TMBL kernels for CUDA GPUs compile faster using PTX: computational intelligence on consumer games and graphics hardware
TMBL kernels for CUDA GPUs compile faster using PTX: computational intelligence on consumer games and graphics hardware
复制标题
CUDA GPU 的 TMBL 内核使用 PTX 编译速度更快：消费游戏和图形硬件上的计算智能
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
G. D. Magoulas
中科院分区：
文献类型：
--
作者：
Tony E. Lewis;G. D. Magoulas
许多最有效的尝试来利用图形处理单元（GPU）加速遗传编程（GP）的力量已经为个人进行了动态编译的代码。该方法在GPU上非常快速执行，但编译缓慢，因此只有大量的数据集完全获得了奖励。为了减少汇编时间，我们在低级语言PTX中生成和编译代码。我们在GPU上实施调整突变行为学习（TMBL）的背景下进行了研究。我们发现，对于300条说明的程序，使用PTX将编译时间缩短了5.861次，甚至将评估速度提高了23.029％。
Many of the most effective attempts to harness the power of the Graphics Processing Unit (GPU) to accelerate Genetic Programming (GP) have dynamically compiled code for individuals as they are to be evaluated. This approach executes very quickly on the GPU but is slow to compile, hence only vast data-sets fully reap its rewards. To reduce compilation time, we generate and compile code in the lower-level language PTX. We investigate this in the context of implementing Tweaking Mutation Behaviour Learning (TMBL) on the GPU. We find that for programs of 300 instructions, using PTX reduces the compile time 5.861 times and even increases the evaluation speed by 23.029%.