86Box: Why Not Pentium III?
86box.net
86Box: Why Not Pentium III?
1–10 of 102 posts
Re: 86Box: Why Not Pentium III?
#2Sorry but not getting to point of cycle-accurate emulation of recent x86 CPUs. What could possibly benefit ? The performance is going to be a disaster compared to say qemu....
Re: 86Box: Why Not Pentium III?
#3Article claims it’s not possible to emulate a Pentium III at full speed on an Apple M1, and so there’s no point to a fork attempting this feat. But isn’t that exactly what Rosetta 2 does?
Re: 86Box: Why Not Pentium III?
#4Article claims it’s not possible to emulate a Pentium III at full speed on an Apple M1, and so there’s no point to a fork attempting this feat. But isn’t that exactly what Rosetta 2 does?
Rosetta 2 is not cycle accurate to a Pentium III.
That's AIUI what box86 targets on the CPUs it supports emulating.
Re: 86Box: Why Not Pentium III?
#5Something alluded to, but not really elaborated on, is what the motivation is for emulating progressively newer CPUs, versus virtualizing them.
With old hardware, the sort I imagine 86Box is mainly used to emulate (it's how I use it, anyway), old OSes rely on specific behavior of old systems and peripherals that can't be easily virtualized through KVM + QEMU or the like. A mixture of processors being too fast and behaving subtly different, possibly due to differences in "undefined behavior".
I doubt there's a binary cutoff point where it's obviously more useful to virtualize or emulate, but it's obvious that emulating an 80386 is ideal, and virtualizing a "Core 2 Duo" is ideal, for running software from those respective periods. Is the Pentium III desirable to emulate, and simply not computationally feasible, or is this just people wanting to make cool things for cool things' sakes? Or a little of both?
Re: 86Box: Why Not Pentium III?
#6Something alluded to, but not really elaborated on, is what the motivation is for emulating progressively newer CPUs, versus virtualizing them. With old hardware, the sort I imagine 86Box is mainly used to emulate (it's how I use it, anyway), old OSes rely on specific behavior of old systems and peripherals that can't be easily virtualized through KVM + QEMU or the like. A mixture of processors being too fast and beh…
> old OSes rely on specific behavior of old systems and peripherals that can't be easily virtualized through KVM + QEMU or the like
This sounds interesting. Do you have examples of these behaviors where something is faulty using standard virtualization versus hardware-level emulation? (I know clock speed can make a difference.)
Re: 86Box: Why Not Pentium III?
#7Something alluded to, but not really elaborated on, is what the motivation is for emulating progressively newer CPUs, versus virtualizing them. With old hardware, the sort I imagine 86Box is mainly used to emulate (it's how I use it, anyway), old OSes rely on specific behavior of old systems and peripherals that can't be easily virtualized through KVM + QEMU or the like. A mixture of processors being too fast and beh…
> old OSes rely on specific behavior of old systems and peripherals that can't be easily virtualized through KVM + QEMU or the like This sounds interesting. Do you have examples of these behaviors where something is faulty using standard virtualization versus hardware-level emulation? (I know clock speed can make a difference.)
AMD has relaxed a bit coherency behavior after page table manipulation leading to Windows 9x crashes:
https://blog.stuffedcow.net/2015/08/win9x-tlb-invalidation-b...
These crashes are not related to clock speed. While Windows 9x already cannot run on these CPU due to clock speed, the clock speed issues have mostly been patched in 9x.
Re: 86Box: Why Not Pentium III?
#8Sorry but not getting to point of cycle-accurate emulation of recent x86 CPUs. What could possibly benefit ? The performance is going to be a disaster compared to say qemu....
The point of cycle-accurate emulation is to emulate something with accuracy down the the cycle, so that software that relies on some particularity will work on it.
Performance is secondary, you can think of the emulation as a lasting documentation, which in time comes usable due to improvements of hardware and software, or can be used as a reference for FPGA, ASIC or alternative implementations.
Re: 86Box: Why Not Pentium III?
#9Sorry but not getting to point of cycle-accurate emulation of recent x86 CPUs. What could possibly benefit ? The performance is going to be a disaster compared to say qemu....
The point of cycle-accurate emulation is to emulate something with accuracy down the the cycle, so that software that relies on some particularity will work on it. Performance is secondary, you can think of the emulation as a lasting documentation, which in time comes usable due to improvements of hardware and software, or can be used as a reference for FPGA, ASIC or alternative implementations.
The question is which software that requires a Pentium III also requires some CPU timing peculiarity. There have been enough CPU vendors that such software would have been difficult to run even at its era.
This is not a videogame console where all hardware was the same, or the early PC world were everything was designed for the Intel 8086 timings as on the IBM PC. This is the modern PC world. Which exact CPU model would you even choose to emulate ?
Re: 86Box: Why Not Pentium III?
#10Arguably, cycle-accurate emulation should be done with FPGA support anyway. The Pentium III is old enough that there should be no legal obstacle to implementing new compatible hardware.