon Bar: News and features: Native versus emulation in 2016 (Part 3)