[v3] conditional tweak

Gabriel Dos Reis gdr@integrable-solutions.net
Fri Nov 7 22:33:00 GMT 2003


Martin Sebor <sebor@roguewave.com> writes:

| Gabriel Dos Reis wrote:
| 
| ...
| > | While I haven't measured Jerry's particular patch, on machines with deep
| > | pipelines, an incorrectly-predicted branch can be a significant stall
| > | (most/all of the pipeline has to be cleared).
| > In theory, yes.  In this particular case, we're speaking of an I/O
| > formatting flag setting which is nowhere a bottleneck (expect probably
| > in a testsuite).
| 
| This conditional actually does happen to have a significant impact
| on performance -- fill() is called every time a number is inserted
| into a stream, for example.

compared to the actual work for formatting?

| Incidentally, I recently profiled the effect of the HP aCC $pragma
| ESTIMATED_FREQUENCY (the rough equivalent of gcc's __builtin_expect)
| on IPF (i.e., IA64). IIRC, the improvement was between 5 and 10% for
| a small block of code.

I have no idea of how HP aCC $pragma works.  Can you display the actual
work or is it covered by proprietary rules?

-- Gaby



More information about the Libstdc++ mailing list