Las instrucciones por segundo ( IPS ) son una medida de la velocidad del procesador de una computadora . Para computadoras con conjuntos de instrucciones complejos (CISC), las diferentes instrucciones toman diferentes cantidades de tiempo, por lo que el valor medido depende de la combinación de instrucciones; incluso para comparar procesadores de la misma familia, la medición IPS puede ser problemática. Muchos valores de IPS reportados han representado tasas de ejecución "máximas" en secuencias de instrucciones artificiales con pocas ramificaciones y sin contención de caché , mientras que las cargas de trabajo realistas generalmente conducen a valores de IPS significativamente más bajos. Jerarquía de memoriatambién afecta en gran medida el rendimiento del procesador, un problema que apenas se considera en los cálculos de IPS. Debido a estos problemas, los puntos de referencia sintéticos como Dhrystone ahora se utilizan generalmente para estimar el rendimiento de la computadora en aplicaciones de uso común, y el IPS en bruto ha caído en desuso.
El término se usa comúnmente en asociación con un prefijo métrico (k, M, G, T, P o E) para formar kiloinstrucciones por segundo ( kIPS ), millones de instrucciones por segundo ( MIPS ) y mil millones de instrucciones por segundo ( GIPS). ) y así. Anteriormente, TIPS se usaba ocasionalmente para "miles de ips".
Computación [ editar ]
IPS se puede calcular usando esta ecuación: [1]
Sin embargo, la medición de instrucciones / ciclo depende de la secuencia de instrucción, los datos y factores externos.
Mil instrucciones por segundo (TIPS / kIPS) [ editar ]
Antes de los puntos de referencia estándar estaban disponibles, la calificación promedio de velocidad de los ordenadores se basa en los cálculos para una mezcla de instrucciones con los resultados dados en kilo instrucciones por segundo (kips). La más famosa fue la Gibson Mix , [2] producida por Jack Clark Gibson de IBM para aplicaciones científicas en 1959. Otras clasificaciones, como la mezcla ADP, que no incluye operaciones de coma flotante, se produjeron para aplicaciones comerciales. La unidad de mil instrucciones por segundo (kIPS) rara vez se usa en la actualidad, ya que la mayoría de los microprocesadores actuales pueden ejecutar al menos un millón de instrucciones por segundo.
La mezcla de Gibson [ editar ]
Gibson dividió las instrucciones de la computadora en 12 clases, basadas en la arquitectura IBM 704 , agregando una decimotercera clase para tener en cuenta el tiempo de indexación. Los pesos se basaron principalmente en el análisis de siete programas científicos ejecutados en el 704, con una pequeña contribución de algunos programas de IBM 650 . El puntaje general fue entonces la suma ponderada de la velocidad de ejecución promedio de las instrucciones en cada clase. [3]
La mezcla de Gibson | % |
---|---|
1. Cargas y almacenamiento | 31,2 |
2. Suma y resta de punto fijo | 6.1 |
3. Compara | 3.8 |
4. Sucursales | 16.6 |
5. Suma y resta flotante | 6,9 |
6. Multiplicar flotante | 3.8 |
7. División flotante | 1,5 |
8. Multiplicación de punto fijo | 0,6 |
9. División de punto fijo | 0,2 |
10. Cambio | 4.4 |
11. Lógico, Y, O, etc. | 1,6 |
12. Instrucciones que no utilizan registros | 5.3 |
13. Indexación | 18 |
Total | 100 |
Millones de instrucciones por segundo (MIPS) [ editar ]
La velocidad de una CPU determinada depende de muchos factores, como el tipo de instrucciones que se ejecutan, el orden de ejecución y la presencia de instrucciones de bifurcación (problemático en las canalizaciones de la CPU). Las tasas de instrucción de la CPU son diferentes de las frecuencias de reloj, generalmente expresadas en Hz , ya que cada instrucción puede requerir varios ciclos de reloj para completarse o el procesador puede ser capaz de ejecutar múltiples instrucciones independientes simultáneamente. MIPS puede ser útil al comparar el rendimiento entre procesadores fabricados con una arquitectura similar (por ejemplo, microcontroladores de la marca Microchip), pero son difíciles de comparar entre diferentes arquitecturas de CPU . [4] Esto llevó a que el término "índices de rendimiento sin sentido" fuera popular entre los técnicos a mediados de la década de 1980.[5]
Por esta razón, MIPS se ha convertido no en una medida de la velocidad de ejecución de instrucciones, sino en la velocidad del desempeño de la tarea en comparación con una referencia. A finales de la década de 1970, se comparó el rendimiento de la minicomputadora mediante VAX MIPS , donde las computadoras se midieron en una tarea y su rendimiento se calificó con el VAX 11/780 que se comercializaba como una máquina 1 MIPS . (La medida también se conocía como la Unidad de rendimiento VAX o VUP .) Se eligió porque el 11/780 era aproximadamente equivalente en rendimiento a un IBM System / 370 modelo 158-3, que se aceptaba comúnmente en la industria de la computación como en ejecución a 1 MIPS.
