Very long instruction work architectures and the ELI-512 论文
1998引用 387
Parallel Computing and Optimization TechniquesEmbedded Systems Design TechniquesLow-power high-performance VLSI design
摘要
By compiling ordinary scientific applications programs with a radical technique called trace scheduling, we are generating code for a parallel machine that will run these programs faster than an equivalent sequential machine -we expect 10 to 30 times faster.
相关事件
暂无数据
相关文章
暂无数据