Instructions per second

Instructions per second (IPS) is a measure of a computer's processor speed. Many reported IPS values have represented "peak" execution rates on artificial instruction sequences with few branches, whereas realistic workloads typically lead to significantly lower IPS values. Memory hierarchy also greatly affects processor performance, an issue barely considered in IPS calculations. Because of these problems, synthetic benchmarks such as SPECint or Dhrystone are now generally used to estimate computer performance in commonly used applications, and raw IPS has fallen into disuse.

The term is commonly used in association with a numeric value such as thousand instructions per second (kIPS), million instructions per second (MIPS), and billion instructions per second (GIPS).

Thousand instructions per second (kIPS)

Before standard benchmarks were available, average speed rating of computers was based on calculations for a mix of instructions with the results given in kilo Instructions Per Second (kIPS). The most famous was the Gibson Mix,^[1] produced by Jack Clark Gibson of IBM for scientific applications. Other ratings, such as the ADP mix which does not include floating point operations, were produced for commercial applications. Computer Speeds From Instruction Mixes pre-1960 to 1971 has results for around 175 computers, providing scientific (Gibson) and commercial (ADP) ratings. For IBM, the earliest Gibson Mix calculations shown are the 1954 IBM 650 at 0.06 kIPS and 1956 IBM 705 at 0.5 kIPS. The results are mainly for IBM and others known as the BUNCH — Burroughs, UNIVAC, NCR, CDC, and Honeywell.

The thousand instructions per second (kIPS) unit is rarely used today, as most current microprocessors can execute at least a million instructions per second.

Millions of instructions per second (MIPS)

The speed of a given CPU depends on many factors, such as the type of instructions being executed, the execution order and the presence of branch instructions (problematic in CPU pipelines). CPU instruction rates are different from clock frequencies, usually reported in Hz, as each instruction may require several clock cycles to complete or the processor may be capable of executing multiple independent instructions simultaneously. MIPS can be useful when comparing performance between processors made with similar architecture (e.g. Microchip branded microcontrollers). They are difficult to compare between differing CPU architectures.^[2]

For this reason, MIPS has become not a measure of instruction execution speed, but task performance speed compared to a reference. In the late 1970s, minicomputer performance was compared using VAX MIPS, where computers were measured on a task and their performance rated against the VAX 11/780 that was marketed as a 1 MIPS machine. (The measure was also known as the VAX Unit of Performance or VUP.) This was chosen because the 11/780 was roughly equivalent in performance to an IBM System/370 model 158-3, which was commonly accepted in the computing industry as running at 1 MIPS.

Many minicomputer performance claims were based on the Fortran version of the Whetstone benchmark, giving Millions of Whetstone Instructions Per Second (MWIPS). The VAX 11/780 with FPA (1977) runs at 1.02 MWIPS.

Effective MIPS speeds are highly dependent on the programming language used. The Whetstone Report has a table showing MWIPS speeds of PCs via early interpreters and compilers up to modern languages. The first PC compiler was for BASIC (1982) when a 4.8 MHz 8088/87 CPU obtained 0.01 MWIPS. Results on a 2.4 GHz Intel Core 2 Duo (1 CPU 2007) vary from 9.7 MWIPS using BASIC Interpreter, 59 MWIPS via BASIC Compiler, 347 MWIPS using 1987 Fortran, 1,534 MWIPS through HTML/Java to 2,403 MWIPS using a modern C/C++ compiler.

For the most early 8-bit and 16-bit microprocessors, performance was measured in thousand instructions per second (1 kIPS = 0.001 MIPS).

zMIPS refers to the MIPS measure used internally by IBM to rate its mainframe servers (zSeries, IBM System z9, and IBM System z10).

Weighted million operations per second (WMOPS) is a similar measurement, used for audio codecs.

Timeline of instructions per second

Note: Bold highlight indicates the next step-up in terms of the highest known MIPS figures of their time.

