On Fri, Oct 14, 2016 at 8:28 PM, Andrew Pinski <pins...@gmail.com> wrote:
> 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.
I should say on ThunderX (aarch64-linux-gnu).
>> 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.