PGA Processor

PGA Processor

The Motorola 68020 is a 32-bit microprocessor from Motorola, released in 1984. It is the successor to the Motorola 68010 and is succeeded by the Motorola 68030.

Description
The 68020 (usually just referred to as the '020, pronounced oh-two-oh or oh-twenty) had 32-bit internal and external data and address buses. A lower cost version, the 68EC020, only had a 24-bit address bus. The 68020 was produced at speeds ranging from 12 MHz to 33 MHz.

Improvements over 68010
The 68020 added many improvements to the 68010 including a 32-bit arithmetic logic unit (ALU), external data bus and address bus, and new instructions and addressing modes. The 68020 (and 68030) had a proper three-stage pipeline.
The alignment restriction on word and longword data access present in its predecessors was removed with the 68020.

Multiprocessing features
The Motorola multiprocessing model was added with the 68020. This allowed up to eight processors per system to co-operate, these eight could be any number of CPUs, FPUs but a single MMU (either a Motorola 68841 or 68851). This had some limitation, as each CPU used had to be the same model (not necessarily the same clock) and each FPU has to be the same model (again, not necessarily the same clock) so multiprocessing a 68020/25 with a 68030/25 was not allowed (the 020, for example, could not be aware of the 030's internal MMU) but a 68020/25 with a 68882/33 was perfectly acceptable and quite common. It was, however, extremely uncommon to see more than one CPU or FPU in the same system. Most Unix boxes made with 68020s were simply the '020, an FPU (68881 or 68882) and an MMU (68841 or 68851).

Instruction set
The new instructions included some minor improvements and extensions to the supervisor state, several instructions for software management of a multiprocessing system (which were removed in the 68060), some support for high-level languages which did not get used much (and was removed from future 680x0 processors), bigger multiply (32×32→64 bits) and divide (64÷32→32 bits quotient and 32 bits remainder) instructions, and bit field manipulations.

Addressing modes
The new addressing modes added scaled indexing and another level of indirection to many of the pre-existing modes, and added quite a bit of flexibility to various indexing modes and operations. Though it was not intended, these new modes made the 68020 very suitable for page printing; most laser printers in the early '90s had a 68EC020 at their core.
The 68020 had a minimal 256 byte direct-mapped instruction cache, arranged as 64 four-byte entries. Although small, it still made a significant difference in the performance of many applications. The resulting decrease in bus traffic was particularly important in systems relying heavily on DMA.

Usage
The 68020 was used in the Apple Macintosh II and Macintosh LC personal computers, as well as Sun 3 workstations and the Hewlett Packard 8711 Series Network Analyzers. The Commodore Amiga 1200 computer and the Amiga CD32 games console used the cost-reduced 68EC020.
It is also the processor used on board TGV trains to decode signalling information which is sent to the trains through the rails, and is the CPU of the computers in the Eurofighter Typhoon.
For more information on the instructions and architecture see Motorola 68000.

Land grid array (LGA)

The land grid array (LGA) is a type of surface-mount packaging used for integrated circuits. It can be electrically connected to a PCB either by the use of a socket or by soldering directly to the PCB.

Use in Microprocessors
The LGA is used as a physical interface for microprocessors of the Intel Pentium 4 and AMD Opteron families. Unlike the pin grid array (PGA) interface found on most AMD and Intel processors, there are no pins on the chip; in place of the pins are pads of bare gold-plated copper that touch pins on the motherboard.
LGA processor sockets include Socket F (also called Socket 1207) from AMD[1] and the Prescott core Pentium 4 and Xeon chip systems with the new model number system from Intel.
The Intel desktop LGA socket is dubbed Socket 775 or Socket T while the server variant is dubbed Socket J or Socket 771. Intel supposedly decided to switch to an LGA socket because it provides a larger contact point, allowing, for example, higher clock frequencies. The LGA setup provides higher pin densities, allowing more power contacts and thus a more stable power supply to the chip. Motherboard vendors have complained that LGA packaging was introduced solely to move the burden of bent pin problems from Intel to the electronics vendors.[citation needed]
Similar to Intel, AMD decided to use an LGA socket because it allows higher pin densities. The required size of a 1207-pin PGA would simply be too large and would consume too much space on motherboards.
Intel released its new LGA format processors in June 2004 and recently displayed plans to transition its Xeon processors to LGAs. AMD released its Socket F LGA Opteron in 2nd quarter 2006.

