نویسنده
Yılmaz, Buse, Aktemur, Tankut Barış, Garzaran, M. J., Kamin, S., Kıraç, Mustafa Furkan
تاریخ انتشار
2016-04
محل انتشار
-
ACM
موضوع
Performance, Experimentation, Measurement, Autotuning, Runtime code generation, Sparse matrix-vector multiplication
نوع
دوره ای
زبان
انگلیسی
دیجیتال
بله
نسخه خطی
خیر
کتابخانه
دانشگاه اوزیغین
شناسه دارایی کتابخانه
1544-3973
شماره ثبت
35155ed4-cde3-432f-be0b-588d015a69fe
محل کتابخانه
Computer Science
تاریخ
2016-04
یادداشتها
Due to copyright restrictions, the access to the full text of this article is only available via subscription.
متن نمونه
Runtime specialization is used for optimizing programs based on partial information available only at runtime. In this paper we apply autotuning on runtime specialization of Sparse Matrix-Vector Multiplication to predict a best specialization method among several. In 91% to 96% of the predictions, either the best or the second-best method is chosen. Predictions achieve average speedups that are very close to the speedups achievable when only the best methods are used. By using an efficient code generator and a carefully designed set of matrix features, we show the runtime costs can be amortized to bring performance benefits for many real-world cases.
DOI
10.1145/2851500
Cilt
13