Muchas afirmaciones sobre el rendimiento de las minicomputadoras se basaron en la versión de Fortran del punto de referencia Whetstone , lo que proporciona millones de instrucciones por segundo de Whetstone (MWIPS). El VAX 11/780 con FPA (1977) funciona a 1.02 MWIPS.
Las velocidades efectivas de MIPS dependen en gran medida del lenguaje de programación utilizado. El Informe Whetstone tiene una tabla que muestra las velocidades MWIPS de las PC a través de los primeros intérpretes y compiladores hasta los lenguajes modernos. El primer compilador de PC fue para BASIC (1982) cuando una CPU 8088/87 de 4.8 MHz obtuvo 0.01 MWIPS. Los resultados en un Intel Core 2 Duo de 2.4 GHz (1 CPU 2007) varían de 9.7 MWIPS usando BASIC Interpreter, 59 MWIPS a través del compilador BASIC, 347 MWIPS usando 1987 Fortran, 1,534 MWIPS a través de HTML / Java a 2,403 MWIPS usando un moderno compilador C / C ++ .
Para la mayoría de los primeros microprocesadores de 8 y 16 bits , el rendimiento se midió en mil instrucciones por segundo (1000 kIPS = 1 MIPS).
zMIPS se refiere a la medida MIPS utilizada internamente por IBM para calificar sus servidores mainframe ( zSeries , IBM System z9 e IBM System z10 ).
Millones de operaciones ponderadas por segundo (WMOPS) es una medida similar, utilizada para códecs de audio.
Cronología de instrucciones por segundo [ editar ]
Procesador / Sistema | Dhrystone MIPS o MIPS y frecuencia | D IPS por ciclo de reloj | D IPS por ciclo de reloj por núcleo | Año | Fuente |
---|---|---|---|---|---|
UNIVAC I | 0,002 MIPS a 2,25 MHz | 0,0008 | 0,0008 | 1951 | [6] |
IBM 7030 ("Estirar") | 1.200 MIPS a 3.30 MHz | 0.364 | 0.364 | 1961 | [7] [8] |
CDC 6600 | 10,00 MIPS a 10,00 MHz | 1 | 1 | 1965 | [9] [10] |
Intel 4004 | 0.092 MIPS at 0.740 MHz (Not Dhrystone) | 0.124 | 0.124 | 1971 | [11] |
IBM System/370 Model 158 | 0.640 MIPS at 8.696 MHz | 0.0736 | 0.0736 | 1972 | [12] |
Intel 8080 | 0.290 MIPS at 2.000 MHz (Not Dhrystone) | 0.145 | 0.145 | 1974 | [13] |
Cray 1 | 160.0 MIPS at 80.00 MHz | 2 | 2 | 1975 | [14] |
MOS Technology 6502 | 0.430 MIPS at 1.000 MHz | 0.43 | 0.43 | 1975 | [15] |
Intel 8080A | 0.435 MIPS at 3.000 MHz (Not Dhrystone) | 0.145 | 0.145 | 1976 | [13] |
Zilog Z80 | 0.580 MIPS at 4.000 MHz (Not Dhrystone) | 0.145 | 0.145 | 1976 | [15] |
Motorola 6802 | 0.500 MIPS at 1.000 MHz | 0.5 | 0.5 | 1977 | [16] |
IBM System/370 Model 158-3 | 0.730 MIPS at 8.696 MHz | 0.0839 | 0.0839 | 1977 | [12] |
VAX-11/780 | 1.000 MIPS at 5.000 MHz | 0.2 | 0.2 | 1977 | [12] |
Motorola 6809 | 0.420 MIPS at 1.000 MHz | 0.42 | 0.42 | 1978 | [15] |
Intel 8086 | 0.330 MIPS at 5.000 MHz | 0.066 | 0.066 | 1978 | [13] |
Fujitsu MB8843 | 2.000 MIPS at 2.000 MHz (Not Dhrystone) | 1 | 1 | 1978 | [17] |
Intel 8088 | 0.750 MIPS at 10.00 MHz | 0.075 | 0.075 | 1979 | [13] |
Motorola 68000 | 1.400 MIPS at 8.000 MHz | 0.175 | 0.175 | 1979 | [15] |
Zilog Z8001/Z8002 | 1.5 MIPS at 6 MHz | 0.25 | 0.25 | 1979 | [18] |
Intel 8035/8039/8048 | 6 MIPS at 6 MHz (Not Dhrystone) | 1 | 1 | 1980 | [19] |
Fujitsu MB8843/MB8844 | 6 MIPS at 6 MHz (Not Dhrystone) | 1 | 1 | 1980 | [17] |
