arXiv subjects

Daniel Lemire

Publications and source records attributed to Daniel Lemire.

At least 55 records · Page 3Linked to original sources

arXiv2017

On Desirable Semantics of Functional Dependencies over Databases with Incomplete Information

Codd's relational model describes just one possible world. To better cope with incomplete information, extended database models allow several possible worlds. Vague tables are one such convenient extended model where attributes accept sets of possible values (e.g., the manager is either Jill or Bob). However, conceptual database design in such cases remains an open problem. In particular, there is no canonical definition of functional dependencies (FDs) over possible worlds (e.g., each employee has just one manager). We identify several desirable properties that the semantics of such FDs should meet including Armstrong's axioms, the independence from irrelevant attributes, seamless satisfaction and implied by strong satisfaction. We show that we can define FDs such that they have all our desirable properties over vague tables. However, we also show that no notion of FD can satisfy all our desirable properties over a more general model (disjunctive tables). Our work formalizes a trade-off between having a general model and having well-behaved FDs.

cs.DB↗

arXiv2017

Vectorized VByte Decoding

We consider the ubiquitous technique of VByte compression, which represents each integer as a variable length sequence of bytes. The low 7 bits of each byte encode a portion of the integer, and the high bit of each byte is reserved as a continuation flag. This flag is set to 1 for all bytes except the last, and the decoding of each integer is complete when a byte with a high bit of 0 is encountered. VByte decoding can be a performance bottleneck especially when the unpredictable lengths of the encoded integers cause frequent branch mispredictions. Previous attempts to accelerate VByte decoding using SIMD vector instructions have been disappointing, prodding search engines such as Google to use more complicated but faster-to-decode formats for performance-critical code. Our decoder (Masked VByte) is 2 to 4 times faster than a conventional scalar VByte decoder, making the format once again competitive with regard to speed.

cs.IR↗

arXiv2017

Upscaledb: Efficient Integer-Key Compression in a Key-Value Store using SIMD Instructions

Compression can sometimes improve performance by making more of the data available to the processors faster. We consider the compression of integer keys in a B+-tree index. For this purpose, systems such as IBM DB2 use variable-byte compression over differentially coded keys. We revisit this problem with various compression alternatives such as Google's VarIntGB, Binary Packing and Frame-of-Reference. In all cases, we describe algorithms that can operate directly on compressed data. Many of our alternatives exploit the single-instruction-multiple-data (SIMD) instructions supported by modern CPUs. We evaluate our techniques in a database environment provided by Upscaledb, a production-quality key-value database. Our best techniques are SIMD accelerated: they simultaneously reduce memory usage while improving single-threaded speeds. In particular, a differentially coded SIMD binary-packing techniques (BP128) can offer a superior query speed (e.g., 40% better than an uncompressed database) while providing the best compression (e.g., by a factor of ten). For analytic workloads, our fast compression techniques offer compelling benefits. Our software is available as open source.

cs.DB↗

arXiv2016

Threshold and Symmetric Functions over Bitmaps

Bitmap indexes are routinely used to speed up simple aggregate queries in databases. Set operations such as intersections, unions and complements can be represented as logical operations (AND, OR, NOT). However, less is known about the application of bitmap indexes to more advanced queries. We want to extend the applicability of bitmap indexes. As a starting point, we consider symmetric Boolean queries (e.g., threshold functions). For example, we might consider stores as sets of products, and ask for products that are on sale in 2 to 10 stores. Such symmetric Boolean queries generalize intersection, union, and T-occurrence queries. It may not be immediately obvious to an engineer how to use bitmap indexes for symmetric Boolean queries. Yet, maybe surprisingly, we find that the best of our bitmap-based algorithms are competitive with the state-of-the-art algorithms for important special cases (e.g., MergeOpt, MergeSkip, DivideSkip, ScanCount). Moreover, unlike the competing algorithms, the result of our computation is again a bitmap which can be further processed within a bitmap index. We review algorithmic design issues such as the aggregation of many compressed bitmaps. We conclude with a discussion on other advanced queries that bitmap indexes might be able to support efficiently.

cs.DB↗

arXiv2016

Regular and almost universal hashing: an efficient implementation

Random hashing can provide guarantees regarding the performance of data structures such as hash tables---even in an adversarial setting. Many existing families of hash functions are universal: given two data objects, the probability that they have the same hash value is low given that we pick hash functions at random. However, universality fails to ensure that all hash functions are well behaved. We further require regularity: when picking data objects at random they should have a low probability of having the same hash value, for any fixed hash function. We present the efficient implementation of a family of non-cryptographic hash functions (PM+) offering good running times, good memory usage as well as distinguishing theoretical guarantees: almost universality and component-wise regularity. On a variety of platforms, our implementations are comparable to the state of the art in performance. On recent Intel processors, PM+ achieves a speed of 4.7 bytes per cycle for 32-bit outputs and 3.3 bytes per cycle for 64-bit outputs. We review vectorization through SIMD instructions (e.g., AVX2) and optimizations for superscalar execution.

