try software emulator the ARM first, I dare you, I double dare you
Eh, if you know who I am (congratulations, I have had the same nick for 30 years) then you already know that I do regular rebuilds of Amibian, both for ARM native and JS (presently doing a WASM port). Emulation is not an issue. The whole point here was that if we have this kick-ass FPGA to play with, why not make that as awesome as possible. So dare accepted and date pushed back by a few years, because building for ARM is pretty common.
most people "demanding" faster CPU claim they cannot do it themselves because they are "software people", so again I challenge you to try software 68k emulation on the ARM!
Again, done and dusted. And utterly beside the point. I even made a custom intermediate assembler that implements support for variables (stack mapped) and Rust like memory handling. The same bytecodes can be post processed and emitted to multiple processors and high-level languages (see link below).
http://quartexhq.myasustor.com/amibian01.jpg
Sorgelig doesn’t care that much about Amiga aside from playing games, so don’t expect much
That is sad to hear, but if he would be interested in a patreon project for doing a new Amiga core, or refactoring the existing Mist core, then im fairly confident the Amiga community would be interested. Presentation is everything, and the Amiga community is very supportive of such projects. Who knows, he might change his mind, it doesn't hurt to ask.
if you want faster CPU core, you most likely must do it yourselves.
Perhaps. But there are plenty of options out there. You can soon pick up the Buffee which chews 68k opcodes at insane 3.2 GHz, where a relatively humble ARM CPU has been tailored to purely act as a CPU (
https://amitopia.com/new-buffee-amiga-a ... 1000-mips/). With the groundwork done, there is nothing stopping Rene' from stuffing a high-end ARM cpu in the next model, something like a SnapDragon 880 series CPU delivers Intel i5 performance. So as always the community have found solutions for the particular problem of speed.
The question really is, wouldn't this be much better to move to FPGA?
If you take the Buffee work that Rene has done, then look at the architecture of the Mister, you cant help thinking that it has a massive advantage over the Vampire. The CPU can be moved to the ARM side. Memory sharing is already solved, and FPGA space can be reserved for the chipset. In such an approach you can free up the gate-blocks allocated for the cpu. This could be refactored as chipset advancements.
that exlains all the revisionism regarding "the vampire situation" and all the rest
In what possible way is cheering on the Mister synonymous with being a Vampire V4 fan? I'm actually quite unbiased on the subject. It became a "thing" because the group I run on FB was created purely for emulation and FPGA, yet some members were utterly incapable of following the rules. The point of the group was to have a space where people could calmly debate emulation, various SBCs, FPGA and next-gen Amiga machines without being hounded by some of the people that, at the time, were ripping through the Commodore Amiga group.
At the moment we have several standards fighting over who is the next best Amiga. You have PPC/OS4, Aros, Vampire, classics, Morphos -- and they are all running with their own ideas, different hardware, different software.
If the Mister could tap in to say the 080/AMMX functionality, it would make life much easier for software developers. Having to cross compile to the extent we do now is pretty tedious, and with the massive differences in speed, hardware capabilities etc. -- new software gravitate towards the lowest end of the spectrum. This could be solved more elegantly by pushing the low-end standard to something akin of a PS2.
But do feel free to elaborate.
Not even Zorro III was interesting *at the time* compared to open alternatives, certainly not now.