Casing System
Introduction
This document is written for professional system integrators building PCs from industry-accepted motherboards, chassis, and peripherals. It provides information and recommendations for thermal management in desktop systems using boxed Intel® Pentium® III, Pentium® II processors, and Celeron® processors. (The term "boxed processors" refers to processors packaged for use by system integrators.)
It is assumed that the reader has a general knowledge of and experience with desktop PC operation, integration, and thermal management. Integrators who follow the recommendations presented here can provide their customers with more reliable PCs and will see fewer customers returning with problems.
Thermal Management
Systems using boxed processors all require thermal management. The term "thermal management" refers to two major elements: a heatsink properly mounted to the processor, and effective airflow through the system chassis. The ultimate goal of thermal management is to keep the processor at or below its maximum operating temperature.
Proper thermal management is achieved when heat is transferred from the processor to the system air, which is then vented out of the system. Desktop boxed processors are shipped with a high-quality fan heatsink, which can effectively transfer processor heat to the system air. It is the responsibility of the system integrator to ensure adequate system airflow.
This document makes recommendations for achieving good system airflow and provides suggestions for improving the effectiveness of a system's thermal management solution.
Fan Heatsink
Boxed processors are shipped in several processor packages;
the Single Edge Contact Cartridge (S.E.C.C.)
the Single Edge Contact Cartridge 2 (S.E.C.C.2)
the Single Edge Processor Package (S.E.P.P.)
and the Plastic Pin Grid Array (PPGA)
All boxed processors for desktop systems are shipped with a fan heatsink and fan power cable. These items should be used following the directions contained within the boxed processor installation notes included in the processor box. Thermal interface material (already applied) provides effective heat transfer from the processor to the fan heatsink. S.E.C.C., S.E.C.C.2, and S.E.P.P. boxed processors ship with an attached fan heatsink with the thermal interface material included between the processor and the fan heatsink. Current PPGA boxed processors ship with an unattached fan heatsink that includes thermal interface material on the fan heatsink base and a fan cable incorporated into the fan. The fan cable provides power to the fan by connecting to a motherboard-mounted power header. Some boxed processor fan heatsinks provide fan speed information to the motherboard. (Only motherboards with hardware monitoring circuitry can use the fan speed signal.)
Boxed processors use high-quality ball-bearing fans that provide a good local air stream. This local air stream transfers heat from the heatsink to the air inside the system. However, moving heat to the system air is only half the task. Sufficient system airflow is also needed in order to exhaust the air. Without a steady stream of air through the system, the fan heatsink will re-circulate warm air, and therefore may not cool the processor adequately.
System Airflow
System airflow is determined by:
Chassis design
Chassis size
Location of chassis air intake and exhaust vents
Power supply fan capacity and venting
Location of the processor slot(s)
Placement of add-in cards and cables
System integrators must ensure airflow through the system to allow the fan heatsink to work effectively. Proper attention to airflow when selecting subassemblies and building PCs is important for good thermal management and reliable system operation.
Integrators use three basic chassis form factors for desktop systems: ATX, microATX, and the older Baby AT form factor.
In systems using Baby AT components, airflow is usually from front to back. Air enters the chassis from vents at the front and is drawn through the chassis by the power supply fan. The power supply fan exhausts the air through the back of the chassis. Figure 1 and Figure 2 show the airflow through Baby AT systems.

Figure 1. System Airflow Through Baby AT Desktop Chassis (Top View)

Figure 2. System Airflow Through Baby AT Tower Chassis (Side View)
Intel recommends the use of ATX and microATX form factor motherboards and chassis for boxed processors. The ATX and microATX form factors simplify assembly and upgrading of desktop systems, while improving the consistency of airflow to the processor.
With regard to thermal management, ATX components differ from Baby AT components in that the processor is located close to the power supply, rather than to the front panel of the chassis. Power supplies that blow air out of the chassis provide proper airflow for active fan heatsinks. The boxed processor's active fan heatsink cools the processor more effectively when combined with an exhausting power supply fan. Because of this, the airflow in systems using the boxed processor should flow from the front of the chassis, directly across the motherboard and processor, and out of the power supply exhaust vents. Figure 3 shows proper airflow through an ATX system to achieve the most effective cooling for a boxed processor with an active fan heatsink. For boxed processors, chassis that conform to the ATX Specification Revision 2.01 or later are highly recommended. For more information on the ATX form factor, and a list of ATX chassis manufacturers, please visit the ATX web site †.

