Efficient cache and BLOB's - profiling cache hits/misses

Question

For a program to be cache efficient the data used should be stored linearly right?

So instead of dynamic allocation I put my data in a blob using a linear allocator. Is this enought to improve performace? what should I do to improve cache efficiency even more?

I know that this questions arent specific but I don't know how to explain it...

Which programs can help me profile cache hits/misses?

what is enough/useful/needed for performance improvement, should be decided by profiling, not by pure guess. if there were a universally applicable recipe, it would have been already implemented in the runtime library. — Vlad, Aug 21 '11 at 11:51
Just added another question... Do you know any profiler to detect cache hits/misses so I can see if any changes I do are improving performance? — Tiago Costa, Aug 21 '11 at 11:55

Necrolis · Accepted Answer · 2011-08-21T13:43:58.283

If your looking for a profiler for windows, you can try AMD's CodeAnalyst or VerySleepy, both of these are free, AMDs is the more powerful of the two however( and works on intel hardware, but iirc you can't use the hardware based profiling stuff), it includes monitoring of things like branch prediction misses and cache utilization. Profiling is great, as it tells you what to optimize, but you don't always know how, for that, you should have a look at Agner Fog's optimization manuals combined with Intel's optimization manual (which contains a lot on locality and cachability optimizations)

score 3 · Answer 2 · edited May 23 '17 at 11:56

3

If you're on Linux you could use Valgrind(specifically cachegrind tool).

If you're on Windows then VS2010(2008) Professional edition has a builtin profiler but I don't know any details about it's cache profiling facilities. There is also the Intel VTune Analyzer(Amplifier). Both of them are commercial products, although I think you can get 30 days evaluation copies.

Some other questions on SO that might be of help:

edited May 23 '17 at 11:56

Community

1
1

answered Aug 21 '11 at 11:58

celavek

5,575
6
41
69

Looks good but I use Windows... Is there any Windows subsitute for Valgrind? – Tiago Costa Aug 21 '11 at 12:00

score 0 · Answer 3 · answered Aug 26 '17 at 21:05

0

On Linux, you can use perf mem to sample memory accesses, including misses in a very fine-grained manner (including the miss address), as described here.

answered Aug 26 '17 at 21:05

BeeOnRope

60,350
16
207
386

Efficient cache and BLOB's - profiling cache hits/misses

3 Answers3