On 6 May 2015 at 10:20, Tom Marchant
<[email protected]> wrote:
> In fact, I could imagine a CPU that would
> recognize a cache miss, initiate the fetch from memory and halt the
> instruction. In that case, the "CPU-determined" number of bytes would
> not necessarily be a fixed number.

This is explicitly recognized in the PoO. "The amount of processing
that results in the setting of condition code 3 is determined by the
CPU on the basis of improving system performance, and it may be a
different amount each time the instruction is executed."  But of
course certain instructions guarantee a minimum amount of processing.

Also of note: "Completion with the setting of condition code 3 permits
interruptions to occur. Depending on the model and the instruction,
condition code 3 may or may not be set when there is not a need for an
interruption."

Tony H.

Reply via email to