Figure 3. System Airflow Through ATX Tower Chassis Optimized For the Boxed Processor With an Active Fan Heatsink
One of the ways microATX chassis differ from ATX chassis is that the power supply location and type may vary. Thermal management improvements that apply to ATX chassis will also apply to microATX. For more information on the microATX form factor, and a list of microATX chassis manufacturers, please visit the microATX website †.
The following is a list of guidelines to be used when integrating a system. Specific mention of Baby AT, ATX, or microATX components is made where necessary.

Cooling system

Introduction
This document is written for professional system integrators building PCs from industry-accepted motherboards, chassis, and peripherals. It provides information and recommendations for thermal testing on systems using desktop boxed processors.
Thermal testing should be done on new system configurations built with boxed processors. Two evaluation methods are detailed here that apply to several desktop boxed processors. Each boxed processor has a thermal management application note that has specific information pertinent to the processor. Together, the specific boxed processor thermal management application note and this document will enable a system integrator to thermally evaluate a system configuration. A third document entitled System Thermal Management for Boxed Intel Processor-Based Desktop PCs has information about building systems with quality thermal management and improving thermal management in systems that have insufficient airflow.
Thermal Management
Systems using boxed processors all require thermal management. The term "thermal management" refers to two major elements: a heatsink properly mounted to the processor, and effective airflow through the system chassis. The ultimate goal of thermal management is to keep the processor at or below its maximum operating temperature.
Proper thermal management is achieved when heat is transferred from the processor to the system air, which is then vented out of the system. Boxed processors are shipped with a high-quality fan heatsink, which can effectively transfer processor heat to the system air. It is the responsibility of the system integrator to ensure adequate system airflow.
This document provides procedures for determining the effectiveness of a system's thermal management solution. The temperature specifications for Intel processors are documented in the processor datasheets that are available from the developer's website. A thermal metrology is also documented for each processor. The metrology describes how to properly test the processor to ensure that the processor never exceeds its maximum specified temperature. Most thermal metrologies for current processors require drilling heatsinks, soldering wires to baseboards, and the purchase of outside equipment. This document details two methods for evaluating the representative system's thermal management. These evaluations do not validate that the processor specification will never be exceeded, but can provide confidence in the system's ability to provide the proper internal environment for the boxed processor.
Before testing the system, it is important to evaluate the conditions that the system will operate under. An important condition to consider is the maximum ambient temperature that the system will be specified to operate under. Many large Original Equipment Manufacturers (OEMs) specify the maximum ambient temperature specification to be 35°C (95°F). In areas without air conditioning, 40°C (104°C) may be more appropriate. System integrators should choose a value that is appropriate for their customers and specify that maximum operating temperature to the customer.
Integrated Fan Heatsink
Boxed processors are shipped with a fan heatsink and fan power cable. These items should be used following the directions in the installation notes shipped with the boxed processor box. Below are drawings of the desktop boxed processor in each of the processor packages.

Plastic Pin Grid Array (PPGA)

Single Edge Processor Package (S.E.P.P.)
Fans used on boxed processors are high-quality ball bearing fans that provide a good local air stream. This local air stream transfers heat from the heatsink to the air inside the system. However, moving heat to the system air is only half the task. Sufficient system airflow is also needed to exhaust the air. Without a steady stream of air through the system, the fan heatsink will re-circulate warm air, and therefore may not cool the processor adequately.
A common feature on all desktop boxed processors is the fan inlet. This circular area on each heatsink has a hologram in the center, and openings that allow air to flow into the fan center and out the sides of the fan heatsink. The temperature of the air entering the fan inlet is a critical factor in cooling the boxed processor. Measuring the temperature of the air entering the fan inlet can determine if the boxed processor fan heatsink is able keep the processor temperature within its operating range. To determine the recommended maximum ambient air temperature for a specific processor, see the thermal management document for that specific product.
The boxed processor fan heatsinks all have metal bases that allow for quick heat transfer. The temperature of the heatsink base at a specified location can also be used to determine if the boxed processor fan heatsink is able to keep the processor within specification. Since the processor heatsink geometry changes as the form factor varies, the exact location of the test point will be documented in the thermal management application note for the specific processor.