Processor / System	Dhrystone MIPS / MIPS	D IPS / clock cycles per second	D IPS / clock cycles per second / cores per die	Year	Source
UNIVAC I	0.002 MIPS at 2.25 MHz	0.0008	0.0008	1951	[3]
Intel 4004	0.092 MIPS at 740 kHz (Not Dhrystone)	0.124	0.124	1971	[4]
IBM System/370 158	0.64 MIPS at 8.696 MHz	0.0736	0.0736	1972	[5]
Intel 8080	0.29 MIPS at 2 MHz	0.145	0.145	1974	[6]
MOS Technology 6502	0.43 MIPS at 1 MHz	0.43	0.43	1975	[7]
Intel 8080A	0.435 MIPS at 3 MHz	0.145	0.145	1976	[6]
Zilog Z80	0.58 MIPS at 4 MHz	0.145	0.145	1976	[7]
Motorola 6809	0.42 MIPS at 1 MHz	0.42	0.42	1977	[7]
Motorola 6802	0.5 MIPS at 1 MHz	0.5	0.5	1977	[8]
IBM System/370 158-3	0.73 MIPS at 8.696 MHz	0.0839	0.0839	1977	[5]
VAX-11/780	1 MIPS at 5 MHz	0.2	0.2	1977	[5]
Fujitsu FACOM 230-75 APU	2 MIPS at 11 MHz	0.182	0.182	1977	[9][10]
Intel 8086	0.33 MIPS at 5 MHz	0.066	0.066	1978	[6]
Fujitsu MB8843	2 MIPS at 2 MHz (Not Dhrystone)	1	1	1978	[11]
Intel 8088	0.75 MIPS at 10 MHz	0.075	0.075	1979	[6]
Motorola 68000	1.4 MIPS at 8 MHz	0.175	0.175	1979	[7]
Zilog Z8001/Z8002	1.5 MIPS at 6 MHz	0.25	0.25	1979	[12]
Intel 8035/8039/8048	6 MIPS at 6 MHz (Not Dhrystone)	1	1	1980	[13]
Fujitsu MB8843/MB8844	6 MIPS at 6 MHz (Not Dhrystone)	1	1	1980	[11]
Zilog Z80/Z80H	1.16 MIPS at 8 MHz	0.145	0.145	1981	[7][14]
Motorola 6802	1.79 MIPS at 3.58 MHz	0.5	0.5	1981	[8][15]
Zilog Z8001/Z8002B	2.5 MIPS at 10 MHz	0.25	0.25	1981	[12]
MOS Technology 6502	2.522 MIPS at 5.865 MHz	0.43	0.43	1981	[7][15]
Sega G80 (3 cores)	7.4 MIPS at 8 MHz	2.467	0.333	1981	[16]
Intel 286	1.28 MIPS at 12 MHz	0.107	0.107	1982	[5]
Motorola 68000	2.188 MIPS at 12.5 MHz	0.175	0.175	1982	[7]
Motorola 68010	2.407 MIPS at 12.5 MHz	0.193	0.193	1982	[17]
NEC V20	4 MIPS at 8 MHz	0.5	0.5	1982	[18]
Namco Pole Position (7 cores)	8.141 MIPS at 3.072 MHz	1.163	0.379	1982	[19]
LINKS-1 Computer Graphics System (257 cores)	642.5 MIPS at 10 MHz	2.5	0.25	1982	[20]
Texas Instruments TMS32010	5 MIPS at 20 MHz	0.25	0.25	1983	[21]
NEC V30	5 MIPS at 10 MHz	0.5	0.5	1983	[18]
Motorola 68010	3.209 MIPS at 16.67 MHz	0.193	0.193	1984	[17]
Motorola 68020	4.848 MIPS at 16 MHz	0.303	0.303	1984	[22]
Hitachi HD63705	2 MIPS at 2 MHz	1	1	1985	[23][24]
Intel i386DX	2.15 MIPS at 16 MHz	0.134	0.134	1985	[5]
