Re: Optimizing Assembler Code

"Frank" <spamtrap@xxxxxxxxxx> wrote in message news:2b818a2b-66df-4bdf-af6b-19a87b7c8a13@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
On 14 Jun., 15:02, Frank <spamt...@xxxxxxxxxx> wrote:
The problem is that when you have to access a variable you are
stalling
the instruction fetch pipeline and the speculative execution of modern
CPU's.
If you have a case which is mapped to binary search jumps (and only
larger
switcher with dense labels are mapped into jump tables) then all this
modern
features are working well.


What does this mean: "you are stalling the fetch pipeline"?
(snipped)

please correct if wrong:
If it isn't in a register and isn't in the store-forwarding queue thing anymore, then it'll have to come from cache, or even RAM (but that's very extreme) which takes (a lot of) time - therefore, the ROB could fill up (if the dependacy chain is that long) preventing new instructions from entering it
Seems like a rather rare situation to me..

.