Aergia: Exploiting packet latency slack in on-chip networks
Traditional Network-on-Chips (NoCs) employ simple arbitration strategies, such as round-
robin or oldest-first, to decide which packets should be prioritized in the network. This is …
robin or oldest-first, to decide which packets should be prioritized in the network. This is …
Application-aware prioritization mechanisms for on-chip networks
Network-on-Chips (NoCs) are likely to become a critical shared resource in future many-
core processors. The challenge is to develop policies and mechanisms that enable multiple …
core processors. The challenge is to develop policies and mechanisms that enable multiple …
NoC-based support of heterogeneous cache-coherence models for accelerators
On-chip shared memory is the primary paradigm for multi-core SoC designs and poses the
most critical challenges to their scalability. Choosing the appropriate coherence model for …
most critical challenges to their scalability. Choosing the appropriate coherence model for …
The runahead network-on-chip
With increasing core counts and higher memory demands from applications, it is imperative
that networks-on-chip (NoCs) provide low-latency, power-efficient communication …
that networks-on-chip (NoCs) provide low-latency, power-efficient communication …
Supporting efficient collective communication in NoCs
Across many architectures and parallel programming paradigms, collective communication
plays a key role in performance and correctness. Hardware support is necessary to prevent …
plays a key role in performance and correctness. Hardware support is necessary to prevent …
Near-ideal networks-on-chip for servers
Server workloads benefit from execution on many-core processors due to their massive
request-level parallelism. A key characteristic of server workloads is the large instruction …
request-level parallelism. A key characteristic of server workloads is the large instruction …
A cost effective centralized adaptive routing for networks-on-chip
As the number of applications and programmable units in CMPs and MPSoCs increases, the
Network-on-Chip (NoC) encounters unpredictable, heterogeneous and time dependent …
Network-on-Chip (NoC) encounters unpredictable, heterogeneous and time dependent …
Heterogeneous NoC design for efficient broadcast-based coherence protocol support
Chip Multiprocessor Systems (CMPs) rely on a cache coherency protocol to maintain
memory access coherence between cached data and main memory. The Hammer …
memory access coherence between cached data and main memory. The Hammer …
Heterogeneous interconnects for energy-efficient message management in cmps
Continuous improvements in integration scale have made major microprocessor vendors to
move to designs that integrate several processing cores on the same chip. Chip …
move to designs that integrate several processing cores on the same chip. Chip …
Polytopes, permanents and graphs with large factors
Randomized algorithms for approximating the number of perfect matchings in a graph are
considered. An algorithm that is a natural simplification of one suggested and analyzed …
considered. An algorithm that is a natural simplification of one suggested and analyzed …