Hitachi-Motorola 68HC000	3.5 MIPS at 20 MHz	0.175	0.175	1985	[7]
Intel 8751	8 MIPS at 8 MHz	1	1	1985	[25]
Sega System 16 (4 cores)	16.33 MIPS at 10 MHz	4.083	0.408	1985	[26]
ARM2	4 MIPS at 8 MHz	0.5	0.5	1986
Texas Instruments TMS34010	6 MIPS at 50 MHz	0.12	0.12	1986	[27]
NEC V70	6.6 MIPS at 20 MHz	0.33	0.33	1987	[28]
Motorola 68030	9 MIPS at 25 MHz	0.36	0.36	1987	[29][30]
Gmicro/200	10 MIPS at 20 MHz	0.5	0.5	1987	[31]
Texas Instruments TMS320C20	12.5 MIPS at 25 MHz	0.5	0.5	1987	[32]
Analog Devices ADSP-2100	12.5 MIPS at 12.5 MHz	1	1	1987	[33]
Texas Instruments TMS320C25	25 MIPS at 50 MHz	0.5	0.5	1987	[32]
Motorola 68020	10 MIPS at 33 MHz	0.303	0.303	1988	[22]
Motorola 68030	18 MIPS at 50 MHz	0.36	0.36	1988	[30]
Namco System 21 (10 cores)	73.927 MIPS at 25 MHz	2.957	0.296	1988	[34]
Intel i386DX	4.3 MIPS at 33 MHz	0.13	0.13	1989	[5]
Intel i486DX	8.7 MIPS at 25 MHz	0.348	0.348	1989	[5]
NEC V80	16.5 MIPS at 33 MHz	0.5	0.5	1989	[28]
Intel i860	25 MIPS at 25 MHz	1	1	1989	[35]
Atari Hard Drivin' (7 cores)	33.573 MIPS at 50 MHz	0.671	0.0959	1989	[36]
NEC SX-3 (4 cores)	680 MIPS at 400 MHz	1.7	0.425	1989	[37][38]
Motorola 68040	44 MIPS at 40 MHz	1.1	1.1	1990	[39]
Namco System 21 (Galaxian³) (96 cores)	1,660.386 MIPS at 40 MHz	41.51	0.432	1990	[40]
AMD Am386	9 MIPS at 40 MHz	0.225	0.225	1991	[41]
Intel i486DX	11.1 MIPS at 33 MHz	0.336	0.336	1991	[5]
Intel i860	50 MIPS at 50 MHz	1	1	1991	[35]
Intel i486DX2	25.6 MIPS at 66 MHz	0.388	0.388	1992	[5]
DEC Alpha 21064 EV4	86 MIPS at 150 MHz	0.573	0.573	1992	[5]
DEC Alpha 21064 EV4	135 MIPS at 200 MHz	0.675	0.675	1993	[5][42]
MIPS R4400	85 MIPS at 150 MHz	0.567	0.567	1993	[43]
Gmicro/500	132 MIPS at 66 MHz	2	2	1993	[44]
IBM-Motorola PowerPC 601	157.7 MIPS at 80 MHz	1.971	1.971	1993	[45]
SGI Onyx RealityEngine^2 (36 cores)	2,640 MIPS at 150 MHz	17.6	0.489	1993	[46]
Namco Magic Edge Hornet Simulator (36 cores)	2,880 MIPS at 150 MHz	19.2	0.533	1993	[43]
Fujitsu-NAL Numerical Wind Tunnel (168 cores)	10,718.4 MIPS at 105 MHz	63.8	0.608	1993	[47][48]
ARM7	40 MIPS at 45 MHz	0.889	0.889	1994	[49]
Intel DX4	70 MIPS at 100 MHz	0.7	0.7	1994	[6]
Motorola 68060	110 MIPS at 75 MHz	1.33	1.33	1994
Intel Pentium	188 MIPS at 100 MHz	1.88	1.88	1994	[50]
Microchip PIC16F	5 MIPS at 20 MHz	0.25	0.25	1995	[51]
