Appeal No. 96-2446
Application 08/246,179
control signals CTRL0 and CTRL1 which select the flag group do not select "in
accordance with an indication in a conditional branch instruction" and are not "decoded by
said instruction decoding unit" as required by the language of claim 1. Woods does not
disclose that the instruction decoding unit produces control signals as required by the
language of claim 1. The examiner states "Woods teaches the simultaneous production of
a plurality of flag groups based on data width, and IBM teaches the saving of a plurality of
flag groups. The selection of a flag group in IBM is deferred until a conditional branch
instruction. These two references together sufficiently teach the Appellant[s'] invention."
(See answer at page 7, paragraph 1.) We disagree. As discussed above, Woods does
not disclose the storage of flag groups in plural storage means.
The Examiner argues "[r]egarding multiple data widths, the Examiner asserts that
Woods and Yamahata, not IBM were relied upon to teach multiple data widths." (See
answer at page 7, paragraph 3.) We note that the discussion in the answer with
respect to Yamahata is limited to "Yamahata discloses a system with varying bit widths
that explicitly teaches an instruction decoder." The Examiner has not provided a convincing
line of reasoning why it would have been obvious to one of ordinary skill in
the art at the time of the invention to incorporate the teachings of Yamahata with those of
Woods and IBM. It is unclear how Yamahata is to be combined with the teachings of
6
Page: Previous 1 2 3 4 5 6 7 8 9 10 11 12 Next
Last modified: November 3, 2007