IEEE Transactions on Very Large Scale Integration (VLSI) Systems · 2011 · 19 citations · 12 references
Heterogeneous ComputingEngineeringEnergy EfficiencyHomogeneous Stream ProcessorsComputer ArchitectureEmbedded SystemsGpu ComputingHardware SecurityHigh-performance ArchitectureHigh-utilization Programmable ShadersParallel ComputingManycore ProcessorComputer EngineeringComputer ScienceMultiple SfusGpu ArchitectureHardware AccelerationMany-core ArchitectureParallel ProgrammingSpecial Function Units
We embed special function units (SFUs) in homogeneous stream processors (SPs) within a graphics processing unit (GPU), to improve its performance in running modern programmable shaders, which make poor use of a single-instruction multiple-data (SIMD) architecture. We also compact instructions, so as to reduce the size of the instruction memory, and reduce area requirements by using a partial SFU in SPs, and a lookup table which is shared between multiple SFUs. The result is an increase of 88% in utilization and a reduction in the normalized area-delay product of 27%, compared to a baseline SIMD architecture. We verified our architecture on an field-programmable gate-array evaluation platform with an ARM9 host processor and a full 3-D graphics pipeline.
12
NVIDIA Tesla: A Unified Graphics and Computing Architecture
Erik Lindholm, John Nickolls, Stuart F. Oberman et al. · IEEE Micro · 2008 · 1.3K citations
Graphics Processing Units for Handhelds
Tomas Akenine‐Möller, Jacob Ström · Proceedings of the IEEE · 2008 · 69 citations
Shader Performance Analysis on a Modern GPU Architecture
Victor Moya, Carlos González, Josep Roca et al. · 2006 · 49 citations
Shader Performance Analysis, Gpu Architecture, Engineering +13