E.1 Ferret
E.1.1 1 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.1: Ferret 1 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.2: Ferret 1 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.3: Ferret 1 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.4: Ferret 1 core DL1 dynamic energy consumption
84
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.5: Ferret 1 core L2 dynamic energy consumption
E.2 Blackscholes
E.2.1 1 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.6: Blackscholes 1 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.7: Blackscholes 1 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.8: Blackscholes 1 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.9: Blackscholes 1 core DL1 dynamic energy consumption
86
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.10: Blackscholes 1 core L2 dynamic energy consumption
E.2.2 4 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.11: Blackscholes 4 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.12: Blackscholes 4 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.13: Blackscholes 4 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.14: Blackscholes 4 core DL1 dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.15: Blackscholes 4 core L2 dynamic energy consumption
88
E.2.3 16 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.16: Blackscholes 16 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.17: Blackscholes 16 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.18: Blackscholes 16 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.19: Blackscholes 16 core DL1 dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.20: Blackscholes 16 core L2 dynamic energy consumption
90
E.3 Swaptions
E.3.1 1 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.21: Swaptions 1 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.22: Swaptions 1 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.23: Swaptions 1 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.24: Swaptions 1 core DL1 dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.25: Swaptions 1 core L2 dynamic energy consumption
92
E.3.2 4 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.26: Swaptions 4 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.27: Swaptions 4 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.28: Swaptions 4 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.29: Swaptions 4 core DL1 dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.30: Swaptions 4 core L2 dynamic energy consumption
E.3.3 16 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.31: Swaptions 16 core processor dynamic energy consumption
94
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.32: Swaptions 16 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.33: Swaptions 16 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.34: Swaptions 16 core DL1 dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.35: Swaptions 16 core L2 dynamic energy consumption
E.4 Dedup
E.4.1 1 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.36: Dedup 1 core processor dynamic energy consumption
96
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.37: Dedup 1 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.38: Dedup 1 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.39: Dedup 1 core DL1 dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.40: Dedup 1 core L2 dynamic energy consumption
E.5 Streamcluster
E.5.1 1 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.41: Streamcluster 1 core processor dynamic energy consumption
98
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.42: Streamcluster 1 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.43: Streamcluster 1 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.44: Streamcluster 1 core DL1 dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.45: Streamcluster 1 core L2 dynamic energy consumption
E.5.2 4 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.46: Streamcluster 4 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.47: Streamcluster 4 core processor dynamic power consumption
100
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.48: Streamcluster 4 core processor static power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.49: Streamcluster 4 core DL1 dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.50: Streamcluster 4 core L2 dynamic energy consumption
E.5.3 16 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.51: Streamcluster 16 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.52: Streamcluster 16 core processor dynamic power consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.53: Streamcluster 16 core processor static power consumption
102
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.54: Streamcluster 16 core DL1 dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.55: Streamcluster 16 core L2 dynamic energy consumption
E.6 Average
E.6.1 1 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.56: Average 1 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.57: Average 1 core processor dynamic power consumption
104
E.6.2 4 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.58: Average 4 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.59: Average 4 core processor dynamic power consumption
E.6.3 16 core
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.60: Average 16 core processor dynamic energy consumption
(a) Fixed associativity and latency (b) Unfixed associativity and latency Figure E.61: Average 16 core processor dynamic power consumption
106
Bibliography
[1] C. Bienia. Benchmarking modern multiprocessors. January 2011.
[2] N. Binkert, B. Beckmann, G. Black, S. K. Reinhardt, A. Saidi, A. Basu, J. Hestness, D. R. Hower, T. Krishna, S. Sardashti, R. Sen, K. Sewell, M. Shoaib, N. Vaish, M. D. Hill, and D. A. Wood. The gem5 simulator. SIGARCH Comput.Archit.News, 39(2):1–7, aug 2011.
[3] N. L. Binkert, R. G. Dreslinski, L. R. Hsu, K. T. Lim, A. G. Saidi, and S. K. Rein-hardt. The m5 simulator: Modeling networked systems. Micro, IEEE, 26(4):52–60, 2006.
[4] D. Brooks, V. Tiwari, and M. Martonosi. Wattch: a framework for architectural-level power analysis and optimizations. In Computer Architecture, 2000. Proceedings of the 27th International Symposium on, pages 83–94, 2000.
