ACM Transactions on Architecture and Code Optimization · 2015 · 51 citations · 45 references
EngineeringComputer EngineeringComputer ScienceComputer ArchitectureHardware Description LanguagesLow-power DesignAccelerator ArchitectureGraphics Processing Unit ArchitectureGraphics Processing Unit ComputingGraphics Processing UnitsHardware AccelerationPhysical DesignGpgpu ComputingGpu AcceleratorsGpu ArchitectureGpu MicroarchitectureMany-core ArchitectureMany-core ProcessorsMicroarchitecturePower-efficient Accelerator Design
GPU‑based general‑purpose computing is emerging as a viable alternative to CPU computing, yet existing tools lack detailed microarchitectural views and accurate area‑power estimates needed for evolving GPGPU research. The authors introduce MIAOW, an open‑source RTL implementation of the AMD Southern Islands GPGPU ISA, to enable low‑level GPU hardware exploration. They evaluate MIAOW’s realism and demonstrate its utility through four case studies that provide a physical‑design perspective, enable new research explorations, and validate simulator‑based hardware characterization. The study contributes both the MIAOW tool and novel insights, underscoring its value for future GPU research.
Graphic processing unit (GPU)-based general-purpose computing is developing as a viable alternative to CPU-based computing in many domains. Today’s tools for GPU analysis include simulators like GPGPU-Sim, Multi2Sim, and Barra. While useful for modeling first-order effects, these tools do not provide a detailed view of GPU microarchitecture and physical design. Further, as GPGPU research evolves, design ideas and modifications demand detailed estimates of impact on overall area and power. Fueled by this need, we introduce MIAOW (Many-core Integrated Accelerator Of Wisconsin), an open-source RTL implementation of the AMD Southern Islands GPGPU ISA, capable of running unmodified OpenCL-based applications. We first explore if MIAOW is realistic and then use four case studies to show that MIAOW enables the following: physical design perspective to “traditional” microarchitecture, new types of research exploration, and validation/calibration of simulator-based characterization of hardware. The findings and ideas are contributions in their own right, in addition to MIAOW’s utility as a tool for others’ research.
45
Rodinia: A benchmark suite for heterogeneous computing
Shuai Che, Michael Boyer, Jiayuan Meng et al. · 2009 · 3K citations
Analyzing CUDA workloads using a detailed GPU simulator
Ali Bakhoda, George L. Yuan, Wilson Wai Lun Fung et al. · 2009 · 1.7K citations
Razor: a low-power pipeline based on circuit-level timing speculation
Dan Ernst, Nam Sung Kim, Shidhartha Das et al. · 2003 · 1.1K citations
Engineering, Computer Engineering, Electrical Engineering +16
Richard M. Russell · Communications of the ACM · 1978 · 697 citations · Full text