Histograms as a side effect of data movement for big data

István, Zsolt; Woods, Louis; Alonso, Gustavo

doi:10.1145/2588555.2612174

Cited by 32 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Active research explores the use of FPGA's to accelerate data analytics [19,31,32,35,45,49,50]. Computation kernels are implemented on FPGA's as co-processors.…”

Section: Discussion and Related Workmentioning

confidence: 99%

“…DAnA [45] automatically generates FPGA implementations from UDFs for iterative machine learning training jobs in RDBMS. Other work explores FPGA's for regex matching [50], data partitioning [35] and histogram generation [32]. However, for interactive queries, building one circuit for each algorithm is impractical due to the latency and resource requirement.…”

Section: Discussion and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Accelerating raw data analysis with the ACCORDA software and hardware architecture

2019

View full text Add to dashboard Cite

The data science revolution and growing popularity of data lakes make efficient processing of raw data increasingly important. To address this, we propose the ACCelerated Operators for Raw Data Analysis (ACCORDA) architecture. By extending the operator interface (subtype with encoding) and employing a uniform runtime worker model, ACCORDA integrates data transformation acceleration seamlessly, enabling a new class of encoding optimizations and robust high-performance raw data processing. Together, these key features preserve the software system architecture, empowering state-of-art heuristic optimizations to drive flexible data encoding for performance. ACCORDA derives performance from its software architecture, but depends critically on the acceleration of the Unstructured Data Processor (UDP) that is integrated into the memory-hierarchy, and accelerates data transformation tasks by 16x-21x (parsing, decompression) to as much as 160x (deserialization) compared to an x86 core. We evaluate ACCORDA using TPC-H queries on tabular data formats, exercising raw data properties such as parsing and data conversion. The ACCORDA system achieves 2.9x-13.2x speedups when compared to SparkSQL, reducing raw data processing overhead to a geomean of 1.2x (20%). In doing so, ACCORDA robustly matches or outperforms prior systems that depend on caching loaded data, while computing on raw, unloaded data. This performance benefit is robust across format complexity, query predicates, and selectivity (data statistics). ACCORDA's encoding-extended operator interface unlocks aggressive encoding-oriented optimizations that deliver 80% average performance increase over the 7 affected TPC-H queries.

show abstract

“…Active research explores the use of FPGA's to accelerate data analytics [19,31,32,35,45,49,50]. Computation kernels are implemented on FPGA's as co-processors.…”

Section: Discussion and Related Workmentioning

confidence: 99%

Section: Discussion and Related Workmentioning

confidence: 99%

Accelerating raw data analysis with the ACCORDA software and hardware architecture

2019

View full text Add to dashboard Cite

show abstract

“…For example, the partitioning we have described can also be used for a hardware conscious group by aggregation [1] and in other operators involving partitioning [27]. Recent literature provides multiple examples for operations which can be offloaded to an FPGA: Sub-operators such as bitonic sorting networks [10], histograms [15], hash functions [18]; full operators such as pattern matching and regular expressions [14,23]; and eventually new functions typically not supported such as skyline operators [40].…”

Section: Discussionmentioning

confidence: 99%

“…SIGMOD '17, May [14][15][16][17][18][19]2017 ticore processors [3,27,32] and to explore possible hardware acceleration [37,41].…”

Section: Introductionmentioning

confidence: 99%

FPGA-based Data Partitioning

Kara

Giceva

Alonso

2017

Proceedings of the 2017 ACM International Conference on Management of Data

Self Cite

View full text Add to dashboard Cite

Implementing parallel operators in multicore machines often involves a data partitioning step that divides the data into cache-size blocks and arranges them so to allow concurrent threads to process them in parallel. Data partitioning is expensive, in some cases up to 90% of the cost of, e.g., a parallel hash join. In this paper we explore the use of an FPGA to accelerate data partitioning. We do so in the context of new hybrid architectures where the FPGA is located as a co-processor residing on a socket and with coherent access to the same memory as the CPU residing on the other socket. Such an architecture reduces data transfer overheads between the CPU and the FPGA, enabling hybrid operator execution where the partitioning happens on the FPGA and the build and probe phases of a join happen on the CPU. Our experiments demonstrate that FPGA based partitioning is significantly faster and more robust than CPU based partitioning. The results open interesting options as FPGAs are gradually integrated tighter with the CPU.

show abstract

“…However, unlike BlueDBM, these architectures accelerate computation on data that is in DRAM. Accelerators have also been placed in-path between network and processor to perform operations at wire speed [32], or to collect information such as histogram tables without overhead [18].…”

Section: Related Workmentioning

confidence: 99%

BlueDBM

Jun

Liu

Lee

et al. 2015

Proceedings of the 42nd Annual International Symposium on Computer Architecture

115

View full text Add to dashboard Cite

Complex data queries, because of their need for random accesses, have proven to be slow unless all the data can be accommodated in DRAM. There are many domains, such as genomics, geological data and daily twitter feeds where the datasets of interest are 5TB to 20 TB. For such a dataset, one would need a cluster with 100 servers, each with 128GB to 256GBs of DRAM, to accommodate all the data in DRAM. On the other hand, such datasets could be stored easily in the flash memory of a rack-sized cluster. Flash storage has much better random access performance than hard disks, which makes it desirable for analytics workloads. In this paper we present BlueDBM, a new system architecture which has flashbased storage with in-store processing capability and a lowlatency high-throughput inter-controller network. We show that BlueDBM outperforms a flash-based system without these features by a factor of 10 for some important applications. While the performance of a ram-cloud system falls sharply even if only 5%~10% of the references are to the secondary storage, this sharp performance degradation is not an issue in BlueDBM. BlueDBM presents an attractive point in the cost-performance trade-off for Big Data analytics.

show abstract

Histograms as a side effect of data movement for big data

Cited by 32 publications

References 27 publications

Accelerating raw data analysis with the ACCORDA software and hardware architecture

Accelerating raw data analysis with the ACCORDA software and hardware architecture

FPGA-based Data Partitioning

BlueDBM

Contact Info

Product

Resources

About