(ACM Computing Surveys 2015)
This paper first reviews research works which compare energy efficiency of GPUs with other computing systems, e.g. FPGAs and CPUs. Then, it reviews techniques proposed for power management of GPUs and classifies the techniques based on several dimensions.
(IEEE TPDS 2015)
This paper especially focusses on techniques proposed for modeling and improving resilience against soft (transient) errors caused due to cosmic radiation etc. It discusses techniques proposed for CPU and GPU (and their components such as cache, main memory, register file, functional unit), non-volatile memories (e.g. phase change memory) etc.
(IEEE TPDS 2015)
It discusses compression in CPUs and GPUs, conventional (SRAM and DRAM) and non-volatile memory (NVM) systems, and 2D and 3D memory systems. It also discusses interaction of compression with prefetching, error-correction and thermal and power management