Zilog Z80/Z80H | 1.16 MIPS at 8 MHz (Not Dhrystone) | 0.145 | 0.145 | 1981 | [15][20] |
Motorola 6802 | 1.79 MIPS at 3.58 MHz | 0.5 | 0.5 | 1981 | [16][21] |
Zilog Z8001/Z8002B | 2.5 MIPS at 10 MHz | 0.25 | 0.25 | 1981 | [18] |
MOS Technology 6502 | 2.522 MIPS at 5.865 MHz | 0.43 | 0.43 | 1981 | [15][21] |
Intel 286 | 1.28 MIPS at 12 MHz | 0.107 | 0.107 | 1982 | [12] |
Motorola 68000 | 2.188 MIPS at 12.5 MHz | 0.175 | 0.175 | 1982 | [15] |
Motorola 68010 | 2.407 MIPS at 12.5 MHz | 0.193 | 0.193 | 1982 | [22] |
NEC V20 | 4 MIPS at 8 MHz (Not Dhrystone) | 0.5 | 0.5 | 1982 | [23] |
LINKS-1 Computer Graphics System (257-processor) | 642.5 MIPS at 10 MHz | 2.5 | 0.25 | 1982 | [24] |
Texas Instruments TMS32010 | 5 MIPS at 20 MHz | 0.25 | 0.25 | 1983 | [25] |
NEC V30 | 5 MIPS at 10 MHz (Not Dhrystone) | 0.5 | 0.5 | 1983 | [23] |
Motorola 68010 | 3.209 MIPS at 16.67 MHz | 0.193 | 0.193 | 1984 | [22] |
Motorola 68020 | 4.848 MIPS at 16 MHz | 0.303 | 0.303 | 1984 | [26] |
Hitachi HD63705 | 2 MIPS at 2 MHz | 1 | 1 | 1985 | [27][28] |
Intel i386DX | 2.15 MIPS at 16 MHz | 0.134 | 0.134 | 1985 | [12] |
Hitachi-Motorola 68HC000 | 3.5 MIPS at 20 MHz | 0.175 | 0.175 | 1985 | [15] |
Intel 8751 | 1 MIPS at 12 MHz | 0.083 | 0.083 | 1985 | [29] |
Sega System 16 (4-processor) | 16.33 MIPS at 10 MHz | 4.083 | 1.020 | 1985 | [30] |
ARM2 | 4 MIPS at 8 MHz | 0.5 | 0.5 | 1986 | [31] |
Texas Instruments TMS34010 | 6 MIPS at 50 MHz | 0.12 | 0.12 | 1986 | [32] |
NEC V70 | 6.6 MIPS at 20 MHz | 0.33 | 0.33 | 1987 | [33] |
Motorola 68030 | 9 MIPS at 25 MHz | 0.36 | 0.36 | 1987 | [34][35] |
Gmicro/200 | 10 MIPS at 20 MHz | 0.5 | 0.5 | 1987 | [36] |
Texas Instruments TMS320C20 | 12.5 MIPS at 25 MHz | 0.5 | 0.5 | 1987 | [37] |
Analog Devices ADSP-2100 | 12.5 MIPS at 12.5 MHz | 1 | 1 | 1987 | [38] |
Texas Instruments TMS320C25 | 25 MIPS at 50 MHz | 0.5 | 0.5 | 1987 | [37] |
Motorola 68020 | 10 MIPS at 33 MHz | 0.303 | 0.303 | 1988 | [26] |
Motorola 68030 | 18 MIPS at 50 MHz | 0.36 | 0.36 | 1988 | [35] |
Namco System 21 (10-processor) | 73.927 MIPS at 25 MHz | 2.957 | 0.296 | 1988 | [39] |
Intel i386DX | 4.3 MIPS at 33 MHz | 0.13 | 0.13 | 1989 | [12] |
Intel i486DX | 8.7 MIPS at 25 MHz | 0.348 | 0.348 | 1989 | [12] |
NEC V80 | 16.5 MIPS at 33 MHz | 0.5 | 0.5 | 1989 | [33] |
Intel i860 | 25 MIPS at 25 MHz | 1 | 1 | 1989 | [40] |
Atari Hard Drivin' (7-processor) | 33.573 MIPS at 50 MHz | 0.671 | 0.0959 | 1989 | [41] |
NEC SX-3 (4-processor) | 680 MIPS at 400 MHz | 1.7 | 0.425 | 1989 | [42] |
ARM3 | 12 MIPS at 25 MHz | 0.5 | 0.5 | 1989 | [43] |
Motorola 68040 | 44 MIPS at 40 MHz | 1.1 | 1.1 | 1990 | [44] |
Namco System 21 (Galaxian³) (96-processor) | 1,660.386 MIPS at 40 MHz | 41.51 | 0.432 | 1990 | [45] |
AMD Am386 | 9 MIPS at 40 MHz | 0.225 | 0.225 | 1991 | [46] |
Intel i486DX | 11.1 MIPS at 33 MHz | 0.336 | 0.336 | 1991 | [12] |
Intel i860 | 50 MIPS at 50 MHz | 1 | 1 | 1991 | [40] |
Intel i486DX2 | 25.6 MIPS at 66 MHz | 0.388 | 0.388 | 1992 | [12] |
Alpha 21064 | 86 MIPS at 150 MHz | 0.573 | 0.573 | 1992 | [12] |
Alpha 21064 | 135 MIPS at 200 MHz | 0.675 | 0.675 | 1993 | [12][47] |