cs.DS↗

arXiv2016

Bloofi: Multidimensional Bloom Filters

Bloom filters are probabilistic data structures commonly used for approximate membership problems in many areas of Computer Science (networking, distributed systems, databases, etc.). With the increase in data size and distribution of data, problems arise where a large number of Bloom filters are available, and all them need to be searched for potential matches. As an example, in a federated cloud environment, each cloud provider could encode the information using Bloom filters and share the Bloom filters with a central coordinator. The problem of interest is not only whether a given element is in any of the sets represented by the Bloom filters, but which of the existing sets contain the given element. This problem cannot be solved by just constructing a Bloom filter on the union of all the sets. Instead, we effectively have a multidimensional Bloom filter problem: given an element, we wish to receive a list of candidate sets where the element might be. To solve this problem, we consider 3 alternatives. Firstly, we can naively check many Bloom filters. Secondly, we propose to organize the Bloom filters in a hierarchical index structure akin to a B+ tree, that we call Bloofi. Finally, we propose another data structure that packs the Bloom filters in such a way as to exploit bit-level parallelism, which we call Flat-Bloofi. Our theoretical and experimental results show that Bloofi and Flat-Bloofi provide scalable and efficient solutions alternatives to search through a large number of Bloom filters.

cs.DB↗

arXiv2016

Removing Manually-Generated Boilerplate from Electronic Texts: Experiments with Project Gutenberg e-Books

Collaborative work on unstructured or semi-structured documents, such as in literature corpora or source code, often involves agreed upon templates containing metadata. These templates are not consistent across users and over time. Rule-based parsing of these templates is expensive to maintain and tends to fail as new documents are added. Statistical techniques based on frequent occurrences have the potential to identify automatically a large fraction of the templates, thus reducing the burden on the programmers. We investigate the case of the Project Gutenberg corpus, where most documents are in ASCII format with preambles and epilogues that are often copied and pasted or manually typed. We show that a statistical approach can solve most cases though some documents require knowledge of English. We also survey various technical solutions that make our approach applicable to large data sets.

cs.DL↗

arXiv2016

Sorting improves word-aligned bitmap indexes

Bitmap indexes must be compressed to reduce input/output costs and minimize CPU usage. To accelerate logical operations (AND, OR, XOR) over bitmaps, we use techniques based on run-length encoding (RLE), such as Word-Aligned Hybrid (WAH) compression. These techniques are sensitive to the order of the rows: a simple lexicographical sort can divide the index size by 9 and make indexes several times faster. We investigate row-reordering heuristics. Simply permuting the columns of the table can increase the sorting efficiency by 40%. Secondary contributions include efficient algorithms to construct and aggregate bitmaps. The effect of word length is also reviewed by constructing 16-bit, 32-bit and 64-bit indexes. Using 64-bit CPUs, we find that 64-bit indexes are slightly faster than 32-bit indexes despite being nearly twice as large.

cs.DB↗

arXiv2016

Recursive n-gram hashing is pairwise independent, at best

Many applications use sequences of n consecutive symbols (n-grams). Hashing these n-grams can be a performance bottleneck. For more speed, recursive hash families compute hash values by updating previous values. We prove that recursive hash families cannot be more than pairwise independent. While hashing by irreducible polynomials is pairwise independent, our implementations either run in time O(n) or use an exponential amount of memory. As a more scalable alternative, we make hashing by cyclic polynomials pairwise independent by ignoring n-1 bits. Experimentally, we show that hashing by cyclic polynomials is is twice as fast as hashing by irreducible polynomials. We also show that randomized Karp-Rabin hash families are not pairwise independent.

cs.DB↗

arXiv2016

Collaborative OLAP with Tag Clouds: Web 2.0 OLAP Formalism and Experimental Evaluation

Increasingly, business projects are ephemeral. New Business Intelligence tools must support ad-lib data sources and quick perusal. Meanwhile, tag clouds are a popular community-driven visualization technique. Hence, we investigate tag-cloud views with support for OLAP operations such as roll-ups, slices, dices, clustering, and drill-downs. As a case study, we implemented an application where users can upload data and immediately navigate through its ad hoc dimensions. To support social networking, views can be easily shared and embedded in other Web sites. Algorithmically, our tag-cloud views are approximate range top-k queries over spontaneous data cubes. We present experimental evidence that iceberg cuboids provide adequate online approximations. We benchmark several browser-oblivious tag-cloud layout optimizations.

cs.DB↗

arXiv2016

Better bitmap performance with Roaring bitmaps

Bitmap indexes are commonly used in databases and search engines. By exploiting bit-level parallelism, they can significantly accelerate queries. However, they can use much memory, and thus we might prefer compressed bitmap indexes. Following Oracle's lead, bitmaps are often compressed using run-length encoding (RLE). Building on prior work, we introduce the Roaring compressed bitmap format: it uses packed arrays for compression instead of RLE. We compare it to two high-performance RLE-based bitmap encoding techniques: WAH (Word Aligned Hybrid compression scheme) and Concise (Compressed `n' Composable Integer Set). On synthetic and real data, we find that Roaring bitmaps (1) often compress significantly better (e.g., 2 times) and (2) are faster than the compressed alternatives (up to 900 times faster for intersections). Our results challenge the view that RLE-based bitmap compression is best.

