Re: "Double Precison" Keywords?



"glen herrmannsfeldt" <gah@xxxxxxxxxxxxxxxx> wrote in message news:ihlad0$tt4$1@xxxxxxxxxxxxxxxxxxxxxxxxxxxxx
| robin <robin51@xxxxxxxxxxxxxxxxxx> wrote:
| (snip, I wrote)
|
| > | IBM S/370 and successors support 128 bit (extended precision)
| > | in hardware.
|
| > but not division in the case of S/370.
|
| IBM did a cost/benefit study, and found that DXR was used rarely
| enough

The DXR instruction didn't exist, so they couldn't have found
that it was used rarely.
More likely., they probably were pushed for time, and didn't
develop the microcode in time for the 370.

And BTW, one could make that argument for almost any instruction,
and implement it by software, including such things as
ED, EDMK, TR, TRT, and so on, or even D, DR.

| that a software implementation was the best choice.
|
| The did reserve the opcode for it, such that when it was
| implemented in ESA/390, programs would be ready for it.
|
| > | The VAX architecture includes it, but allows for
| > | software emulation by the OS to support it. VAX compilers, then,
| > | assume that the hardware supports it, whether or not it does.
|
| > | Other than IBM, is there other hardware currently, or recently,
| > | in production with REAL*16 support?
|
| > REAL*16 is a non-standard.
|
| It is supported by the IBM and VAX compilers, though.

It's still non-standard, and always has been.


.