MIPS R4400 | 85 MIPS at 150 MHz | 0.567 | 0.567 | 1993 | [48] |
Gmicro/500 | 132 MIPS at 66 MHz | 2 | 2 | 1993 | [49] |
IBM-Motorola PowerPC 601 | 157.7 MIPS at 80 MHz | 1.971 | 1.971 | 1993 | [50] |
SGI Onyx RealityEngine2 (36-processor) | 2,640 MIPS at 150 MHz | 17.6 | 0.489 | 1993 | [51] |
Namco Magic Edge Hornet Simulator (36-processor) | 2,880 MIPS at 150 MHz | 19.2 | 0.533 | 1993 | [48] |
ARM7 | 40 MIPS at 45 MHz | 0.889 | 0.889 | 1994 | [52] |
Intel DX4 | 70 MIPS at 100 MHz | 0.7 | 0.7 | 1994 | [13] |
Motorola 68060 | 110 MIPS at 75 MHz | 1.33 | 1.33 | 1994 | |
Intel Pentium | 188 MIPS at 100 MHz | 1.88 | 1.88 | 1994 | [53] |
Microchip PIC16F | 5 MIPS at 20 MHz | 0.25 | 0.25 | 1995 | [54] |
IBM-Motorola PowerPC 603e | 188 MIPS at 133 MHz | 1.414 | 1.414 | 1995 | [55] |
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 | [55] |
Intel Pentium Pro | 541 MIPS at 200 MHz | 2.7 | 2.7 | 1996 | [56] |
Hitachi SH-4 | 360 MIPS at 200 MHz | 1.8 | 1.8 | 1997 | [57][58] |
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 | [59] |
Intel Pentium III | 2,054 MIPS at 600 MHz | 3.4 | 3.4 | 1999 | [53] |
Sega Naomi Multiboard (32-processor) | 6,400 MIPS at 200 MHz | 32 | 1 | 1999 | [60] |
Freescale MPC8272 | 760 MIPS at 400 MHz | 1.9 | 1.9 | 2000 | [61] |
AMD Athlon | 3,561 MIPS at 1.2 GHz | 3.0 | 3.0 | 2000 | |
Silicon Recognition ZISC 78 | 8,600 MIPS at 33 MHz | 260.6 | 260.6 | 2000 | [62] |
ARM11 | 515 MIPS at 412 MHz | 1.25 | 1.25 | 2002 | [63] |
AMD Athlon XP 2500+ | 7,527 MIPS at 1.83 GHz | 4.1 | 4.1 | 2003 | [53] |
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 | [64][65] |
ARM Cortex-M3 | 125 MIPS at 100 MHz | 1.25 | 1.25 | 2004 | [66] |
Nios II | 190 MIPS at 165 MHz | 1.13 | 1.13 | 2004 | [67] |
MIPS32 4KEc | 356 MIPS at 233 MHz | 1.5 | 1.5 | 2004 | [68] |
VIA C7 | 1,799 MIPS at 1.3 GHz | 1.4 | 1.4 | 2005 | [69] |
ARM Cortex-A8 | 2,000 MIPS at 1.0 GHz | 2.0 | 2.0 | 2005 | [70] |
AMD Athlon FX-57 | 12,000 MIPS at 2.8 GHz | 4.3 | 4.3 | 2005 | |
AMD Athlon 64 3800+ X2 (2-core) | 14,564 MIPS at 2.0 GHz | 7.3 | 3.6 | 2005 | [71] |
PowerPC G4 MPC7448 | 3,910 MIPS at 1.7 GHz | 2.3 | 2.3 | 2005 | [72] |
ARM Cortex-R4 | 450 MIPS at 270 MHz | 1.66 | 1.66 | 2006 | [73] |
MIPS32 24K | 604 MIPS at 400 MHz | 1.51 | 1.51 | 2006 | [74] |
PS3 Cell BE (PPE only) | 10,240 MIPS at 3.2 GHz | 3.2 | 3.2 | 2006 | |
IBM Xenon CPU (3-core) | 19,200 MIPS at 3.2 GHz | 6.0 | 2.0 | 2005 | |
AMD Athlon FX-60 (2-core) | 18,938 MIPS at 2.6 GHz | 7.3 | 3.6 | 2006 | [71] |
Intel Core 2 Extreme X6800 (2-core) | 27,079 MIPS at 2.93 GHz | 9.2 | 4.6 | 2006 | [71] |
Intel Core 2 Extreme QX6700 (4-core) | 49,161 MIPS at 2.66 GHz | 18.4 | 4.6 | 2006 | [75] |
MIPS64 20Kc | 1,370 MIPS at 600 MHz | 2.3 | 2.3 | 2007 | [76] |
P.A. Semi PA6T-1682M | 8,800 MIPS at 1.8 GHz | 4.4 | 4.4 | 2007 | [77] |
Qualcomm Scorpion (Cortex A8-like) | 2,100 MIPS at 1 GHz | 2.1 | 2.1 | 2008 | [63] |
Intel Atom N270 | 3,846 MIPS at 1.6 GHz | 2.4 | 2.4 | 2008 | [78] |
Intel Core 2 Extreme QX9770 (4-core) | 59,455 MIPS at 3.2 GHz | 18.6 | 4.6 | 2008 | [75] |
