Brief description not available

 Efficiency gains for a few sample applications; CGM = Continuous Glucose Monitor; MSS = Mergeable Stateful Signatures.

Modern Graphical Processing Units (GPUs) consist of several Streaming Multiprocessors (SM) – each has its own Register File (RF) and a number of integers, floating points and specialized computational cores. GPU program is decomposed into one or more cooperative thread arrays that are scheduled to the SMs. GPUs invest in large RFs to enable fine-grained and fast switching between executing groups of threads. This results in RFs being the most power hungry components of the GPU. The RF organization substantially affects the overall performance and energy efficiency of the GPU.

Prof. Nael Ghazaleh and Hodjat Asghari Esfeden from the University of California, Riverside have developed Breathing Operand Windows (BOW), an enhanced GPU pipeline and operand collector technique that supports bypassing register file accesses and instead passes values directly between instructions within the same window. While this baseline design can only bypass register reads, they also introduce an improved design capable of bypassing unnecessary write operations to the RF. Compiler optimizations help guide the write-back destination of operands depending on whether they will be reused to further reduce the write traffic. The BOW microarchitecture reduces RF dynamic energy consumption by 55%, while at the same time increases overall performance by 11%, with a modest overhead of 12KB of additional storage which is ~4% of the RF size. Fig 1: shows the dynamic energy normalized to the baseline GPU for BOW-WR across fifteen different benchmarks. The small segments on top of each bar represent the overheads of the structures added by the idea. Dynamic energy savings in Fig 1 are due to the reduced number of accesses to the register file as BOW-WR shields the RF from unnecessary read and write operations.