发明名称 SYSTEM AND METHOD FOR PROCESSING THREAD GROUPS IN SIMD ARCHITECTURE
摘要 PROBLEM TO BE SOLVED: To provide a SIMD processor which utilizes its hardware resources to achieve higher data processing throughput. SOLUTION: The effective width of the SIMD processor is extended by clocking the instruction processing side of the SIMD processor at a fraction of the rate of the data processing side and by providing multiple execution pipelines, each with multiple data paths. As a result, higher data processing throughput is achieved while an instruction is fetched and issued once per clock. This configuration also allows a large group of threads to be clustered and executed together through the SIMD processor so that greater memory efficiency can be achieved for a certain type of operation like texture memory access performed in connection with graphics processing. COPYRIGHT: (C)2007,JPO&INPIT
申请公布号 JP2007157154(A) 申请公布日期 2007.06.21
申请号 JP20060327322 申请日期 2006.12.04
申请人 NVIDIA CORP 发明人 COON BRETT W;LINDHOLM JOHN E
分类号 G06F9/38 主分类号 G06F9/38
代理机构 代理人
主权项
地址