Intel Core i7 920 (4-core) | 82,300 MIPS at 2.93 GHz | 28.089 | 7.022 | 2008 | [79] |
ARM Cortex-M0 | 45 MIPS at 50 MHz | 0.9 | 0.9 | 2009 | [80] |
ARM Cortex-A9 (2-core) | 7,500 MIPS at 1.5 GHz | 5.0 | 2.5 | 2009 | [81] |
AMD Phenom II X4 940 Black Edition | 42,820 MIPS at 3.0 GHz | 14.3 | 3.5 | 2009 | [82] |
AMD Phenom II X6 1100T | 78,440 MIPS at 3.3 GHz | 23.7 | 3.9 | 2010 | [79] |
Intel Core i7 Extreme Edition 980X (6-core) | 147,600 MIPS at 3.33 GHz | 44.7 | 7.46 | 2010 | [83] |
ARM Cortex A5 | 1,256 MIPS at 800 MHz | 1.57 | 1.57 | 2011 | [70] |
ARM Cortex A7 | 2,850 MIPS at 1.5 GHz | 1.9 | 1.9 | 2011 | [63] |
Qualcomm Krait (Cortex A15-like, 2-core) | 9,900 MIPS at 1.5 GHz | 6.6 | 3.3 | 2011 | [63] |
AMD E-350 (2-core) | 10,000 MIPS at 1.6 GHz | 6.25 | 3.125 | 2011 | [84] |
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 2-core) | 14,000 MIPS at 2.0 GHz | 7.0 | 3.5 | 2011 | [85] |
Intel Core i5-2500K (4-core) | 83,000 MIPS at 3.3 GHz | 25.152 | 6.288 | 2011 | [86] |
Intel Core i7 875K | 92,100 MIPS at 2.93 GHz | 31.4 | 7.85 | 2011 | [79] |
AMD FX-8150 (8-core) | 90,749 MIPS at 3.6 GHz | 25.2 | 3.15 | 2011 | [87] |
Intel Core i7 2600K | 117,160 MIPS at 3.4 GHz | 34.45 | 8.61 | 2011 | [88] |
Intel Core i7-3960X | 176,170 MIPS at 3.3 GHz | 53.38 | 8.89 | 2011 | [89] |
AMD FX-8350 | 97,125 MIPS at 4.2 GHz | 23.1 | 2.9 | 2012 | [87][90] |
AMD FX-9590 | 115,625 MIPS at 5.0 GHz | 23.1 | 2.9 | 2012 | [79] |
Intel Core i7 3770K | 106,924 MIPS at 3.9 GHz | 27.4 | 6.9 | 2012 | [87] |
Intel Core i7 4770K | 133,740 MIPS at 3.9 GHz | 34.29 | 8.57 | 2013 | [87][90][91] |
Intel Core i7 5960X | 298,190 MIPS at 3.5 GHz | 85.2 | 10.65 | 2014 | [92] |
Raspberry Pi 2 | 4,744 MIPS at 1.0 GHz | 4.744 | 1.186 | 2014 | [93] |
Intel Core i7 6950X | 320,440 MIPS at 3.5 GHz | 91.55 | 9.16 | 2016 | [94] |
ARM Cortex A73 (4-core) | 71,120 MIPS at 2.8 GHz | 25.4 | 6.35 | 2016 | |
ARM Cortex A75 | ? | ? | 8.2-9.5 | 2017 | [95] |
ARM Cortex A76 | ? | ? | 10.7-12.4 | 2018 | [95] |
ARM Cortex A77 | ? | ? | ? | 2019 | |
ARM Cortex A78 | ? | ? | ? | 2020 | |
AMD Ryzen 7 1800X | 304,510 MIPS at 3.7 GHz | 82.3 | 10.29 | 2017 | [96] |
Intel Core i7-8086K | 221,720 MIPS at 5.0 GHz | 44.34 | 7.39 | 2018 | [97] |
Intel Core i9-9900K | 412,090 MIPS at 4.7 GHz | 87.68 | 10.96 | 2018 | [98] |
AMD Ryzen 9 3950X | 749,070 MIPS at 4.6 GHz | 162.84 | 10.18 | 2019 | [98] |
AMD Ryzen Threadripper 3990X | 2,356,230 MIPS at 4.35 GHz | 541.66 | 8.46 | 2020 | [99] |
Processor / System | Dhrystone MIPS / MIPS | D IPS per clock cycle | D IPS per clock cycle per core | Year | Source |
See also[edit]
- TOP500
- FLOPS - floating-point operations per second
- SUPS
- Benchmark (computing)
- BogoMips (measurement of CPU speed made by the Linux kernel)
- Instructions per cycle
- Cycles per instruction
- Dhrystone (benchmark) - DMIPS integer benchmark
- Whetstone (benchmark) - floating-point benchmark
- Million service units (MSU)
- Orders of magnitude (computing)
- Performance per watt
- Data-rate units
References[edit]
- ^ US, Dell. "Technical Resources migrated from TechCenter - Dell US". en.community.dell.com.