[5] BSC. Extrae. http://www.bsc.es/computer-sciences/extrae. Visited on 03/18/2015.
[6] BSC. Mercurium. https://pm.bsc.es/projects/mcxx. Visited on 03/18/2015.
[7] BSC. Nanos. https://pm.bsc.es/projects/nanox. Visited on 03/18/2015.
[8] BSC. Paraver: a flexible performance analysis tool. http://www.bsc.es/computer-sciences/performance-tools/paraver/general-overview. Visited on 03/18/2015.
[9] T. E. Carlson, W. Heirman, and L. Eeckhout. Sniper: Exploring the level of abstrac-tion for scalable and accurate parallel multi-core simulaabstrac-tion. In High Performance Computing, Networking, Storage and Analysis (SC), 2011 International Conference for, pages 1–12, 2011.
[10] L. J. Colmenar JM, Risco Martin JL. an overview of computer architecture and system simulation. Technical report, 2011.
[11] A. Duran, E. Ayguad´e, R. M. Badia, J. Labarta, L. Martinell, X. Martorell, and J. Planas. Ompss: A proposal for programming heterogeneous multi-core architec-tures. Parallel Processing Letters, 21(02):173–193, 2011.
[12] F. A. Endo, C. Damien, and H.-P. Charles. Micro-architectural simulation of embed-ded core heterogeneity with gem5 and mcpat. In Proceedings of the 2015 Workshop on Rapid Simulation and Performance Evaluation: Methods and Tools, RAPIDO
’15, pages 7:1–7:6, 2015.
[13] D. Genbrugge, S. Eyerman, and L. Eeckhout. Interval simulation: Raising the level of abstraction in architectural simulation. In High Performance Computer Architecture (HPCA), 2010 IEEE 16th International Symposium on, pages 1–12, 2010.
[14] S. Li, J. H. Ahn, R. D. Strong, J. B. Brockman, D. M. Tullsen, and N. P. Jouppi.
Mcpat: An integrated power, area, and timing modeling framework for multicore and manycore architectures. In Proceedings of the 42Nd Annual IEEE/ACM Inter-national Symposium on Microarchitecture, MICRO 42, pages 469–480, 2009.
[15] S. Li, J. H. Ahn, R. D. Strong, J. B. Brockman, D. M. Tullsen, and N. P. Jouppi.
The mcpat framework for multicore and manycore architectures: Simultaneously modeling power, area, and timing. ACM Trans.Archit.Code Optim., 10(1):5:1–5:29, apr 2013.
[16] M. M. K. Martin, D. J. Sorin, B. M. Beckmann, M. R. Marty, M. Xu, A. R.
Alameldeen, K. E. Moore, M. D. Hill, and D. A. Wood. Multifacet’s gen-eral execution-driven multiprocessor simulator (gems) toolset. SIGARCH Com-put.Archit.News, 33(4):92–99, nov 2005.
[17] J. E. Miller, H. Kasture, G. Kurian, C. Gruenwald, N. Beckmann, C. Celio, J. Eastep, and A. Agarwal. Graphite: A distributed parallel simulator for mul-ticores. In High Performance Computer Architecture (HPCA), 2010 IEEE 16th International Symposium on, pages 1–12, 2010.
[18] A. Rico, F. Cabarcas, C. Villavieja, M. Pavlovic, A. Vega, Y. Etsion, A. Ramirez, and M. Valero. On the simulation of large-scale architectures using multiple ap-plication abstraction levels. ACM Trans.Archit.Code Optim., 8(4):36:1–36:20, jan 2012.
[19] A. Rico, A. Duran, F. Cabarcas, Y. Etsion, A. Ramirez, and M. Valero. Trace-driven simulation of multithreaded applications. In Performance Analysis of Systems and Software (ISPASS), 2011 IEEE International Symposium on, pages 87–96, 2011.
[20] C. Sun, C. H. O. Chen, G. Kurian, L. Wei, J. Miller, A. Agarwal, L.-S. Peh, and V. Stojanovic. Dsent - a tool connecting emerging photonics with electronics for opto-electronic networks-on-chip modeling. In Networks on Chip (NoCS), 2012 Sixth IEEE/ACM International Symposium on, pages 201–210, 2012.
108
[21] S. J. E. Wilton and N. P. Jouppi. Cacti: an enhanced cache access and cycle time model. Solid-State Circuits, IEEE Journal of, 31(5):677–688, 1996.