IBM-Motorola PowerPC 603e	188 MIPS at 133 MHz	1.414	1.414	1995	[52]
ARM 7500FE	35.9 MIPS at 40 MHz	0.9	0.9	1996
IBM-Motorola PowerPC 603ev	423 MIPS at 300 MHz	1.41	1.41	1996	[52]
Intel Pentium Pro	541 MIPS at 200 MHz	2.7	2.7	1996	[53]
Hitachi SH-4	360 MIPS at 200 MHz	1.8	1.8	1997	[54][55]
IBM-Motorola PowerPC 750	525 MIPS at 233 MHz	2.3	2.3	1997
Zilog eZ80	80 MIPS at 50 MHz	1.6	1.6	1999	[56]
Intel Pentium III	2,054 MIPS at 600 MHz	3.4	3.4	1999	[50]
Sega Naomi Multiboard (32 cores)	6,400 MIPS at 200 MHz	32	1	1999	[57]
Freescale MPC8272	760 MIPS at 400 MHz	1.9	1.9	2000	[58]
AMD Athlon	3,561 MIPS at 1.2 GHz	3.0	3.0	2000
Sony-Toshiba Emotion Engine (PS2)	6,000 MIPS at 294 MHz	20.408	2.551	2000	[59]
Silicon Recognition ZISC 78	8,600 MIPS at 33 MHz	260.6	260.6	2000	[60]
NEC SX-6 (Single Node, 8 cores)	44,208 MIPS at 500 MHz	88.416	11.052	2001	[5]
NEC SX-6 (128 Node, 1024 cores)	5,658,624 MIPS at 500 MHz	11,317.248	11.052	2001	[5]
ARM11	515 MIPS at 412 MHz	1.25	1.25	2002	[61]
NEC Earth Simulator (5120 cores)	28,293,540 MIPS at 500 MHz	56,587.08	11.052	2002	[62]
AMD Athlon XP 2500+	7,527 MIPS at 1.83 GHz	4.1	4.1	2003	[50]
Pentium 4 Extreme Edition	9,726 MIPS at 3.2 GHz	3.0	3.0	2003
Microchip PIC10F	1 MIPS at 4 MHz	0.25	0.25	2004	[63][64]
ARM Cortex-M3	125 MIPS at 100 MHz	1.25	1.25	2004	[65]
Nios II	190 MIPS at 165 MHz	1.13	1.13	2004	[66]
MIPS32 4KEc	356 MIPS at 233 MHz	1.5	1.5	2004	[67]
VIA C7	1,799 MIPS at 1.3 GHz	1.4	1.4	2005	[68]
ARM Cortex-A8	2,000 MIPS at 1.0 GHz	2.0	2.0	2005	[69]
AMD Athlon FX-57	12,000 MIPS at 2.8 GHz	4.3	4.3	2005
AMD Athlon 64 3800+ X2 (Dual core)	14,564 MIPS at 2.0 GHz	7.3	3.6	2005	[70]
ARM Cortex-R4	450 MIPS at 270 MHz	1.66	1.66	2006	[71]
MIPS32 24K	604 MIPS at 400 MHz	1.51	1.51	2006	[72]
PS3 Cell BE (PPE only)	10,240 MIPS at 3.2 GHz	3.2	3.2	2006
Xbox360 IBM "Xenon" (Triple core)	19,200 MIPS at 3.2 GHz	6.0	2.0	2005
AMD Athlon FX-60 (Dual core)	18,938 MIPS at 2.6 GHz	7.3	3.6	2006	[70]
Intel Core 2 Extreme X6800 (Dual core)	27,079 MIPS at 2.93 GHz	9.2	4.6	2006	[70]
Intel Core 2 Extreme QX6700 (Quad core)	49,161 MIPS at 2.66 GHz	18.4	4.6	2006	[73]
MIPS64 20Kc	1,370 MIPS at 600 MHz	2.3	2.3	2007	[74]
P.A. Semi PA6T-1682M	8,800 MIPS at 1.8 GHz	4.4	4.4	2007	[75]
