Re: [PATCH] tree-optimization/103116 - SLP permutes and peeling for gaps

2022-05-04 Thread Richard Biener via Gcc-patches
On Wed, 4 May 2022, Richard Sandiford wrote: > Richard Biener writes: > > The testcase shows that we can end up with a contiguous access across > > loop iterations but by means of permutations the elements accessed > > might only cover parts of a vector. In this case we end up with > > GROUP_GAP

Re: [PATCH] tree-optimization/103116 - SLP permutes and peeling for gaps

2022-05-04 Thread Richard Sandiford via Gcc-patches
Richard Biener writes: > The testcase shows that we can end up with a contiguous access across > loop iterations but by means of permutations the elements accessed > might only cover parts of a vector. In this case we end up with > GROUP_GAP == 0 but still need to avoid accessing excess elements

[PATCH] tree-optimization/103116 - SLP permutes and peeling for gaps

2022-05-04 Thread Richard Biener via Gcc-patches
The testcase shows that we can end up with a contiguous access across loop iterations but by means of permutations the elements accessed might only cover parts of a vector. In this case we end up with GROUP_GAP == 0 but still need to avoid accessing excess elements in the last loop iterations. Pe