- ^ Gibson, J.C. (1970). The Gibson Mix (Technical Report TR 00.2043). Poughkeepsie, N.Y.: IBM Systems Development Division.
- ^ Elliot, Jimmie Lynn (June 5, 1975). "Appendix E, The Gibson Mix by Jack C. Gibson". Computer Performance and Evaluation Utilizating the Resource Planing and Management System, Masters Thesis. Oregon State University. pp. 88–92. Retrieved March 21, 2021.
- ^ Ted MacNeil. "Don't be Misled by MIPS". IBM magazine. Archived from the original on 2012-08-17. Retrieved 2009-11-15.
- ^ "The Best of Both Worlds: Mac II vs. IBM PS/2 Model 80". PC Magazine. November 24, 1987. p. 105.
- ^ US Steel News. 15–20. Industrial Relations Department of The United States Steel Corporation of Delaware. 1950–1955. p. 29.
- ^ Padua, David (2011-09-08). Encyclopedia of Parallel Computing. Springer Science & Business Media. ISBN 9780387097657.
- ^ Meagher, R.E. (May 9, 1961). "STRETCH Report" (PDF). Computer History.
- ^ "Control Data Corporation, CDC-6600 & 7600". ed-thelen.org. Retrieved 2017-05-25.
- ^ "Control Data 6600: The Supercomputer Arrives". Dr. Dobb's. Archived from the original on 2017-06-05. Retrieved 2017-05-25.
- ^ "MCS4 > IntelP4004".
- ^ a b c d e f g h i j k "Cost of CPU Performance Through Time 1944-2003". Archived from the original on 2014-10-09.
- ^ a b c d e "Intel Processors". 24 April 2012. Archived from the original on 2012-04-24.
- ^ "History of Computers and Computing, Birth of the modern computer, Electronic computer, Cray computers of Seymour Cray". history-computer.com. Retrieved 2017-05-25.
- ^ a b c d e f g h Drolez, Ludovic. "Lud's Open Source Corner".
- ^ a b 2 cycles per instruction [1]
- ^ a b 1 instruction per cycle [2]
- ^ a b 4 cycles per instruction [3] Archived 2015-06-09 at the Wayback Machine = 0.25 instructions per cycle
- ^ "intel :: dataSheets :: 8048 8035 HMOS Single Component 8-Bit Microcomputer DataSheet 1980".
- ^ "Sega G80 Hardware Reference". 25 October 1997. Archived from the original on 2012-02-19.
- ^ a b "System 16 - Irem M27 Hardware (Irem)".
- ^ a b 10% faster [4] than 68000 (0.175 MIPS per MHz [5])
- ^ a b NEC V20/V30: "250 nanoseconds per instruction @ 8 MHz" means some fastest 2-clock register-register instructions only
- ^ LINKS-1 Computer Graphics System: 257× Zilog Z8001 [6] at 10 MHz [7] (2.5 MIPS [8] Archived 2015-06-09 at the Wayback Machine) each
- ^ "TMS320C1x DIGITAL SIGNAL PROCESSORS" (PDF). Archived from the original (PDF) on 2014-10-06.
- ^ a b "32-Bit Microprocessor-NXP".
- ^ "ZTAT (ZeroTurnAroundTime) Microcomputers" (PDF). Archived from the original (PDF) on October 6, 2014.
- ^ http://www.datasheetarchive.com/dlmain/Datasheets-13/DSA-246134.pdf[permanent dead link]
- ^ 1 instruction per cycle [9]
- ^ Sega System 16: Hitachi-Motorola 68000 @ 10 MHz (1.75 MIPS), NEC-Zilog Z80 @ 4 MHz (0.58 MIPS) [10] [11], Intel 8751 @ 8 MHz [12] (8 MIPS [13]), Intel 8048 @ 6 MHz "Archived copy". Archived from the original on 2016-01-25. Retrieved 2016-08-08.CS1 maint: archived copy as title (link) (6 MIPS [14])
- ^ "ARM2 - Microarchitectures - Acorn". Wikichip.org. Retrieved 17 October 2018.