cs.DB↗

arXiv2016

Web 2.0 OLAP: From Data Cubes to Tag Clouds

cs.DB↗

arXiv2015

Faster 64-bit universal hashing using carry-less multiplications

Intel and AMD support the Carry-less Multiplication (CLMUL) instruction set in their x64 processors. We use CLMUL to implement an almost universal 64-bit hash family (CLHASH). We compare this new family with what might be the fastest almost universal family on x64 processors (VHASH). We find that CLHASH is at least 60% faster. We also compare CLHASH with a popular hash function designed for speed (Google's CityHash). We find that CLHASH is 40% faster than CityHash on inputs larger than 64 bytes and just as fast otherwise.

cs.DS↗

arXiv2015

A General SIMD-based Approach to Accelerating Compression Algorithms

Compression algorithms are important for data oriented tasks, especially in the era of Big Data. Modern processors equipped with powerful SIMD instruction sets, provide us an opportunity for achieving better compression performance. Previous research has shown that SIMD-based optimizations can multiply decoding speeds. Following these pioneering studies, we propose a general approach to accelerate compression algorithms. By instantiating the approach, we have developed several novel integer compression algorithms, called Group-Simple, Group-Scheme, Group-AFOR, and Group-PFD, and implemented their corresponding vectorized versions. We evaluate the proposed algorithms on two public TREC datasets, a Wikipedia dataset and a Twitter dataset. With competitive compression ratios and encoding speeds, our SIMD-based algorithms outperform state-of-the-art non-vectorized algorithms with respect to decoding speeds.

cs.IR↗

arXiv2015

Measuring academic influence: Not all citations are equal

The importance of a research article is routinely measured by counting how many times it has been cited. However, treating all citations with equal weight ignores the wide variety of functions that citations perform. We want to automatically identify the subset of references in a bibliography that have a central academic influence on the citing paper. For this purpose, we examine the effectiveness of a variety of features for determining the academic influence of a citation. By asking authors to identify the key references in their own work, we created a data set in which citations were labeled according to their academic influence. Using automatic feature selection with supervised machine learning, we found a model for predicting academic influence that achieves good performance on this data set using only four features. The best features, among those we evaluated, were those based on the number of times a reference is mentioned in the body of a citing paper. The performance of these features inspired us to design an influence-primed h-index (the hip-index). Unlike the conventional h-index, it weights citations by how many times a reference is mentioned. According to our experiments, the hip-index is a better indicator of researcher performance than the conventional h-index.

cs.DL↗

arXiv2014

Compressed bitmap indexes: beyond unions and intersections

Compressed bitmap indexes are used to speed up simple aggregate queries in databases. Indeed, set operations like intersections, unions and complements can be represented as logical operations (AND,OR,NOT) that are ideally suited for bitmaps. However, it is less obvious how to apply bitmaps to more advanced queries. For example, we might seek products in a store that meet some, but maybe not all, criteria. Such threshold queries generalize intersections and unions; they are often used in information-retrieval and data-mining applications. We introduce new algorithms that are sometimes three orders of magnitude faster than a naive approach. Our work shows that bitmap indexes are more broadly applicable than is commonly believed.

cs.DB↗

arXiv2014

Diamond Dicing

In OLAP, analysts often select an interesting sample of the data. For example, an analyst might focus on products bringing revenues of at least 100 000 dollars, or on shops having sales greater than 400 000 dollars. However, current systems do not allow the application of both of these thresholds simultaneously, selecting products and shops satisfying both thresholds. For such purposes, we introduce the diamond cube operator, filling a gap among existing data warehouse operations. Because of the interaction between dimensions the computation of diamond cubes is challenging. We compare and test various algorithms on large data sets of more than 100 million facts. We find that while it is possible to implement diamonds in SQL, it is inefficient. Indeed, our custom implementation can be a hundred times faster than popular database engines (including a row-store and a column-store).

cs.DB↗

arXiv2014

Functional dependencies with null markers

Functional dependencies are an integral part of database design. However, they are only defined when we exclude null markers. Yet we commonly use null markers in practice. To bridge this gap between theory and practice, researchers have proposed definitions of functional dependencies over relations with null markers. Though sound, these definitions lack some qualities that we find desirable. For example, some fail to satisfy Armstrong's axioms---while these axioms are part of the foundation of common database methodologies. We propose a set of properties that any extension of functional dependencies over relations with null markers should possess. We then propose two new extensions having these properties. These extensions attempt to allow null markers where they make sense to practitioners. They both support Armstrong's axioms and provide realizable null markers: at any time, some or all of the null markers can be replaced by actual values without causing an anomaly. Our proposals may improve database designs.

cs.DB↗