摘要: // 8 Rows of square-matrix A processed by each CTA. // This can be max 32 and only power of 2 (i.e., 2/4/8/16/32). #define ROWS_PER_CTA 8 #if !defined 阅读全文
posted @ 2020-07-03 19:24 洛笔达 阅读(152) 评论(0) 推荐(0) 编辑