I finally read this thread.
I have written many award winning scsi drivers, as well as designed SCSI host bus adapters (HBA) for the macintosh. In fact I an a main author of what was used by 18 different companies such as Club Mac and APS and Atto and many more (Apollyonics SCSI Director allowed rebranding), and I wrote every line of cd products such as FWB's CD-Rom Toolkit 1 and v2. I also rewrote the USB Mass storage class for OS9, and did a dual port dual 2 gigabit FibreChannel card for OS9. I've done RAID, SATA, ATAPI, Ultra DMA, firewire, and done many many more than those things for I/O hardware. I own the copyright in many cases, and could leverage code if needed to such a ide/sata I/O product.
Adding a SCSI Manager 4.3 "XPT layer" (for ancient machines) is not impossible or hard. FWB did it (loaded a clone of a fake SCSI Manager 4.3 on non 4.3 compatible macs). So many macs allow SCSI Manager 4.3, except for a couple powerc laptops, with system 7.5, that such a "dream nubus card" would not be too restrictive if limited to machines that run 7.5 and had a standard NCR 53C96 SCSI controller chip.
But running ide drives on old mac hardware, whether Nubus or PDS is not what I care about in this dream peripheral thread ...
All I want is someone to figure out how to add a real genuine existing Motorola 333 MHz 68060 chip (V5 core) into a 840AV or other AV. With dual execution pipelines and a larger branch cache, this next-generation core provides a 2x performance increase compared to a 220 MHz MCF5407 device, a V4-based standard product
The chip was announced at Oct. 19, 2002 many years ago !
Because of issues of incompatibility with 68060 though, even though there are royalty-free and price-free software library tricks to make it work, a 68040 emulator is needed, and that is how Amiga people get the 220 MHz MCF5407 device to run their 68030 code.
here are raw diffs, without software exception handling :
http://www.microapl.co.uk/Porting/ColdFire/cf_68k_diffs.html
Think of the chip as a 610 Mhz chip conceptually though, not a 333, because of its internal design. It gets 610 MIPs in benchmarks.
I have written many award winning scsi drivers, as well as designed SCSI host bus adapters (HBA) for the macintosh. In fact I an a main author of what was used by 18 different companies such as Club Mac and APS and Atto and many more (Apollyonics SCSI Director allowed rebranding), and I wrote every line of cd products such as FWB's CD-Rom Toolkit 1 and v2. I also rewrote the USB Mass storage class for OS9, and did a dual port dual 2 gigabit FibreChannel card for OS9. I've done RAID, SATA, ATAPI, Ultra DMA, firewire, and done many many more than those things for I/O hardware. I own the copyright in many cases, and could leverage code if needed to such a ide/sata I/O product.
Adding a SCSI Manager 4.3 "XPT layer" (for ancient machines) is not impossible or hard. FWB did it (loaded a clone of a fake SCSI Manager 4.3 on non 4.3 compatible macs). So many macs allow SCSI Manager 4.3, except for a couple powerc laptops, with system 7.5, that such a "dream nubus card" would not be too restrictive if limited to machines that run 7.5 and had a standard NCR 53C96 SCSI controller chip.
But running ide drives on old mac hardware, whether Nubus or PDS is not what I care about in this dream peripheral thread ...
All I want is someone to figure out how to add a real genuine existing Motorola 333 MHz 68060 chip (V5 core) into a 840AV or other AV. With dual execution pipelines and a larger branch cache, this next-generation core provides a 2x performance increase compared to a 220 MHz MCF5407 device, a V4-based standard product
The chip was announced at Oct. 19, 2002 many years ago !
Because of issues of incompatibility with 68060 though, even though there are royalty-free and price-free software library tricks to make it work, a 68040 emulator is needed, and that is how Amiga people get the 220 MHz MCF5407 device to run their 68030 code.
here are raw diffs, without software exception handling :
http://www.microapl.co.uk/Porting/ColdFire/cf_68k_diffs.html
Think of the chip as a 610 Mhz chip conceptually though, not a 333, because of its internal design. It gets 610 MIPs in benchmarks.