Latest Buses

PCI Express Connector Manufacturers
PCIe uses 4 different sizes of connector, all of which are card-edge type to accept a PCI Express card using card-edge fingers spaced on a 1.00mm pitch [0.394 inches]. The 1x size is the smallest with 36 contact positions. The x4 uses 64 contacts, the x8 uses 98 contacts, and the x16 has 164 contact positions. The nominal height of the connector above the PWB is 11mm. The width of the 1x and 16x connector is 8.70mm as shown below, how ever the 1x graphic is shown slightly larger.

Introduction
The processor communicates with other peripherals in the PC through a path of data called bus. Since the release of the first PC, in 1981, up to the present day, several types of bus have been developed in order to allow the communication between the processor and input and output peripherals. We can name the following buses already launched:
=>ISA
=>EISA
=>MCA
=>VLB
=>PCI
=>AGP
PCI Express
The main difference among the several types of bus is in the number of bits that can be transmitted at a time, and in the operating frequency used. Nowadays the two fastest types of PC expansion bus are the PCI and the AGP. We listed the transfer rate of those buses in the chart below. The PCI-X bus is an extension of the PCI bus designed to the market of network servers.

The PCI bus was released by Intel in June, 1992. Since then, almost all PC expansion peripherals, such as hard disks, sound cards, LAN cards, and video cards have been using the PCI bus. The thing is, the PCI bus maximum transfer rate - 133 MB/s – proved to be insufficient for modern 3D applications and it represented a limitation to the development of more sophisticated video cards. In order to solve that issue, Intel created a new bus, called AGP, to increase the transfer rate of video cards – now they wouldn’t have to be installed in the PCI bus anymore, but in the AGP bus, which is faster. Then the PCI was not so “busy” anymore, since video cards were the great responsible for the intense traffic in the PCI bus.

AMD vs. Intel Processors
There now exists only two major brands of central processing units (CPUs): Intel and AMD. AMD, by the way, stands for Advanced Micro Devices. The difference between the two processor brands is sometimes hard to see, as each has its own line, and even give such vital statistics, such as processor speed, in different terms. It can be difficult sometimes to simply compare an AMD processor and an Intel processor. Typically, AMD has produced cheaper alternatives to the Intel processor line. But the big question is, has this come at a cost of performance? In the processor industry, just as in any other, it is likely that you get what you pay for. Nonetheless, here we take a look at some AMD and Intel products and try to figure out a comparative cost to performance ratio.

Pentium 4 Extreme Edition vs. AMD Athlon FX 64

To compare the companies as fairly as possible, lets take a look at two of the newest processors by each, and compare the speed to cost ratio. The newest processor by AMD is the AMD Athlon FX 64-bit processor. AMD claims that this processor gives you "leading-edge performance and unparalleled technology with its simultaneous 32-bit and 64-bit computing." 64-bit processing is certainly a new development, and one that is perhaps long overdue. This chip is really something to behold, and hints that AMD is going to be in this battle for quite sometime. Some of the nice features of the FX include a 128-bit integrated DDR memory controller (up to 6.4GB/sec memory bandwidth for breakthrough performance and extraordinary cinematic computing experiences) and HyperTransport technology (much like Intel's hyperthreading), which provides "increased bandwidth and reduced I/O bottlenecks for increased system performance and better multitasking." You can purchase one of these processors for about $800 or so, if you look hard enough. You will find that their "core operating speeds" are about 2.6GHZ or so max.

