{"author":"Szymon Ożóg","author_email":"58388001+SzymonOzog@users.noreply.github.com","author_time":1715620441,"commit_time":1715620441,"committer":"GitHub","committer_email":"noreply@github.com","hash":"d97d5a76899a3caf448b093f69a2e21bdd76be97","message":"Optimize PTX gated loads index calculation (#4304)\n\n* WIP but working\r\n\r\n* Cleanup\r\n\r\n* Remove float4 pred and alt\r\n\r\n* Cleanup\r\n\r\n* this is somehow slowin it down\r\n\r\n* Simplify\r\n\r\n* add define var to ignore when optimizing gates\r\n\r\n* Update assembly.py\r\n\r\n* Test for optimizing gated loads\r\n\r\n* Cleanup\r\n\r\n* Fix NEG needed before if\r\n\r\n* Remove unused parameters\r\n\r\n* Update assembly.py\r\n\r\n* Fix for cachable gone\r\n\r\n---------\r\n\r\nCo-authored-by: oz <oz@oz-MS-7B86.NAT.gliwice.vectranet.pl>\r\nCo-authored-by: chenyu <chenyu@fastmail.com>","parents":["c67b70ca67849938af7012e86a27e1c1c8d73d39"],"tree_hash":"94847d238b0ef99bcdfb65673439250d2d1a582c"}