Qualcomm Scorpion (Cortex A8-like)	2,100 MIPS at 1 GHz	2.1	2.1	2008	[61]
Intel Atom N270 (Single core)	3,846 MIPS at 1.6 GHz	2.4	2.4	2008	[76]
Intel Core 2 Extreme QX9770 (Quad core)	59,455 MIPS at 3.2 GHz	18.6	4.6	2008	[77]
Intel Core i7 920 (Quad core)	82,300 MIPS at 2.93 GHz	28.089	7.022	2008	[78]
ARM Cortex-M0	45 MIPS at 50 MHz	0.9	0.9	2009	[79]
ARM Cortex-A9 (Dual core)	7,500 MIPS at 1.5 GHz	5.0	2.5	2009	[80]
AMD Phenom II X4 940 Black Edition	42,820 MIPS at 3.0 GHz	14.3	3.5	2009	[81]
Fujitsu SPARC64 VIIIfx	113,471.314 MIPS at 2 GHz	113,471.314	7.092	2009	[59][82]
AMD Phenom II X6 1100T	78,440 MIPS at 3.3 GHz	23.7	3.9	2010	[78]
Intel Core i7 Extreme Edition 980X (Hex core)	147,600 MIPS at 3.33 GHz	44.7	7.46	2010	[83]
Tianhe-1A (186,368 cores)	2,670,000,000 MIPS at 2.93 GHz	14,326.494	4.89	2010	[59][84]
ARM Cortex A5	1,256 MIPS at 800 MHz	1.57	1.57	2011	[69]
ARM Cortex A7	2,850 MIPS at 1.5 GHz	1.9	1.9	2011	[61]
Qualcomm Krait (Cortex A15-like, Dual core)	9,900 MIPS at 1.5 GHz	6.6	3.3	2011	[61]
AMD E-350 (Dual core)	10,000 MIPS at 1.6 GHz	6.25	3.125	2011	[85]
Nvidia Tegra 3 (Quad core Cortex-A9)	13,800 MIPS at 1.5 GHz	9.2	2.5	2011
Samsung Exynos 5250 (Cortex-A15-like Dual core)	14,000 MIPS at 2.0 GHz	7.0	3.5	2011	[86]
Intel Core i5-2500K (Quad core)	83,000 MIPS at 3.3 GHz	25.152	6.288	2011	[87]
Intel Core i7 875K	92,100 MIPS at 2.93 GHz	31.4	7.85	2011	[88]
AMD FX-8150 (Eight core)	108,890 MIPS at 3.6 GHz	30.2	3.78	2011	[89][90]
Intel Core i7 2600K	117,160 MIPS at 3.4 GHz	34.45	8.61	2011	[91]
Intel Core i7 Extreme Edition 3960X (Hex core)	176,170 MIPS at 3.3 GHz	53.38	8.89	2011	[92]
Fujitsu K computer (705,024 cores)	10,000,000,000 MIPS at 2 GHz	113,471.314	7.092	2011	[59][82]
AMD FX-8350	97,125 MIPS at 4.2 GHz	23.1	2.9	2012	[90][93]
Intel Core i7 3770K	106,924 MIPS at 3.9 GHz	27.4	6.9	2012	[90]
Intel Core i7 3630QM	113,093 MIPS at 3.2 GHz	35.3	8.83	2012	[94]
Intel Core i7 4770K	133,740 MIPS at 3.9 GHz	34.29	8.57	2013	[90][93][95]
Intel Core i7 5960X	238,310 MIPS at 3.0 GHz	79.4	9.92	2014	[96]
Raspberry Pi 2	4,744 MIPS at 1.0 GHz	4.744	1.186	2014	[97]
Processor / System	Dhrystone MIPS / MIPS	D IPS / clock cycles per second	D IPS / clock cycles per second / cores per die	Year	Source