Intel's latest chip is the Pentium 4 extreme edition. This processor is also very impressive with about a 3.2GHZ core operating speed. Like the most recent p4s before it, the Pentium 4 extreme edition comes with Hyper-Threading technology. However, it also comes with a hefty 800 MHz system bus and its major distinction from previous versions: a L3 cache at 2 MB, which is integrated into the chip and runs at the processor core clock speed. Another interesting architectual note is that the Pentium 4 extreme has 170 mln transistors, compared with the 104 mln found on the Athlon FX. This processor currently sells for about $1000 - a bit more expensive.
The cost to speed ratios for the Pentium 4 extreme edition and the AMD Athlon FX are actually very similar. Deciding which processor to spend your hard earned money on depends more upon what you actually plan on using your computer for. After various trials, it was found that the Pentium 4 extreme does better - overall - with gaming programs like Doom 3 and AntiPlanet. However, if you aren't a big gamer, you could probably save yourself some money going with the FX, and not really seeing any difference in application performance. In fact, you may even find that some games work better with Athlon FX. It really seems that AMD, with its new 64-bit processor, really has put out some stiff competition for Intel and the Pentium line.

Comments

Processor speed: Intel Pentium Dual Core vs. AMD Turion?
I know the processor speed isn't the only thing to look at, but if they have the same memory and hard drive space, are both of these processors powerful? Does one outdo the other? I'm looking at Intel Pentium Dual Core (T2060 or T2080) and AMD Turion 64 X2 Dual-Core TL-50. I'm not a gamer, but I do muti-task with many web and Word windows.

Victor C Lopez Jr.

Leah Mae Evan

Rhea Mae Sanguer

Warren Andojar

John Angelo Genzola

Jemmar Paron

Jayson Villasor

Cesar Ryan Bondoc

group 3 IT-213

The History of Intel

Intel was founded on July 18, 1968 with one main goal in mind: to make semiconductor memory more practicle. Intels first microprocessor, the 4004 microcomputer, was released at the end of 1971. The chip was smaller then a thumbnail, contained 2300 transistors, and was capable of executing 60,000 operations in one second. Shortly after the release of th 4004 the 8008 microcomputer was released and was capable of executing twice as many operations per second then the 4004. Intels commitment to the microprocessor led to IBM's choice of Intel's 8088 chip for the CPU of the its first PC. In 1982, Intel introduced the first 286 chip, it contained 134,000 transistors and provided around three times the performance of the other microprocessors at the time. In 1989 the 486 processor was released that contained 1.2 million transistors and the first built in math coprocessor. The chip was approximately 50 times faster then Intels original 4004 processor and equaled the performance of a powerful mainframe computer. In 1993 Intel introduced the Pentium processor, which was five times as fast as the 486, it contained 3.1 million transistors, and was capable of 90 million instructions per second (MIPS). In 1995 Intel introduced its new technology, MMX, MMX was designed to enhance the computers multimedia performance. Throughout the years that followed Intel released several lines of processors including the Celeron, the P2, P3, and P4. Intel processors now reach speeds upwards of 2200 MHZ or 2.2 GHZ.

Intel founder: Silicon Valley no longer unique
By Robert McMillan

The region that gave birth to such legendary high technology startups as Apple Computer Inc., Hewlett-Packard Co. and Cisco Systems Inc. may be seeing some of its influence wane, Gordon Moore, one of the founders of Intel Corp., said Wednesday.

Though Silicon Valley was once unparalleled as the natural home of high technology startups, things have changed in the nearly 40 years since Moore, along with Robert Noyce and Andy Grove founded Intel. "It's uniqueness is not as great as it was in the beginning. Other areas have picked up on the technology," Moore said of the region. "Now it's spread around to a lot of other places."

China, for example, is fast rising as a technology player, he said. "We have very formidable competition in the world. I think the impact of China is just beginning to be felt," he said. "China is training 10 times as many engineers. ... Their technology is catching up fairly rapidly. It's a very entrepreneurial society."

Chief among the challenges ahead for Silicon Valley is the relative weakness of the U.S. public education system, which Moore characterized as a problem for the entire country, and the San Francisco Bay Area's notoriously high cost of living, both which are making it harder to attract top workers. "It's so damned expensive, especially the housing. It's hard to move young people in."

The median price paid for a Bay Area home was US$534,000 in January, according to real estate research firm DataQuick Information Systems Inc.

But Moore did express a qualified faith in both the region and the country that had given birth to his company. "Silicon Valley is still a great place to start a company," he said. "I expect the U.S. will still be a successful player, but I don't think it will enjoy the position it's had in the past 20 years."

