6 CONCLUSION
In this paper we have presented measures for trad-
ing storage overhead for workload reduction. Our
key findings were, that despite being more accu-
rate, fully redundant storage does not yield propor-
tional performance gain, compared to the memory in-
vested. We could show in our evaluation, that our
hand tuned Bloom filter approach can save a tremen-
dous amount of main memory and still provide rea-
sonable speedups. Considering the huge experimen-
tal space, we envision to continue this research and
combine these findings with (Krause et al., 2017a),
to built an adaptive system, which can adapt both the
partitioning and the employed Bloom filter to achieve
optimal performance.
REFERENCES
Bagan, G., Bonifati, A., Ciucanu, R., Fletcher, G. H. L.,
Lemay, A., and Advokaat, N. (2017). gMark:
Schema-driven generation of graphs and queries.
IEEE Transactions on Knowledge and Data Engineer-
ing, 29(4).
Bloom, B. H. (1970). Space/time trade-offs in hash coding
with allowable errors. Communications of the ACM,
13(7).
Borkar, S. et al. (2011). The future of microprocessors.
Commun. ACM, 54(5).
Broder, A. Z. and Mitzenmacher, M. (2003). Survey: Net-
work applications of bloom filters: A survey. Internet
Mathematics, 1(4).
Decker, S., Melnik, S., van Harmelen, F., Fensel, D., Klein,
M. C. A., Broekstra, J., Erdmann, M., and Horrocks,
I. (2000). The semantic web: The roles of XML and
RDF. IEEE Internet Computing, 4(5).
Granlund, T. (2017). Instruction latencies and
throughput for AMD and Intel x86 processors.
https://gmplib.org/˜tege/x86-timing.pdf.
Hull, T. E. and Dobell, A. R. (1962). Random Number Gen-
erators. SIAM Review, 4.
Karypis, G. and Kumar, V. (1998). A fast and high quality
multilevel scheme for partitioning irregular graphs.
Kissinger, T., Kiefer, T., Schlegel, B., Habich, D., Molka,
D., and Lehner, W. (2014). ERIS: A numa-aware in-
memory storage engine for analytical workload. In In-
ternational Workshop on Accelerating Data Manage-
ment Systems Using Modern Processor and Storage
Architectures - ADMS, Hangzhou, China, September
1.
Ko, S. and Han, W. (2018). Turbograph++: A scalable and
fast graph analytics system. In Proceedings of the In-
ternational Conference on Management of Data, SIG-
MOD Conference, Houston, TX, USA, June 10-15.
Krause, A., Kissinger, T., Habich, D., Voigt, H., and Lehner,
W. (2017a). Partitioning strategy selection for in-
memory graph pattern matching on multiprocessor
systems. In Euro-Par 2017: Parallel Processing -
23rd International Conference on Parallel and Dis-
tributed Computing, Santiago de Compostela, Spain,
August 28 - September 1, Proceedings.
Krause, A., Ungeth
¨
um, A., Kissinger, T., Habich, D., and
Lehner, W. (2017b). Asynchronous graph pattern
matching on multiprocessor systems. In New Trends
in Databases and Information Systems - ADBIS 2017
Short Papers and Workshops, AMSD, BigNovelTI,
DAS, SW4CH, DC, Nicosia, Cyprus, September 24-
27, Proceedings.
Lu, Y., Cheng, J., Yan, D., and Wu, H. (2014). Large-scale
distributed graph computing systems: An experimen-
tal evaluation. PVLDB, 8(3).
Neumann, T. and Weikum, G. (2009). Scalable join pro-
cessing on very large RDF graphs. In Proceedings of
the ACM SIGMOD International Conference on Man-
agement of Data, Providence, Rhode Island, USA,
June 29 - July 2.
Otte, E. and Rousseau, R. (2002). Social network analysis:
a powerful strategy, also for the information sciences.
J. Information Science, 28(6).
Pandis, I., Johnson, R., Hardavellas, N., and Ailamaki, A.
(2010). Data-oriented transaction execution. PVLDB,
3(1).
Pandit, S., Chau, D. H., Wang, S., and Faloutsos, C. (2007).
Netprobe: a fast and scalable system for fraud detec-
tion in online auction networks. In Proceedings of the
16th International Conference on World Wide Web,
Banff, Alberta, Canada, May 8-12.
Paradies, M. and Voigt, H. (2017). Big graph data ana-
lytics on single machines - an overview. Datenbank-
Spektrum, 17(2).
Sutter, H. (2005). The free lunch is over: A fundamental
turn toward concurrency in software. Dr. Dobb’s jour-
nal, 30(3).
Tran, T., Wang, H., Rudolph, S., and Cimiano, P. (2009).
Top-k exploration of query candidates for efficient
keyword search on graph-shaped (RDF) data. In Pro-
ceedings of the 25th International Conference on Data
Engineering, ICDE, March 29 - April 2, Shanghai,
China.
Wood, P. T. (2012). Query languages for graph databases.
SIGMOD Record, 41(1).
Yan, D., Cheng, J., Lu, Y., and Ng, W. (2015). Effec-
tive techniques for message reduction and load bal-
ancing in distributed graph computation. In Proceed-
ings of the 24th International Conference on World
Wide Web, Florence, Italy, May 18-22.
Trading Memory versus Workload Overhead in Graph Pattern Matching on Multiprocessor Systems
407