首页> 外国专利> Technique for the intermetallic - procedural memory addresses space optimization in gpu - rake compiler

Technique for the intermetallic - procedural memory addresses space optimization in gpu - rake compiler

机译:金属间程序存储器的技术解决了GPU-rake编译器中的空间优化问题

摘要

A devices - compiler - and - linker is configured for optimization of a program code of a coprocessor - suitable application by dissolving a generic memory access operations within this program code, in order to remove targets on specific storage spaces. In cases where a generic memory access operation, and cannot be resolved to constant memory may be aimed at, are constant variable, the with these generic memory access operations are associated, shifted in such a manner that they process, in the global memory residual.
机译:通过在该程序代码中分解通用内存访问操作,可将设备-编译器-和-链接器配置为优化协处理器-合适的应用程序,以删除特定存储空间上的目标。在通用存储器访问操作无法解决为恒定存储器的情况下,如果它们是恒定变量,则这些通用存储器访问操作将与这些通用存储器访问操作相关联,并以它们处理的方式在全局存储器残差中关联。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号