发明名称 TECHNIQUE FOR PERFORMING MEMORY ACCESS OPERATIONS VIA TEXTURE HARDWARE
摘要 A texture processing pipeline can be configured to service memory access requests that represent texture data access operations or generic data access operations. When the texture processing pipeline receives a memory access request that represents a texture data access operation, the texture processing pipeline may retrieve texture data based on texture coordinates. When the memory access request represents a generic data access operation, the texture pipeline extracts a virtual address from the memory access request and then retrieves data based on the virtual address. The texture processing pipeline is also configured to cache generic data retrieved on behalf of a group of threads and to then invalidate that generic data when the group of threads exits.
申请公布号 US2014173258(A1) 申请公布日期 2014.06.19
申请号 US201213720746 申请日期 2012.12.19
申请人 NVIDIA CORPORATION 发明人 FAHS Brian;ANDERSON Eric T.;BARROW-WILLIAMS Nick;GADRE Shirish;MCCORMACK Joel James;NORDQUIST Bryon S.;SAXENA Nirmal Raj;SHAH Lacky V.
分类号 G06F9/30 主分类号 G06F9/30
代理机构 代理人
主权项 1. A computer implemented method for performing a generic data access operation for a group of threads executing on a processing unit, the method comprising: receiving a memory access request from a thread within the group of threads; determining that a portion of data associated with the memory access request is not present in a cache memory unit; retrieving the portion of data associated with the memory access request from global memory; storing the portion of data within the cache memory unit during execution of the threads within the thread group; and flushing the portion of data from the cache memory unit upon determining that each thread within the group of threads has completed executing on the processing unit.
地址 Santa Clara CA US