Guy E. Blelloch

Guy E. Blelloch, Anupam Gupta, Ioannis Koutis et al.

We present the design and analysis of a near linear-work parallel algorithm for solving symmetric diagonally dominant (SDD) linear systems. On input of a SDD $n$-by-$n$ matrix $A$ with $m$ non-zero entries and a vector $b$, our algorithm computes a vector $\tilde{x}$ such that $\norm[A]{\tilde{x} - A^+b} \leq \vareps \cdot \norm[A]{A^+b}$ in $O(m\log^{O(1)}{n}\log{\frac1ε})$ work and $O(m^{1/3+θ}\log \frac1ε)$ depth for any fixed $θ> 0$. The algorithm relies on a parallel algorithm for generating low-stretch spanning trees or spanning subgraphs. To this end, we first develop a parallel decomposition algorithm that in polylogarithmic depth and $\otilde(|E|)$ work, partitions a graph into components with polylogarithmic diameter such that only a small fraction of the original edges are between the components. This can be used to generate low-stretch spanning trees with average stretch $O(n^α)$ in $O(n^{1+α})$ work and $O(n^α)$ depth. Alternatively, it can be used to generate spanning subgraphs with polylogarithmic average stretch in $\otilde(|E|)$ work and polylogarithmic depth. We apply this subgraph construction to derive a parallel linear system solver. By using this solver in known applications, our results imply improved parallel randomized algorithms for several problems, including single-source shortest paths, maximum flow, minimum-cost flow, and approximate maximum flow.

Michael A. Bender, Guy E. Blelloch, Martin Farach-Colton et al.

We study the problem of constructing concurrent objects in a setting where $P$ processes run in parallel and interact through a shared memory that is subject to write contention. Our goal is to transform hardware primitives that are subject to write contention into ones that handle contention gracefully. We give contention-resolution algorithms for several basic primitives, and analyze them under a relaxed, roughly-synchronous stochastic scheduler, where processes run at roughly the same rate up to a constant factor with high probability. Specifically, we construct read/write registers and CAS registers that have latency $O(\log P)$ w.h.p. under our scheduler model, using $O(1)$ hardware read/write registers and, in the case of our CAS construction, one hardware CAS register. Our algorithms guarantee performance even when their operations are invoked by an adaptive adversary that is able to see the entire history of operations so far, including their timing and return values. This allows them to be used as building blocks inside larger programs; using this compositionality property, we obtain several other constructions (LL/SC, fetch-and-increment, bounded max registers, and counters). To complement our constructions, we give a trade-off showing that even under a perfectly synchronous schedule and even if each process only executes one operation, any algorithm that implements any of the primitives that we consider, uses space $M$, and has latency at most $L$ with high probability must have expected latency at least $Ω(\log_{ML} P)$.

Magdalen Dobson Manohar, Zheqi Shen, Guy E. Blelloch et al.

Approximate nearest-neighbor search (ANNS) algorithms are a key part of the modern deep learning stack due to enabling efficient similarity search over high-dimensional vector space representations (i.e., embeddings) of data. Among various ANNS algorithms, graph-based algorithms are known to achieve the best throughput-recall tradeoffs. Despite the large scale of modern ANNS datasets, existing parallel graph based implementations suffer from significant challenges to scale to large datasets due to heavy use of locks and other sequential bottlenecks, which 1) prevents them from efficiently scaling to a large number of processors, and 2) results in nondeterminism that is undesirable in certain applications. In this paper, we introduce ParlayANN, a library of deterministic and parallel graph-based approximate nearest neighbor search algorithms, along with a set of useful tools for developing such algorithms. In this library, we develop novel parallel implementations for four state-of-the-art graph-based ANNS algorithms that scale to billion-scale datasets. Our algorithms are deterministic and achieve high scalability across a diverse set of challenging datasets. In addition to the new algorithmic ideas, we also conduct a detailed experimental study of our new algorithms as well as two existing non-graph approaches. Our experimental results both validate the effectiveness of our new techniques, and lead to a comprehensive comparison among ANNS algorithms on large scale datasets with a list of interesting findings.