Moore's comments came Wednesday, at a press event to honor the 40th anniversary of the April 1965 Electronics magazine article that first articulated Moore's famous law on the rate of growth in the chip industry. Originally, a somewhat obscure prediction that the number of components on an integrated circuit would continue to double every year, Moore's Law has come to be regarded as an article of faith in an industry that has defined itself with rapid growth. In 1975, Moore updated his law to predict that components would double every two years.

Though he was at first embarrassed that his observation had become an industry rule -- "it was (in) a McGraw Hill publication that we described as one of the throwaway journals," he said Wednesday -- Moore eventually grew more comfortable with his status as a lawmaker. "Gradually, I got to accept it. It was shorthand for showing what the technology allowed you to do."

With the dimensions of chip components now being measured in atoms, it seems that the ability of engineers to keep doubling the number of transistors they put on chips may now be in jeopardy. But on Wednesday, Moore warned against writing off his famous maxim before its time. "I've never been able to see more than two or three (product) generations ahead without seeing something that appeared to be an impenetrable barrier there," he said.

For example, the 90 nanometer process technology commonly used by chipmakers today once seemed an impossibility, Moore said. "I remember the time that I thought 1 micron was probably going to be the limit," he said. "It wasn't a barrier at all." There are 1,000 nm in a micron, which represents one millionth of a meter.

Though Moore stopped short Wednesday of predicting that his law would hold for another 40 years, he pointed out that it has continually defied a more pessimistic maxim. "Moore's Law is a violation of Murphy's Law," he said. "Everything gets better as you make things smaller."

Moore's Law

The term Moore's Law was coined by Carver Mead around 1970.^[4] Moore's original statement can be found in his publication "Cramming more components onto integrated circuits", Electronics Magazine 19 April 1965:

“

The complexity for minimum component costs has increased at a rate of roughly a factor of two per year ... Certainly over the short term this rate can be expected to continue, if not to increase. Over the longer term, the rate of increase is a bit more uncertain, although there is no reason to believe it will not remain nearly constant for at least 10 years. That means by 1975, the number of components per integrated circuit for minimum cost will be 65,000. I believe that such a large circuit can be built on a single wafer.[1]

”

Under the assumption that chip "complexity" is proportional to the number of transistors, regardless of what they do, the law has largely held the test of time to date. However, one could argue that the per-transistor complexity is less in large RAM cache arrays than in execution units. From this perspective, the validity of one formulation of Moore's Law may be more questionable.

Gordon Moore's observation was not named a "law" by Moore himself, but by the Caltech professor, VLSI pioneer, and entrepreneur Carver Mead.^[2] Moore, indicating that it cannot be sustained indefinitely, has since observed "It can't continue forever. The nature of exponentials is that you push them out and eventually disaster happens."^[5]

Moore may have heard Douglas Engelbart, a co-inventor of today's mechanical computer mouse, discuss the projected downscaling of integrated circuit size in a 1960 lecture.^[6] In 1975, Moore projected a doubling only every two years. He is adamant that he himself never said "every 18 months", but that is how it has been quoted. The SEMATECH roadmap follows a 24 month cycle.

In April 2005, Intel offered $10,000 to purchase a copy of the original Electronics Magazine.^[7]

[edit] Understanding Moore's Law

Moore's law is not about just the density of transistors that can be achieved, but about the density of transistors at which the cost per transistor is the lowest[1]. As more transistors are made on a chip the cost to make each transistor reduces but the chance that the chip will not work due to a defect rises. If the rising cost of discarded non working chips is balanced against the reducing cost per transistor of larger chips, then as Moore observed in 1965 there is a number of transistors or complexity at which "a minimum cost" is achieved. He further observed that as transistors were made smaller through advances in photolithography this number would increase "a rate of roughly a factor of two per year".^[1]

[edit] Formulations of Moore's Law

PC hard disk capacity (in GB). The plot is logarithmic, so the fit line corresponds to exponential growth.

The most popular formulation is of the doubling of the number of transistors on integrated circuits every 18 months. At the end of the 1970s, Moore's Law became known as the limit for the number of transistors on the most complex chips. However, it is also common to cite Moore's Law to refer to the rapidly continuing advance in computing power per unit cost, because increase in transistor count is also a rough measure of computer processing power. On this basis, the power of computers per unit cost - or more colloquially, "bangs per buck" - doubles every 24 months (or, equivalently, increases 32-fold in 10 years).

