Lines Matching refs:word
289 # Since the divisor is only a word (and larger than the mslw of the dividend),
292 # dividing the divisor word into each dividend word. In this case,
296 # the last two divisions to get a quotient longword and word remainder:
305 mov.w %d5, %d1 # first quotient word
320 # In this algorithm, the divisor is treated as a 2 digit (word) number
321 # which is divided into a 3 digit (word) dividend to get one quotient
322 # digit (word). After subtraction, the dividend is shifted and the
331 btst &31, %d7 # must we normalize? first word of
348 mov.w &0xffff, %d1 # use max trial quotient word
362 clr.w %d6 # word u3 left
375 mov.w %d6,%d4 # insert lower word (U3)
377 tst.w %d0 # is upper word set?
387 # now test the word by multiplying it by the divisor (V1V2) and comparing
388 # the 3 digit (word) result with the current dividend words
408 clr.w %d3 # %d3 now ls word of divisor
409 add.l %d3, %d6 # aligned with 3rd word of dividend
412 clr.w %d3 # %d3 now ms word of divisor
413 swap %d3 # aligned with 2nd word of dividend
429 # add 2nd word to quotient, get the remainder.
431 # shift down one word/digit to renormalize remainder.
778 # longword size whether the operation is byte, word, or long. The #
884 # sign extend word to long so we can do simple longword compares.
885 ext.l %d2 # sign extend data word