Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Johnathan Alsop"'
Publikováno v:
ACM Transactions on Architecture and Code Optimization. 19:1-26
Hardware specialization is becoming a key enabler of energy-efficient performance. Future systems will be increasingly heterogeneous, integrating multiple specialized and programmable accelerators, each with different memory demands. Traditionally, c
Autor:
Sarita V. Adve, Matthew D. Sinclair, Muhammad Huzaifa, Johnathan Alsop, Giordano Salvador, Abdulrahman Mahmoud
Publikováno v:
ACM Transactions on Architecture and Code Optimization. 17:1-27
As GPUs have become more programmable, their performance and energy benefits have made them increasingly popular. However, while GPU compute units continue to improve in performance, on-chip memories lag behind and data accesses are becoming increasi
Autor:
Johnathan Alsop, Wesley H. Darvin, Giordano Salvador, Sarita V. Adve, Muhammad Huzaifa, Matthew D. Sinclair
Publikováno v:
ISPASS
This work provides the first study to explore the interaction of update propagation with and without fine-grained synchronization (push vs. pull), emerging coherence protocols (GPU vs. DeNovo coherence), and software-centric consistency models (DRF0,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34cda0a77bd0705afdf636d286cb0064
Autor:
Bradford M. Beckmann, Tsung Tai Yeh, Xianwei Zhang, Alexandru Dutu, Anthony Gutierrez, Onur Kayiran, Srikant Bharadwaj, Matthew D. Sinclair, Michael LeBeane, Sooraj Puthoor, Johnathan Alsop, Brandon Potter
Publikováno v:
IISWC
In recent years, machine intelligence (MI) applications have emerged as a major driver for the computing industry. Optimizing these workloads is important, but complicated. As memory demands grow and data movement overheads increasingly limit perform
Publikováno v:
ISCA
Recent heterogeneous architectures have trended toward tighter integration and shared memory largely due to the efficient communication and programmability enabled by this shift. However, such integration is complex, because accelerators have widely
Autor:
Vikram Adve, Johnathan Alsop, Rakesh Komuravelli, Maria Kotsifakou, Matthew D. Sinclair, Prakalp Srivastava, Muhammad Huzaifa, Sarita V. Adve
Publikováno v:
ISCA
Heterogeneous systems employ specialization for energy efficiency. Since data movement is expected to be a dominant consumer of energy, these systems employ specialized memories (e.g., scratchpads and FIFOs) for better efficiency for targeted data. T
Publikováno v:
IISWC
Traditionally GPUs focused on streaming, data-parallel applications, with little data reuse or sharing and coarse-grained synchronization. However, the rise of general-purpose GPU (GPGPU) computing has made GPUs desirable for applications with more g
Publikováno v:
ISCA
An unambiguous and easy-to-understand memory consistency model is crucial for ensuring correct synchronization and guiding future design of heterogeneous systems. In a widely adopted approach, the memory model guarantees sequential consistency (SC) a
Publikováno v:
2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO).
Publikováno v:
ISPASS
In recent years the power wall has prevented the continued scaling of single core performance. This has lead to the rise of dark silicon and motivated a move toward parallelism and specialization. As a result, energy-efficient high-throughput GPU cor