A similar law (sometimes called Kryder's Law) has held for hard disk storage cost per unit of information.^[8] The rate of progression in disk storage over the past decades has actually sped up more than once, corresponding to the utilization of error correcting codes, the magnetoresistive effect and the giant magnetoresistive effect. The current rate of increase in hard drive capacity is roughly similar to the rate of increase in transistor count. However, recent trends show that this rate is dropping, and has not been met for the last three years. See Hard disk capacity.

Another version states that RAM storage capacity increases at the same rate as processing power.

Pixels per dollar based on Australian recommended retail price of Kodak digital cameras

Similarly, Barry Hendy of Kodak Australia has plotted the "pixels per dollar" as a basic measure of value for a digital camera, demonstrating the historical linearity (on a log scale) of this market and the opportunity to predict the future trend of digital camera price and resolution.

Due to the mathematical power of exponential growth (similar to the financial power of compound interest), seemingly minor fluctuations in the relative growth rates of CPU performance, RAM capacity, and disk space per dollar have caused the relative costs of these three fundamental computing resources to shift markedly over the years, which in turn has caused significant changes in programming styles. For many programming problems, the developer has to decide on numerous time-space tradeoffs, and throughout the history of computing these choices have been strongly influenced by the shifting relative costs of CPU cycles versus storage space.

Amdahl's law

Jump to: navigation, search

The speedup of a program using multiple processors in parallel computing is limited by the sequential fraction of the program. For example, if 0.5 portion of the program is sequential, the theoretical maximum speedup using parallel computing would be 2 as shown in the diagram no matter how many processors are used. i.e. (1/(0.5+(1-0.5)/N)) when N is very big

Amdahl's law, named after computer architect Gene Amdahl, is used to find the maximum expected improvement to an overall system when only part of the system is improved. It is often used in parallel computing to predict the theoretical maximum speedup using multiple processors.

The generalized Amdahl's law is:

where

• is a percentage of the instructions that can be improved (or slowed),
• is the speed-up multiplier (where 1 is no speed-up and no slowing),
• represents a label for each different percentage and speed-up, and
• is the number of different speed-up/slow-downs resulting from the system change.

Description

Amdahl's law is a formula that computes the expected speedup of parallelized implementations of an algorithm relative to the non-parallelized algorithm. For example, if a parallelized implementation of an algorithm can run 12% of the algorithm's operations arbitrarily fast (while the remaining 88% of the operations are not parallelizable), Amdahl's law states that the maximum speedup of the parallelized version is times faster than the non-parallelized implementation.

More technically, the law is concerned with the speedup achievable from an improvement to a computation that affects a proportion P of that computation where the improvement has a speedup of S. (For example, if an improvement can speed up 30% of the computation, P will be 0.3; if the improvement makes the portion affected twice as fast, S will be 2). Amdahl's law states that the overall speedup of applying the improvement will be

.

To see how this formula was derived, assume that the running time of the old computation was 1, for some unit of time. The running time of the new computation will be the length of time the unimproved fraction takes, (which is 1 − P), plus the length of time the improved fraction takes. The length of time for the improved part of the computation is the length of the improved part's former running time divided by the speedup, making the length of time of the improved part P/S. The final speedup is computed by dividing the old running time by the new running time, which is what the above formula does.

Here's another example. We are given a task which is split up into four parts: P1 = .11 or 11%, P2 = .18 or 18%, P3 = .23 or 23%, P4 = .48 or 48%, which add up to 100%. Then we say P1 is not sped up, so S1 = 1 or 100%, P2 is sped up 5x, so S2 = 5 or 500%, P3 is sped up 20x, so S3 = 20 or 2000%, and P4 is sped up 1.6x, so S4 = 1.6 or 160%. By using the formula , we find the running time is or a little less than ½ the original running time which we know is 1. Therefore the overall speed boost is or a little more than double the original speed using the formula . Notice how the 20x and 5x speedup don't have much effect on the overall speed boost and running time when over half of the task is only sped up 1x, (i.e. not sped up), or 1.6x.

Victor Lopez Jr.

Jayson Villasor

Rhea Mae Sanguer

Leah Mae Evan

Warren Andojar

Liwayway Gerolaga

Cesar Ryan Bondoc

Karlmax Pacifico

John Angelo Genzola