Decoupled access/execute computer architectures

By James E. Smith. 1984

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Carole-Jean Wu
2. Lianmin Zheng
3. Young Geun Kim
4. Tianqi Chen
5. Carlos Guestrin
6. Thierry Moreau
7. Ji Lin
8. Ziheng Jiang

Citations in the corpus

• Socio-Technological Challenges and Opportunities: Paths Forward (2021, background): “Microarchitectural optimizations enabled impressive ILP scaling: most notably, in-order vs. out-of-order execution [Tomasulo, 1967, Smith, 1982a, Hwu and Patt, 1986], branch predictors [Smith, 1981, Lee and Smith, 1984, Pnevmatikatos et al., 1993, Yeh et al., 1993, Jimenez and Lin, 2001], caches…”
• TVM: An Automated End-to-End Optimizing Compiler for Deep Learning (2018, background): “In contrast, specialized deep learning accelerators such as the TPU [20] usually favor leaner control with a decoupled access-execute (DAE) architecture [32] and offload the problem of finegrained synchronization to software.”
• Automatic thread extraction with decoupled software pipelining (2005, background): “Others describe how such intercore queues can be implemented [20, 23].”
• TVM: An Automated End-to-End Optimizing Compiler for Deep Learning (2018, background): “leaner control with a decoupled access-execute (DAE) architecture [35] and offload the problem of fine-grained synchronization to software.”