- ^ Inc, InfoWorld Media Group (23 January 1989). "InfoWorld". InfoWorld Media Group, Inc. – via Google Books.
- ^ a b 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
- ^ Inc, Ziff Davis (24 November 1987). "PC Mag". Ziff Davis, Inc. – via Google Books.
- ^ a b "Enhanced 32-Bit Processor-NXP".
- ^ "TRON VLSI CPU Introduction".
- ^ a b "060 1987 Drivers Eyes + 1989 Winning Run" (PDF). The history of racing games. June 2007.
- ^ "Analog Devices - datasheet pdf" (PDF).
- ^ Namco System 21 hardware: 5× Texas Instruments TMS320C20 @ 25 MHz (62.5 MIPS [15]), 2× Motorola 68000 @ 12.288 MHz [16] (4.301 MIPS [17]), Motorola 68020 [18] @ 12.5 MHz (3.788 MIPS [19]), Hitachi HD63705 @ 2.048 MHz [20] (2.048 MIPS [21]), Motorola 6809 @ 3.072 MHz [22] (1.29 MIPS [23])
- ^ a b "Intel i860-based Bus Boards". Archived from the original on 2013-06-25.
- ^ Atari Hard Drivin' hardware: [24] Motorola 68000 @ 7 MHz (1.225 MIPS [25]), Motorola 68010 @ 7 MHz (1.348 MIPS [26]), 3× Texas Instruments TMS34010 @ 50 MHz (18 MIPS [27]), Analog Devices ADSP-2100 @ 8 MHz (8 MIPS [28]), Texas Instruments TMS32010 @ 20 MHz (5 MIPS "Archived copy" (PDF). Archived from the original (PDF) on 2014-10-06. Retrieved 2014-09-17.CS1 maint: archived copy as title (link))
- ^ "SUPERCOMPUTER". Pik - Praxis der Informationsverarbeitung und Kommunikation. 13 (4). 1990. doi:10.1515/piko.1990.13.4.205.
- ^ "ARM3 - Microarchitectures - Acorn". Wikichip.org. Retrieved 17 October 2018.
- ^ "(Including EC, LC, and V)-NXP".
- ^ Namco System 21 (Galaxian³) hardware: [29] 80× Texas Instruments TMS320C25 @ 40 MHz (1600 MIPS [30]), 5× Motorola 68020 @ 24.576 MHz (37.236 MIPS [31]) Motorola 68000 @ 12.288 MHz (2.15 MIPS [32]), 10× Motorola 68000 @ 12 MHz (21 MIPS [33])
- ^ Enterprise, I. D. G. (25 March 1991). "Computerworld". IDG Enterprise – via Google Books.
- ^ Digital's 21064 Microprocessor, Digital Equipment Corporation[permanent dead link] (c1992) accessdate=2009-08-29
- ^ a b "System 16 - Namco Magic Edge Hornet Simulator Hardware (Namco)".
- ^ Uchiyama, Kunio; Arakawa, Fumio; Narita, Susumu; Aoki, Hirokazu; Kawasaki, Ikuya; Matsui, Shigezumi; Yamamoto, Mitsuyoshi; Nakagawa, Norio; Kudo, Ikuo (1 September 1993). "The Gmicro/500 Superscalar Microprocessor with Branch Buffers". IEEE Micro. 13 (5): 12–22. doi:10.1109/40.237998. S2CID 30178249.
- ^ "dhrystone".
- ^ 24× MIPS R4400 (2040 MIPS), [34] 12× Intel i860 (600 MIPS) "Archived copy". Archived from the original on 2013-06-25. Retrieved 2014-09-17.CS1 maint: archived copy as title (link)
- ^ "DCTP - Saturn Specifications". Archived from the original on 2003-03-01.
- ^ a b c "Charts, benchmarks CPU Charts 2004, Sandra - CPU Dhrystone". Archived from the original on 2013-02-05.
- ^ "PIC16F84A - 8-bit PIC Microcontrollers".
- ^ a b "MOTOROLA P OWER PC 603 E ™ MICROPROCESSOR" (PDF). Archived from the original (PDF) on 2014-09-18. Retrieved 2014-09-17.
- ^ "SiSoftware – Windows, GPGPU, Android, iOS analysers, diagnostic and benchmarking apps".
- ^ "DCTP - Hitachi's 200 MHz SH-4". Archived from the original on 2014-12-11. Retrieved 2014-09-18.
- ^ "DCTP - January 1998 News Archives". Archived from the original on 2016-03-05.
- ^ "Zilog Sees New Lease of Life for Z80 in Internet Appliances". Computergram International. 1999. Archived from the original on 2012-05-25.
