Cloanto's plans mentioned in Business Week OnLine

[Hammer]

Michele Battilana's Cloanto was mentioned in mainstream Business Week OnLine on February 26, 2004. It made reference for releasing a 'new' 64-bit software for the new Microsoft OS (i.e. "Windows XP 64-Bit Edition for 64-Bit Extended Systems").


Business Week Online Article

[Hammer]

16 bit systems could address more than 1 MB of ram

Note that a true "16bit" processor (16bit address space) can only access 2^16 worth memory i.e. MC68000 is hybrid processor.

why would corperations/hospitals need or have to upgrade their hw.

For lowering the cost of HW which runs large MIS/Relational Database systems that exceeds 2^32(~4GB) memory i.e. 8GB of memory. AMD64 brings the 64bit processor market closer to the commodity X86-32 market.

[Hammer]

@SHADES

In relation to Intel's 8080, it has seven 8bit registers which can combine to form three 16bit registers (recalling).

Intel 8086 has four 16bit general registers but can be treated as eight 8bit general registers. The memory model in this CPU is defined in some circles as "brain damaged".

Note that; there is the PAE segmentation memory model in +P6 generation processors i.e. X86-32 can physically address up to 2^36bit of memory(via PAE) but it is divided into 2^32 segmented pages(recalling). Using this PAE extended mode can slow down the overall performance, thus the need for AMD64.

[Hammer]

That's an 8 bit CPU with access to 1MB of memory

Intel 8088 was a 16bit CPU with 8bit wide i/o data bus i.e. like MC68008. The "bit’ness" usually refers to how the CPU treats its internal data sets.

[Hammer]

So if we go by your train of thought, being the internal path/width of memory addressing, the 8088 is actually a 20 bit CPU Providing we are still talking in bits of information that can be accessed here

Note that it’s pointers(important for the "bit'ness") wouldn’t be at 20bits.

[Hammer]

>8088 is actually a 20 bit CPU

It’s more complex than that. To specify an
address you use a 16 bit base register and a 16 bit offset to form a 20 bit physical address (recalling the hack). Notice the use of two 16bit instructions. To access more than 64KB of memory, this hack must be use i.e. some commentaries associated this to "brain damage".

To compound the memory restrictions; the original IBM PC can be expanded to 256K (i.e. maximum memory using IBM parts at that time(1)).

Usually, "Bit’ness" refers to GPRs and Pointers.(simplifying). Note that the current X86-32 can ready handle 64bit data sets(e.g. 3DNow, SSE, AMD32's EV6 FSB, internal data path).

Reference
1. http://en.wikipedia.org/wiki/IBM_PC

[Hammer]

In relation article’s 16bit comments, they could be referring to systems at that time i.e. using IBM's parts for memory expansions. The market proportion at that time between 86/286/386  would an issue. "16bit" label has been played loosely in reference to particular systems. The article’s "typical desktop PC" seems to be pointing to i8086/8088/NECV3x based systems at that time.

Back at that time, there are some crazy X86 PC prices(1)(2)(3). As prices may indicate; the “typical desktop PC” may tend to be the cheaper solution.

PS; I’m well aware of 8086 bit-shift i.e. I'm just lethargic in typing the whole text. There known caveat with 8086's 'brain dead' memory model i.e. referring to the same physical memory location via two different base segment:off_sets values.

Reference;
1. http://www.can.ibm.com/helpware/8595.html
2. http://www.can.ibm.com/helpware/8555.html
3. http://www.can.ibm.com/helpware/8525.html