TRT[E] is not the same as TR. It *stops* if the "translated-to" byte is non-zero.
It's hard to say whether a TR loop or just an "open code" loop would be better on the current in-use crop of hardware. If CPU performance is extremely important, I'd do some experimenting. Even if the z10 offered a "Translate Extended" instruction, the OP couldn't count on it being there on every Customer's machine for quite a while. It sounded like the data had to be moved in addition to translated, so an "open code" solution might handle both the move and the translate (one byte at a time). --Art C. At 02:22 PM 3/24/2008, john gilmore wrote: >Look at the TRTE, TRanslate and Test Extended, instruction on pp. 7-231ff of >the current PROP. > >"Looping" is still required when a condition-code value of 3 is set, but only >a branch back to the same, already executed TRTE is required to accomplish it. > In particular, there is no requirement for a running count of the number of >bytes that remain to be translated. ================================================== Art Celestini Celestini Development Services Phone: 201-670-1674 Wyckoff, NJ ============= http://celestini.com ============= Mail sent to the "From" address used in this post will be rejected by our server. Please send off- list email to: ibmmain<at-sign>celestini<dot>com. ================================================== ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
