You're right. That instruction only does anything on the original 8087, and isn't even documented by later processor manuals, when the inline assembler was written <g>. I'll see about adding it. In the meantime, you can get by with:

db 0xDB, 0xE1

"KarL" <someone@somewhere.org> wrote in message news:b979vu$1nkh$1@digitaldaemon.com...

Pinched the following code from somewhere:

#include <dos.h>
//
//      Save FPU state.
//
//      This uses a magic spell taken from Intel application note AP-113.
//
void fpusave (char far* t)
{
    //_ES = FP_SEG (t);
    //_BX = FP_OFF (t);
    __asm les bx,t
    __asm  fnstcw  es:[bx]     // save IEM bit status
    __asm  nop                 // delay while control word saved
    __asm  fndisi              // disable BUSY signal
    __asm  mov     ax, es:[bx] // get original control word in AX
    __asm  fsave   es:[bx]     // save FPU state
    __asm  fwait               // wait for save to complete
    __asm  mov     es:[bx],ax  // put original control word in saved state
}

//
//      Restore FPU state.
//
void fpurest (char far* t)
{
    //_ES = FP_SEG (t);
    //_BX = FP_OFF (t);
    __asm les bx,t
    __asm frstor es:[bx]
}

Found the compiler cannot recognise fndisi instruction. Compiles with MS VC++ 1.5 and above and BCC as well.

When Obj2asmed the code generated by BC or VC,

fndisi (db e1)

is being intepreted as

fdisi (9b db e1)

Don't ask me what they mean as I haven't read into the Intel data book yet...