Historic data

• Computer Speeds From Instruction Mixes pre-1960 to 1971 (kIPS 175 systems)
• Computer Speed Claims 1980 to 1996 (MIPS >2000 systems)
• PC CPU Performance Comparisons %MIPS/MHz

See also

• Benchmark (computing)
• BogoMips (measurement of CPU speed made by the Linux kernel)
• Cycles per instruction
• Dhrystone (benchmark) - DMIPS integer benchmark
• FLOPS - floating-point operations per second
• Whetstone (benchmark) - floating-point benchmark
• Instructions per cycle
• Million service units (MSU)
• Orders of magnitude (computing)
• Performance per watt
• List of ARM microarchitectures

References

1. Gibson, J.C. (1970). The Gibson Mix (Technical Report TR 00.2043). Poughkeepsie, N.Y.: IBM Systems Development Division.
2. Ted MacNeil. "Don't be Misled by MIPS". IBM magazine.
3. US Steel News. 15-20. Industrial Relations Department of The United States Steel Corporation of Delaware. 1950–1955. p. 29.
4. MCS4 > IntelP4004
5. http://www.jcmit.com/cpu-performance.htm
6. http://web.archive.org/web/20120424231244/http://www.depi.itch.edu.mx/apacheco/asm/Intel_cpus.htm
7. http://www.drolez.com/retro/
8. 2 cycles per instruction
9. http://museum.ipsj.or.jp/en/computer/super/0003.html
10. http://homepage1.nifty.com/KSudou-NET/ks0D0D03.htm
11. 1 instruction per cycle
12. 4 cycles per instruction = 0.25 instructions per cycle
13. https://archive.org/stream/bitsavers_inteldataSngleComponent8BitMicrocomputerDataSheet1_846962/8048_8035_HMOS_Single_Component_8-Bit_Microcomputer_DataSheet_1980
14. http://web.archive.org/web/20120219195401/http://www.cityofberwyn.com/simulation/gameHardware/G80ref1.20.txt
15. http://www.system16.com/hardware.php?id=735
16. Sega G80: Zilog Z80 @ 8 MHz (1.16 MIPS ), 2× Intel 8035/8039 @ 3.12 MHz (6.24 MIPS )
17. 10% faster than 68000 (0.175 MIPS per MHz )
18. NEC V20/V30: 250 nanoseconds per instruction @ 8 MHz
19. Namco Pole Position: Zilog Z80 @ 3.072 (0.445 MIPS ), 2× Zilog Z8002 @ 3.072 MHz (1.536 MIPS ), 4× Fujitsu MB8843/MB8844 @ 1.54 MHz (6.16 MIPS )
20. LINKS-1 Computer Graphics System: 257× Zilog Z8001 at 10 MHz (2.5 MIPS ) each
21. http://www.ti.com/lit/ds/symlink/tms320ss16.pdf
22. MC68020 Product Summary Page
23. http://digital.hitachihyoron.com/pdf/1985/08/1985_08_05.pdf
24. http://www.datasheetarchive.com/dlmain/Datasheets-13/DSA-246134.pdf
25. 1 instruction per cycle
26. Sega System 16: Hitachi-Motorola 68000 @ 10 MHz (1.75 MIPS), NEC-Zilog Z80 @ 4 MHz (0.58 MIPS) , Intel 8751 @ 8 MHz (8 MIPS ), Intel 8048 @ 6 MHz (6 MIPS )
27. http://books.google.co.uk/books?id=KzoEAAAAMBAJ&pg=PT22
28. http://ipsj.ixsq.nii.ac.jp/ej/?action=pages_view_main&active_action=repository_view_main_item_detail&item_id=59745&item_no=1&page_id=13&block_id=8
29. http://books.google.co.uk/books?id=KU7dCBpP7fsC&pg=PA130
30. MC68030 Product Summary Page
31. http://tronweb.super-nova.co.jp/tronvlsicpu.html
32. http://historyofracinggames.files.wordpress.com/2007/06/060-1987-drivers-eyes-1989-winning-run.pdf
33. http://pdf.datasheetcatalog.com/datasheet/analogdevices/ADSP-2100KG.pdf
34. Namco System 21 hardware: 5× Texas Instruments TMS320C20 @ 25 MHz (62.5 MIPS ), 2× Motorola 68000 @ 12.288 MHz (4.301 MIPS ), Motorola 68020 @ 12.5 MHz (3.788 MIPS ), Hitachi HD63705 @ 2.048 MHz (2.048 MIPS ), Motorola 6809 @ 3.072 MHz (1.29 MIPS )
35. http://alacron.com/index.php?src=gendocs&ref=Inteli860_basedBusBoardsFT_200_VME&category=news
36. Atari Hard Drivin' hardware: Motorola 68000 @ 7 MHz (1.225 MIPS ), Motorola 68010 @ 7 MHz (1.348 MIPS ), 3× Texas Instruments TMS34010 @ 50 MHz (18 MIPS ), Analog Devices ADSP-2100 @ 8 MHz (8 MIPS ), Texas Instruments TMS32010 @ 20 MHz (5 MIPS )
