This paper considers a hybrid memory system composed of memory technologies with different characteristics; in particular a small, near memory exhibiting high bandwidth, i.e., 3D-stacked DRAM, and a larger, far memory offering capacity at lower bandwidth, i.e., off-chip DRAM. In the past, the near memory of such a system has been used either as a DRAM cache or as part of a flat address space combined with a migration mechanism. Caches and migration offer different tradeoffs (between performance, main memory capacity, data transfer costs, etc.) and share similar challenges related to data-transfer granularity and metadata management. This paper proposes Hybrid 2 , a new hybrid memory system architecture that combines a DRAM cache with a migration scheme. Hybrid 2 does not deny valuable capacity from the memory system because it uses only a small fraction of the near memory as a DRAM cache; 64MB in our experiments. It further leverages the DRAM cache as a staging area to select the data most suitable for migration. Finally, Hybrid 2 alleviates the metadata overheads of both DRAM caches and migration using a common mechanism. Using near to far memory ratios of 1:16, 1:8 and 1:4 in our experiments, Hybrid 2 on average outperforms current state-of-the-art migration schemes by 7.9%, 9.1% and 6.4%, respectively. In the same system configurations, compared to DRAM caches Hybrid 2 gives away on average only 0.3%, 1.2%, and 5.3% of performance offering 5.9%, 12.1%, and 24.6% more main memory capacity, respectively.

Task-based dataflow programming models and runtimes emerge as promising candidates for programming multicore and manycore architectures. These programming models analyze dynamically task dependencies at runtime and schedule independent tasks concurrently to the processing elements. In such models, cache locality, which is critical for performance, becomes more challenging in the presence of finegrain tasks, and in architectures with many simple cores.This paper presents a combined hardware-software approach to improve cache locality and offer better performance is terms of execution time and energy in the memory system. We propose the explicit bulk prefetcher (EBP) and epoch-based cache management (ECM) to help runtimes prefetch task data and guide the replacement decisions in caches. The runtime software can use this hardware support to expose its internal knowledge about the tasks to the architecture and achieve more efficient task-based execution. Our combined scheme outperforms HW-only prefetchers and state-of-the-art replacement policies, improves performance by an average of 17%, generates on average 26% fewer L2 misses, and consumes on average 28% less energy in the components of the memory system.

In order to reach exascale performance, current HPC systems need to be improved. Simple hardware scaling is not a feasible solution due to the increasing utility costs and power consumption limitations. Apart from improvements in implementation technology, what is needed is to refine the HPC application development flow as well as the system architecture of future HPC systems. ECOSCALE tackles these challenges by proposing a scalable programming environment and architecture, aiming to substantially reduce energy consumption as well as data traffic and latency. ECOSCALE introduces a novel heterogeneous energyefficient hierarchical architecture, as well as a hybrid many-core+OpenCL programming environment and runtime system. The ECOSCALE approach is hierarchical and is expected to scale well by partitioning the physical system into multiple independent Workers (i.e. compute nodes). Workers are interconnected in a tree-like fashion and define a contiguous global address space that can be viewed either as a set of partitions in a Partitioned Global Address Space (PGAS), or as a set of nodes hierarchically interconnected via an MPI protocol. To further increase energy efficiency, as well as to provide resilience, the Workers employ reconfigurable accelerators mapped into the virtual address space utilizing a dual stage System Memory Management Unit with coherent memory access. The architecture supports shared partitioned reconfigurable resources accessed by any Worker in a PGAS partition, as well as automated hardware synthesis of these resources from an OpenCL-based programming model.

Abstract-Modeling emerging multicore architectures is challenging and imposes a tradeoff between simulation speed and accuracy. An effective practice that balances both targets well is to map the target architecture on FPGA platforms. We find that accurate prototyping of hundreds of cores on existing FPGA boards faces at least one of the following problems: (i) limited fast memory resources (SRAM) to model caches, (ii) insufficient inter-board connectivity for scaling the design or (iii) the board is too expensive. We address these shortcomings by designing a new FPGA board for multicore architecture prototyping, which explicitly targets scalability and cost-efficiency. Formic has a 35% bigger FPGA, three times more SRAM, four times more links and costs at most half as much when compared to the popular Xilinx XUPV5 prototyping platform. We build and test a 64-board system by developing a 512-core, MicroBlaze-based, non-coherent hardware prototype with DMA capabilities, with full networkon-chip in a 3D-mesh topology. We believe that Formic offers significant advantages over existing academic and commercial platforms that can facilitate hardware prototyping for future manycore architectures.

Packet classification is one of the most important enabling technologies for next generation network services. Even though many multi-dimensional classification algorithms have been proposed, most of them are precluded from commercial equipments due to their high memory requirements. In this paper, we present an efficient packet classification scheme, called Bloom Based Packet Classification (B2PC). B2PC comprises of an innovative 5-field search algorithm that decomposes multifield classification rules into internal single field rules which are combined using multi-level Bloom filters. The design of B2PC is optimized for the common case based on analysis of real world classification databases. The hardware implementation of this scheme handles 4K rules by involving only 530KB of memory for its data structures, while it supports network streams at a rate of 15Gbps even in the worst case, and more than 40Gbps in the average case. This system covers 1.3 mm 2 in a 0.18µm CMOS technology. We show that given a certain memory budget and silicon cost, the B2PC is the most efficient hardware-based approach to the classification problem.