does tvm support the autotune of AMD's graphic and AMD's APU with target = “opencl” using cuda depthwise schedule, the generated .so can actually be deployed on the device of AMD?
--- [Visit Topic](http://tracking.discuss.tvm.ai/tracking/click?d=8ibk6r162fJ69L5p1jUSSVUiMfIdDp9Kz2YVI2fxIsboNyI5rrHBfzIPfFr8ypjj33Trzyjh90ETBQnFZbeX-cayzkX2k7hL6EDUKB8SK_sGLwUrIJtuc37Bk1wsOjTxlPA1bdnzM8KdsUPyTfHHr1wSzKH-IGgscovDcN9HfHOB_8BnfVzSeNVPorD8t7ff3nlSzHhx-mP-VQ6_3Rs2Xrs1) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](http://tracking.discuss.tvm.ai/tracking/click?d=7cFgOaAA4XIBVlVKt_oyC07uihTjg4Q6cjeBRNRTiPqFBqfWq8Yc5FTfgk44-AFwPEOsOWbyLAFP3c-H04REbZeaiBR5AQF9pSuHYX3ml7x1hulQGCT2VZXruBUb32OeD7cw7Mc7AQlGoIGt8EKFyp9WGf_DO4R1jUUHHyvXfxS7B2NTWOuEIJjz6vZo6YgDBux4t_r69Km8J7Hx98gYmiLrpr73-ugN3hfsvOncOwBP0). Tianqi Chen, UW, Seattle, WA, 98105, United States http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=CZ-s7uDzuhO30WQfc6v6AQ2
