Appeal No. 2001-2610
Application No. 09/052,247
prefetching a next sequential instruction if the instruction is
not an instruction-path changing instruction.”
Moreover, it is our view that the examiner’s rationale for
the rejection of claim 1 is flawed because the examiner states
[answer-page 4] that “if the instruction is not path-changing,
then prefetching a next sequential instruction by
[Mahalingaiah’s] teaching in column 8, lines 65-67 of the branch
direction being “taken”, in which subsequent...instructions are
fetched from the target address of the branch instruction,
wherein the target address of a branch instruction is known to be
beyond the next sequential address” [emphasis ours]. We find no
rational basis for the statement that the target address of a
branch instruction “is known” to be beyond the next sequential
address. We agree with appellants that it is possible that a
target address of a branch instruction may be beyond the next
sequential address but the mere fact that a certain thing may
result from a given set of circumstances is not sufficient to
show that the reference describes the limitation in claim 1
directed to instruction-path-changing instructions [reply brief-
pages 4-5]. The claim does not merely state that a target
address branches beyond a next sequential address. It requires
that an “instruction-path-changing instruction,” (i.e., an
-7–
Page: Previous 1 2 3 4 5 6 7 8 9 10 Next
Last modified: November 3, 2007