TY - GEN
T1 - MosaicSim
T2 - 2020 IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2020
AU - Matthews, Opeoluwa
AU - Manocha, Aninda
AU - Giri, Davide
AU - Orenes-Vera, Marcelo
AU - Tureci, Esin
AU - Sorensen, Tyler
AU - Ham, Tae Jun
AU - Aragon, Juan L.
AU - Carloni, Luca P.
AU - Martonosi, Margaret
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - As Moore's Law has slowed and Dennard Scaling has ended, architects are increasingly turning to heterogeneous parallelism and domain-specific hardware-software co-designs. These trends present new challenges for simulation-based performance assessments that are central to early-stage architectural exploration. Simulators must be lightweight to support rich heterogeneous combinations of general purpose cores and specialized processing units. They must also support agile exploration of hardware-software co-design, i.e. changes in the programming model, compiler, ISA, and specialized hardware. To meet these challenges, we introduce MosaicSim, a lightweight, modular simulator for heterogeneous systems, offering accuracy and agility designed specifically for hardware-software co-design explorations. By integrating the LLVM toolchain, MosaicSim enables efficient modeling of instruction dependencies and flexible additions across the stack. Its modularity also allows the composition and integration of different hardware components. We first demonstrate that MosaicSim captures architectural bottlenecks in applications, and accurately models both scaling trends in a multicore setting and accelerator behavior. We then present two case-studies where MosaicSim enables straightforward design space explorations for emerging systems, i.e. data science application acceleration and heterogeneous parallel architectures.
AB - As Moore's Law has slowed and Dennard Scaling has ended, architects are increasingly turning to heterogeneous parallelism and domain-specific hardware-software co-designs. These trends present new challenges for simulation-based performance assessments that are central to early-stage architectural exploration. Simulators must be lightweight to support rich heterogeneous combinations of general purpose cores and specialized processing units. They must also support agile exploration of hardware-software co-design, i.e. changes in the programming model, compiler, ISA, and specialized hardware. To meet these challenges, we introduce MosaicSim, a lightweight, modular simulator for heterogeneous systems, offering accuracy and agility designed specifically for hardware-software co-design explorations. By integrating the LLVM toolchain, MosaicSim enables efficient modeling of instruction dependencies and flexible additions across the stack. Its modularity also allows the composition and integration of different hardware components. We first demonstrate that MosaicSim captures architectural bottlenecks in applications, and accurately models both scaling trends in a multicore setting and accelerator behavior. We then present two case-studies where MosaicSim enables straightforward design space explorations for emerging systems, i.e. data science application acceleration and heterogeneous parallel architectures.
KW - accelerators
KW - hardware-software co design
KW - heterogeneity
KW - multi-core architectures
KW - performance modeling
UR - http://www.scopus.com/inward/record.url?scp=85097156267&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097156267&partnerID=8YFLogxK
U2 - 10.1109/ISPASS48437.2020.00029
DO - 10.1109/ISPASS48437.2020.00029
M3 - Conference contribution
AN - SCOPUS:85097156267
T3 - Proceedings - 2020 IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2020
SP - 136
EP - 148
BT - Proceedings - 2020 IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2020
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 23 August 2020 through 25 August 2020
ER -