An official website of the United States government
The conventional model of parallel programming today involves either copying data across cores (and then having to track its most recent value), or not copying and requiring deep software stacks to perform even the simplest operation on data that is “remote”, i.e., out of the range of loads and stores from the current core. As application requirements grow to larger data sets, with more irregular access to them, both conventional approaches start to exhibit severe scaling limitations. This paper reviews some growing evidence of the potential value of a new model of computation that skirts between the two: data does not move (i.e., is not copied), but computation instead moves to the data. Several different applications involving large sparse computations, streaming of data, and complex mixed mode operations have been coded for a novel platform where thread movement is handled invisibly by the hardware. The evidence to date indicates that parallel scaling for this paradigm can be significantly better than any mix of conventional models.
more »
« less
Locality: The 3rd Wall and The Need for Innovation in Parallel Architectures
In the past we have seen two major \walls" (memory and power) whose vanquishing required significant advances in architecture. This paper discusses evidence of a third wall dealing with data locality, which is prevalent in data intensive applications where computation is dominated by memory access and movement - not flops, Such apps exhibit large sets of often persistent data, with little reuse during computation, no predictable regularity, significantly different scaling characteristics, and where streaming is becoming important. Further, as we move to highly parallel algorithms (as in running in the cloud), these issues will get even worse. Solving such problems will take a new set of innovations in architecture. In addition to data on the new wall, this paper will look at one possible technique: the concept of migrating threads, and give evidence of its potential value based on several benchmarks that have scaling difficulties on conventional architectures.
more »
« less
- Award ID(s):
- 1822939
- PAR ID:
- 10298915
- Date Published:
- Journal Name:
- 34th GI/ITG International Conference on Architecture of Computing Systems
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Processing In-Memory (PIM) is a data-centric computation paradigm that performs computations inside the memory, hence eliminating the memory wall problem in traditional computational paradigms used in Von-Neumann architectures. The associative processor, a type of PIM architecture, allows performing parallel and energy-efficient operations on vectors. This architecture is found useful in vector-based applications such as Hyper-Dimensional (HDC) Reinforcement Learning (RL). HDC is rising as a new powerful and lightweight alternative to costly traditional RL models such as Deep Q-Learning. The HDC implementation of Q-Learning relies on encoding the states in a high-dimensional representation where calculating Q-values and finding the maximum one can be done entirely in parallel. In this article, we propose to implement the main operations of a HDC RL framework on the associative processor. This acceleration achieves up to\(152.3\times\)and\(6.4\times\)energy and time savings compared to an FPGA implementation. Moreover, HDRLPIM shows that an SRAM-based AP implementation promises up to\(968.2\times\)energy-delay product gains compared to the FPGA implementation.more » « less
-
null (Ed.)Processing-in-memory (PIM) has raised as a viable solution for the memory wall crisis and has attracted great interest in accelerating computationally intensive AI applications ranging from filtering to complex neural networks. In this paper, we try to take advantage of both PIM and the residue number system (RNS) as an alternative for the conventional binary number representation to accelerate multiplication-and-accumulations (MACs), primary operations of target applications. The PIM architecture utilizes the maximum internal bandwidth of memory chips to realize a local and parallel computation to eliminates the off-chip data transfer. Moreover, RNS limits inter-digit carry propagation by performing arithmetic operations on small residues independently and in parallel. Thus, we develop a PIM-RNS, entitled PRIMS, and analyze the potential of intertwining PIM architecture with the inherent parallelism of the RNS arithmetic to delineate the opportunities and challenges. To this end, we build a comprehensive device-to-architecture evaluation framework to quantitatively study this problem considering the impact of PIM technology for a well-known three-moduli set as a case study.more » « less
-
With the end of Dennard scaling, power constraints have led to increasing compute specialization in the form of differently specialized accelerators integrated at various levels of the general-purpose system hierarchy. The result is that the most common general-purpose computing platform is now a heterogeneous mix of architectures even within a single die. Consequently, mapping application code regions into available execution engines has become a challenge due to different interfaces and increased software complexity. At the same time, the energy costs of data movement have become increasingly dominant relative to computation energy. This has inspired a move towards data-centric systems, where computation is brought to data, in contrast to traditional processing-centric models. However, enabling compute nearer memory entails its own challenges, including the interactions between distance-specialization and compute-specialization. The granularity of any offload to near(er) memory logic would impact the potential data transmission reduction, as smaller offloads will not be able to amortize the transmission costs of invocation and data return, while very large offloads can only be mapped onto logic that can support all of the necessary operations within kernel-scale codes, which exacerbates both area and power constraints. For better energy efficiency, each set of related operations should be mapped onto the execution engine that, among those capable of running the set of operations, best balances the data movement and the degree of compute specialization of that engine for this code. Further, this offload should proceed in a decentralized way that keeps both the data and control movement low for all transitions among engines and transmissions of operands and results. To enable such a decentralized offload model, we propose an architecture interface that enables a common offload model for accelerators across the memory hierarchy and a tool chain to automatically identify (in a distance-aware fashion) and map profitable code regions on specialized execution engines. We evaluate the proposed architecture for a wide range of workloads and show energy reduction compared to an energy-efficient in-order core. We also demonstrate better area efficiency compared to kernel-scale offloads.more » « less
-
The explosion of “big data” applications imposes severe challenges of speed and scalability on traditional computer systems. As the performance of traditional Von Neumann machines is greatly hindered by the increasing performance gap between CPU and memory (“known as the memory wall”), neuromorphic computing systems have gained considerable attention. The biology-plausible computing paradigm carries out computing by emulating the charging/discharging process of neuron and synapse potential. The unique spike domain information encoding enables asynchronous event driven computation and communication, and hence has the potential for very high energy efficiency. This survey reviews computing models and hardware platforms of existing neuromorphic computing systems. Neuron and synapse models are first introduced, followed by the discussion on how they will affect hardware design. Case studies of several representative hardware platforms, including their architecture and software ecosystems, are further presented. Lastly we present several future research directions.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
