[Patch PR 44576]: imprivement in compute_miss_rate for prefetching loop arrays

[Fang, Changpeng]

Hi,

Attached is the patch that partially fixes bug 44576:  testsuite/gfortran.dg/zero_sized_1.f90 with huge compile 
time on prefetching + peeling.

This patch avoid useless computation of miss rate because, if delta (address diference) is greater than or equal to
cache line size, The two references will never hit the same cache size and thus all misses.

This patch reduces the compile time of the test case from 5m30'' to 1m20'' on an amd-linux64 system.
Note that without -fprefetching-loop-arrays, the compile time on the same system is 30'', and I am still
working on reducing the complexity of reuse analysis and miss rate computation.

The patch passed Bootstrapping and regression tests.

Is this patch OK to commit?

Thanks,

Changpeng
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0004-pr-44576-miss-rate-computation-improvement-for-prefe.patch
Type: text/x-patch
Size: 1136 bytes
Desc: 0004-pr-44576-miss-rate-computation-improvement-for-prefe.patch
URL: <http://gcc.gnu.org/pipermail/gcc-patches/attachments/20100629/d3fe01cb/attachment.bin>