- ^ Sega Naomi Multiboard hardware: [35] [36] Archived 2014-10-06 at the Wayback Machine 16× Hitachi SH-4 at 200 MHz (5760 MIPS [37] Archived 2014-12-11 at the Wayback Machine), 16× ARM7 at 45 MHz (640 MIPS [38])
- ^ "Freescale Semiconductor - MPC8272 PowerQUICC II Processor Family" (PDF). Archived from the original (PDF) on 2012-02-18. Retrieved 2008-05-13.
- ^ "ZISC78 datasheet & application note - Datasheet Archive".
- ^ a b c d Shimpi, Anand Lal. "ARM's Cortex A7: Bringing Cheaper Dual-Core & More Power Efficient High-End Devices".
- ^ "PIC10F200 - 8-bit PIC Microcontrollers".
- ^ "Microchip Redirect". Archived from the original on 2014-10-06.
- ^ "Cortex-M3 Processor - ARM".
- ^ "Nios II Performance Benchmarks" (PDF).
- ^ "MIPS Architecture Enabling Growing List of Mobile Application Processors".
- ^ "mini-itx.com - epia px 10000 review".
- ^ a b "Cortex-A Series - ARM".
- ^ a b c "Charts, benchmarks CPU Charts 2007, Synthetic SiSoft Sandra XI CPU". Archived from the original on 2013-02-04.
- ^ "MPC7448: RISC Microprocessor".
- ^ "Cortex-R4 Processor - ARM".
- ^ 24K[permanent dead link]
- ^ a b "Tom's Hardware Articles - Find and Filter Our Latest Articles".
- ^ "Semiconductor IP Cores Companies".
- ^ Merritt, Rick (5 February 2007). "Startup takes PowerPC to 25 W". EE Times. UBM Tech. Archived from the original on 21 January 2013. Retrieved 20 November 2012.
- ^ "Benchmarks of ECS 945GCT-D with Intel Atom 1.6GHz".
- ^ a b c d "Charts, benchmarks Desktop CPU Charts 2010, ALU Performance: SiSoftware Sandra 2010 Pro (ALU)". Archived from the original on 2013-02-04.
- ^ "Cortex-M0 Processor - ARM".
- ^ "EEE Journal: ARM11 vs Cortex A8 vs Cortex A9 - Netbooks processors EEE PC, MSI Wind, HP, Acer Aspire, ARM Cortex vs Intel Atom". Archived from the original on 2011-07-19.
- ^ "The Phenom II List of Overclocks - Page 21".
- ^ "OC3D :: Review :: Intel 980x Gulftown :: Synthetic Benchmarks".
- ^ "Benchmark Results: Sandra 2011 - ASRock's E350M1: AMD's Brazos Platform Hits The Desktop First". 14 January 2011.
- ^ "Samsung Semiconductor Global Official Website".
- ^ "Core i5 2500K and Core i7 2600K review".
- ^ a b c d "Test: Sandra Dhrystone (MIPS) for i7-4770K, i7-3770K, FX-8350, FX-8150".
- ^ "Benchmark Results: SiSoftware Sandra 2011 - The Intel Core i7-990X Extreme Edition Processor Review". 25 February 2011.
- ^ "HardOCP - Synthetic Benchmarks".
- ^ a b "AMD FX-8350 Black Edition vs Intel Core i7-4770K - Compare CPUs".
- ^ "Intel Core i7-4770K Desktop Processor".
- ^ Rob Williams (August 29, 2014). "Core i7-5960X Extreme Edition Review: Intel's Overdue Desktop 8-Core Is Here". Techgage.
- ^ By (2015-02-05). "Benchmarking The Raspberry Pi 2". hackaday.com.
- ^ ccokeman (May 30, 2016). "Intel Core I7 6950X Extreme Edition Broadwell-E CPU Review".
- ^ a b http://users.nik.uni-obuda.hu/sima/letoltes/Processor_families_Knowledge_Base_2019/ARM_processors_lecture_2018_12_02.pdf
- ^ Chiappetta, Marco (2017-03-02). "AMD Ryzen 7 1800X, 1700X, And 1700 Review And Benchmarks: Zen Brings The Fight Back To Intel". HotHardware. Archived from the original on 2017-03-05. Retrieved 2017-03-05.
- ^ "Details for Component Intel Core i7-8086K". SiSoftware Official Live Ranker.
- ^ a b Marco Chiappetta (14 November 2019). "AMD Ryzen 9 3950X Review: A 16-Core Zen 2 Powerhouse". HotHardware. Archived from the original on 6 March 2020. Retrieved 22 March 2020.
- ^ Marco Chiappetta (7 February 2020). "AMD Threadripper 3990X Review: A 64-Core Multithreaded Beast Unleashed". HotHardware. Archived from the original on 18 March 2020. Retrieved 22 March 2020.