On Thu, Sep 22, 2016 at 12:10 PM, Pat Haugen
<pthau...@linux.vnet.ibm.com> wrote:
> I noticed the loop unroller peels an extra copy of the loop before it enters 
> the switch block code to round the iteration count to a multiple of the 
> unroll factor. This peeled copy is only needed for the case where the exit 
> test is at the beginning of the loop since in that case it inserts the test 
> for zero peel iterations before that peeled copy.
> This patch bumps the iteration count by 1 for loops with the exit at the end 
> so that it represents the number of times the loop body is executed, and 
> therefore removes the need to always execute that first peeled copy. With 
> this change, when the number of executions of the loop is an even multiple of 
> the unroll factor then the code will jump to the unrolled loop immediately 
> instead of executing all the switch code and peeled copies of the loop and 
> then falling into the unrolled loop. This change also reduces code size by 
> removing a peeled copy of the loop.
> Bootstrap/regtest on powerpc64le with no new regressions. Ok for trunk?

This patch or
PR rtl-optimization/68212
* cfgloopmanip.c (duplicate_loop_to_header_edge): Use preheader edge
frequency when computing scale factor for peeled copies.
* loop-unroll.c (unroll_loop_runtime_iterations): Fix freq/count
values for switch/peel blocks/edges.

Caused a ~2.7-3.5% regression in coremarks with -funroll-all-loops.


> 2016-09-22  Pat Haugen  <pthau...@us.ibm.com>
>         * loop-unroll.c (unroll_loop_runtime_iterations): Condition initial
>         loop peel to loops with exit test at the beginning.

Reply via email to