Power calculation for transistor operation What will cause

Power calculation for transistor operation • What will cause power consumption to increase? CS 2710 Computer Organization 1

Measuring the current used by the Atmega microprocessor shows a linear relationship ATMEGA 32 Current versus Crystal Frequency 50 R 2 = 0. 9921 Microprocessor Current (m. A) 45 40 35 30 25 Current 20 Linear(Current) 15 10 5 0 0 2000000 4000000 6000000 80000001000000012000000140000001600000018000000 Crystal Frequency (Hz) Note: V=5 v for in this case CS 2710 Computer Organization 2

What effect does increasing voltage to a microprocessor have on power? On speed? Power versus Microprocessor Voltage 250 R 2 = 0. 9984 Microprocessor Power (m. W) 200 150 Power(Power) 100 50 Below around 2. 5 v (for this microprocessor), the transistors simply stop working 0 0 1 2 Microprocessor Voltage 4 3 CS 2710 Computer Organization 5 6 3

The Power Wall: Why haven’t clock rates continued to increase at historical rates? CS 2710 Computer Organization 4

Manufacturers have turned to multi-core architectures to bypass the Power Wall Clock speed decrease, but overall performance increase CS 2710 Computer Organization 5

Benchmarking Lecture Objectives: 1) Explain the SPEC benchmarks. 2) Define Amdahl's law 3) Define MIPS

Amdahl’s Law (p 51) • The performance enhancement possible with a given improvement is limited by the amount that the improved feature is used CS 2710 Computer Organization 7

Amdahl’s Law Applied • A Program spends 40 seconds performing network transfers and 60 seconds generating reports. – Suppose we could rewrite the report generator to make it more efficient. – What improvement in performance in the report generator would be necessary to increase the overall speed of the program by a factor of 2? – How about by a factor of 3? CS 2710 Computer Organization 8

A Performance Metric: MIPS Units: millions of instructions per second CS 2710 Computer Organization 9

Issues with MIPS metrics 1. Measures instruction execution rate, but doesn’t consider the complexity of the instructions performed 2. Average instruction complexity varies between programs executing on a single computer 3. Different microprocessors implement instructions of differing complexities • MIPS may vary independently from performance • We cannot compare computers with different instruction sets using MIPS! CS 2710 Computer Organization 10

Benchmarking: How do you decide which computer to buy? CS 2710 Computer Organization 11

SPEC Benchmark • A set of programs used to measure performance – Supposedly typical of actual workload • Standard Performance Evaluation Corp (SPEC) – Develops benchmarks for CPU, I/O, Web, … • SPEC CPU 2006 – Elapsed time to execute a selection of programs • Negligible I/O, so focuses on CPU performance – Normalize relative to reference machine – Summarize as geometric mean of performance ratios • CINT 2006 (integer) and CFP 2006 (floating-point) CS 2710 Computer Organization 12

Geometric vs. Arithmetic Mean • Arithmetic mean: • Geometric mean: CS 2710 Computer Organization 13

Which computer has better overall performance? Computer A Computer B Computer C Program 1 1 10 20 Program 2 1000 100 20 CS 2710 Computer Organization 14

Which computer has better overall performance? Computer A Computer B Computer C Program 1 1 10 20 Program 2 1000 100 20 Arithmetic mean 500. 5 55 20 Geometric mean 31. 622. . . 20 A is fastest via Arithmetic mean. A and B are tied via Geometric mean is the appropriate mean when the ranges of the values being compared vary significantly. CS 2710 Computer Organization 15

Benchmarking often computes performance relative to a standard reference Computer A Computer B Computer C Program 1 1 10 20 Program 2 1000 100 20 Let’s say A is the “reference” computer. We adjust all performance values by dividing each value by the reference computer’s value. In this example, we divide all results for Program 2 by the reference computer’s performance value of 1000, giving: Computer A (reference) Computer B Computer C Program 1 1 10 20 Program 2 1 0. 02 Scaling the results in this manner is called normalization. Note that no normalization was needed for Program 1 since the reference computer’s value was already 1. CS 2710 Computer Organization 16

Arithmetic and Geometric means based on the normalized values: Computer A Computer B Computer C Program 1 1 10 20 Program 2 1 0. 02 Arithmetic mean 1 5. 05 10. 01 Geometric mean 1 1 0. 632. . . Now C is fastest via Arithmetic mean! A and B are still tied via Geometric mean. CS 2710 Computer Organization 17

Now consider computer B to be the “reference” computer and normalize A and C w. r. t. B Computer A Computer B (reference) Computer C Program 1 0. 1 1 2 Program 2 10 1 0. 2 Arithmetic mean 5. 05 1 1. 1 Geometric mean 1 1 0. 632 Now A is fastest via Arithmetic mean! A and B are still tied via Geometric mean. The Geometric mean is consistent regardless of normalization! CS 2710 Computer Organization 18

The SPECjvm 2008 application – SPECjvm 2008 is a benchmark suite for measuring the performance of a Java Runtime Environment (JRE), containing several real life applications and benchmarks focusing on core java functionality. – The SPECjvm 2008 workload mimics a variety of common general purpose application computations. CS 2710 Computer Organization 19

CINT 2006 integer performance benchmarks for the Opteron X 4 2356 Name Description IC× 109 CPI Tc (ns) Exec time Ref time SPECratio perl Interpreted string processing 2, 118 0. 75 0. 40 637 9, 777 15. 3 bzip 2 Block-sorting compression 2, 389 0. 85 0. 40 817 9, 650 11. 8 gcc GNU C Compiler 1, 050 1. 72 0. 47 24 8, 050 11. 1 mcf Combinatorial optimization 336 10. 00 0. 40 1, 345 9, 120 6. 8 go Go game (AI) 1, 658 1. 09 0. 40 721 10, 490 14. 6 hmmer Search gene sequence 2, 783 0. 80 0. 40 890 9, 330 10. 5 sjeng Chess game (AI) 2, 176 0. 96 0. 48 37 12, 100 14. 5 libquantum Quantum computer simulation 1, 623 1. 61 0. 40 1, 047 20, 720 19. 8 h 264 avc Video compression 3, 102 0. 80 0. 40 993 22, 130 22. 3 omnetpp Discrete event simulation 587 2. 94 0. 40 690 6, 250 9. 1 astar Games/path finding 1, 082 1. 79 0. 40 773 7, 020 9. 1 xalancbmk XML parsing 1, 058 2. 70 0. 40 1, 143 6, 900 6. 0 Geometric mean 11. 7 CS 2710 Computer Organization 20

SPEC and power: ssj_ops (server-side java operations/sec) • Power consumption of server at different workload levels – Performance: ssj_ops/sec – Power: Watts (Joules/sec) CS 2710 Computer Organization 21

A Power benchmark: SPEC Power versus load SPECpower_ssj 2008 for X 4 Target Load % Performance (ssj_ops/sec) Average Power (Watts) 100% 231, 867 295 90% 211, 282 286 80% 185, 803 275 70% 163, 427 265 60% 140, 160 256 50% 118, 324 246 40% 920, 35 233 30% 70, 500 222 20% 47, 126 206 10% 23, 066 180 0% 0 141 1, 283, 590 2, 605 Overall sum ∑ssj_ops/ ∑power 493 CS 2710 Computer Organization 22

Low power at low usage? No! • Look back at X 4 power benchmark – At 100% load: 295 W – At 50% load: 246 W (83%) – At 10% load: 180 W (61%) • Google data center – Mostly operates at 10% – 50% load – At 100% load less than 1% of the time • Future research/development: Design processors to make power proportional to load CS 2710 Computer Organization 23