Advanced Micro Devices, Inc.
Compressed Read and Write Operations via Deduplication

Abstract:

Systems, apparatuses, and methods for implementing a collapsed stack are disclosed. A parallel processor includes a plurality of compute units for executing wavefronts of a given application. Each compute unit includes multiple single-instruction, multiple-data (SIMD) units. When the work-items executing on the execution lanes of a SIMD unit are writing data values to a stack, many of the data values are repeated. In these cases, when the lanes are pushing duplicate data values to the stack, a control unit deduplicates the duplicate data values and stores the deduplicated data values. The control unit then generates a control word that maps the deduplicated data values to execution lanes and stores the control word in association with the stored data values. When the stored data values are restored, the control word is used to determine which lanes receive which values of the stored data values.