CUDA
i_dont_give_a_fxxk
专注。。。坚持。。。
展开
-
对于__syncthreads()的理解
CUDA官方文档的原文是:__syncthreads()is allowed in conditional code but only if the conditional evaluatesidentically across the entire thread block, otherwise the code execution is likely to hangor produce原创 2014-03-18 22:12:08 · 2626 阅读 · 0 评论 -
关于warp中遇到Branch Divergence的执行情况
CUDA官方的文档[1]里原文是:If threads of a warp diverge via adata-dependent conditional branch, the warp serially executes each branch path taken,disabling threads that are not on that path, and when all pa原创 2014-03-18 21:24:29 · 2214 阅读 · 0 评论