37. http://www.degruyter.com/dg/viewarticle/j$002fpiko.1990.13.issue-4$002fpiko.1990.13.4.205$002fpiko.1990.13.4.205.xml;jsessionid=2928071D864D5E4F9045C8A209E7AA94
38. http://www.top500.org/system/170813
39. MC68040 Product Summary Page
40. Namco System 21 (Galaxian³) hardware: 80× Texas Instruments TMS320C25 @ 40 MHz (1600 MIPS ), 5× Motorola 68020 @ 24.576 MHz (37.236 MIPS ) Motorola 68000 @ 12.288 MHz (2.15 MIPS ), 10× Motorola 68000 @ 12 MHz (21 MIPS )
41. http://books.google.co.uk/books?id=sc0wyeolS8cC&pg=PA97
42. Digital's 21064 Microprocessor, Digital Equipment Corporation (c1992) accessdate=2009-08-29
43. http://www.system16.com/hardware.php?id=832
44. http://dl.acm.org/citation.cfm?id=623816
45. http://www.netlib.org/performance/html/dhrystone.data.col0.html
46. 24× MIPS R4400 (2040 MIPS), 12× Intel i860 (600 MIPS)
47. http://museum.ipsj.or.jp/en/computer/super/0020.html
48. http://www.fujitsu.com/global/Images/fujitsu-contribution-to-hpc.pdf
49. http://www.segatech.com/technical/saturnspecs/
50. Tomshardware Cpu chart 2004
51. PIC16F84A
52. http://www.fermimn.gov.it/inform/materiali/evarchi/motorola/603e_fs.pdf
53. SiSoftware Zone
54. http://www.segatech.com/technical/cpu/
55. http://www.segatech.com/archives/january1998.html
56. "Zilog Sees New Lease of Life for Z80 in Internet Appliances". Computergram International. 1999.
57. Sega Naomi Multiboard hardware: 16× Hitachi SH-4 at 200 MHz (5760 MIPS ), 16× ARM7 at 45 MHz (640 MIPS )
58. Freescale Semiconductor - MPC8272 PowerQUICC II Processor Family
59. http://www.frc.ri.cmu.edu/~hpm/book97/ch3/processor.list.txt
60. http://www.datasheetarchive.com/ZISC78-datasheet.html
61. Anandtech ARM Cortex A7 architecture comparison
62. NEC Earth Simulator: 5,120× NEC SX-6 at 500 MHz (28,293,540 MIPS)
63. PIC10F200
64. Microchip Technology Debuts Industry’s First 6-Pin Microcontrollers: The World’s Smallest Microcontroller
65. ARM Cortex-M3
66. Nios II Performance Benchmarks
68. mini-itx.com - epia px 10000 review
69. ARM Cortex-A Series Comparison
70. CPU Charts 2007 - Tom's Hardware
71. Cortex-R4 Processor
72. [http://www.mips.com/products/cores/32-64-bit-cores/mips32-24k/ MIPS32 24K]
73. Synthetics, Continued - Tom's Hardware : Intel's Core 2 Quadro Kentsfield: Four Cores on a Rampage
74. Design Reuse - needs free registration
75. Merritt, Rick (5 February 2007). "Startup takes PowerPC to 25 W". EE Times. UBM Tech. Retrieved 20 November 2012.
76. OC Workbench
77. Synthetic - Sandra CPU - Tom's Hardware : Intel Core 2 Extreme QX9770: Paper Tiger?
78. Tom's Hardware Cpu Charts 2010
79. Cortex-M0 Processor
80. EEE Journal
81. XtremeSystems Member Synthetic - Sandra CPU
82. K computer: 88,128× Fujitsu SPARC64 VIIIfx @ 2 GHz each
83. Overclock3D - Sandra CPU
84. http://www.top500.org/system/176929
85. Tom's Hardware
86. Samsung Exynos 5250 Announcement
87. http://www.guru3d.com/articles-pages/core-i5-2500k-and-core-i7-2600k-review,13.html
88. Tom's Hardware - Desktop CPU Charts 2011: Sandra 2010 Pro ALU
89. HardOCP Bulldozer Desktop Performance - Synthetic Benchmarks
90. http://www.cpu-world.com/benchmarks/browse/910_80,965_61,993_80,1035_96/?c_test=6&PROCESS=Show+Selected
91. Tom's Hardware - Benchmark Results: Synthetics
92. HardOCP - Synthetic Benchmarks
93. http://versus.com/en/amd-fx-8350-black-edition-vs-intel-core-i7-4770k
94. - Notebookcheck
95. http://www.notebookcheck.net/Intel-Core-i7-Desktop-4770K-Notebook-Processor.93553.0.html
96. http://techgage.com/print/core-i7-5960x-extreme-edition-review-intels-overdue-desktop-8-core-is-here/
97. http://hackaday.com/2015/02/05/benchmarking-the-raspberry-pi-2/