What is 64-bit Computing?
64-bit Addressing
A 64-bit processor, with 64-bit registers and a 64-bit integer data path, has the ability to address considerably more memory than a 32-bit processor, with 32-bit registers and a 32-bit integer data path. A 32-bit processor provides flat addressing of up to 232 32-bit bytes, or about 4GB of memory. In contrast, a 64-bit processor provides flat addressing for 264 64-bit bytes, or 18 billion GB (18 Exabytes) of memory. Scalability increases associated with 64 bits are dramatic and can be illustrated by the following example:
64-bit Integer Arithmetic
In a 64-bit CPU, integer arithmetic provides greater performance and precision. Since most compilers support 64-bit data types, even on 32-bit CPUs, the main benefit for integer arithmetic is increased performance on larger data types.
64-bit Operating System
A true 64-bit operating system uses the 64-bit addressing and arithmetic capabilities of the CPU to provide more system resources to you and your applications. 64-bit operating systems allow larger files, and more files, user IDs, shared library segments, and other resources than a 32-bit operating system. There is not a significant performance penalty for this increased scalability, because 64-bit operating systems are using the native capabilities of the 64-bit CPU.
64-bit Applications
64-bit applications take advantage of the 64-bit capabilities of the CPU and operating system. Depending on the application, these may include the 64-bit addressing and arithmetic capabilities of the CPU, as well as increased system resources provided by the operating system.
There are many elements involved in 64-bit computing, including addressing, integer arithmetic, operating systems and applications.
The Benefits of 64-bit Computing
Increased Scalability
The main benefit of 64-bit computing is increased scalability of your computer and applications. Some applications simply do not fit into a 32-bit computing model. For example, limitations on file size in a 32-bit environment may require database systems to use multiple files to represent a single file. Applications requiring large files, a large number of files, or a large number of users benefit from 64-bit computing.
Increased Performance
Any application that is outgrowing a 32-bit computing environment suffers performance hits. Applications may need large files, large memory, high precision arithmetic, and/or algorithmic accommodations for 32-bit limitations. Applications needing more code or data in memory will benefit from decreased swapping with 64-bit computing. Reduced swapping can make database inquiries as much as 100 times faster (individual performance gains may vary).
The following table summarizes the sources of increases in performance and scalability associated with 64-bit computing by type of application:
64-bit Computing in Perspective
64-bit computing is essential for applications that must make use of the increased scalability and performance of a 64-bit OS. However, most high-end computing needs are met with 32-bit applications on a 32-bit OS. HP is providing both 32-bit and 64-bit versions of HP-UX, so you can choose the operating environment that best meets your needs. Since both 32-bit and 64-bit versions of HP-UX run on the 64-bit HP PA-RISC processors, you can upgrade from 32-bit HP-UX to 64-bit HP-UX when your requirements change.
Most 32-bit applications perform better compiled as a 32-bit binary, because more of the application binary fits in the computer's cache. When a 32-bit application is recompiled for 64 bits, the 64-bit binary is typically larger than its 32-bit binary. With a given cache size available on a system, performance may actually decline because of a greater number of cache misses when running the 64-bit binary.
Whether your needs are for 32-bit or 64-bit computing on HP-UX, HP workstations can fulfill your requirements.
HP-UX 11i v1 Tackles 32-bit and 64-bit Applications
With HP's introduction of the robust 64-bit HP-UX 11i v1 operating system, you can now run 32-bit and 64-bit applications without modifying the configuration. This new OS is a boon to designers who traditionally work with large data sets (> 4 GBs) and require the addressability of a 64-bit system, yet still use some 32-bit applications. It's important to note that if you don't need the expanded address space that 64-bit applications provide, you may choose to run 32-bit versions of your applications; they often run faster than 64-bit versions.
The new HP Workstation c8000 runs HP-UX 11i v1 and accepts up to 32 GBs of RAM enabling outstanding performance and interactivity on 64-bit applications. Whether your job requires 32-bit applications, 64-bit applications, or both, you can enjoy full performance on the HP Workstation c8000.
To learn more about the HP c8000, visit www.hp.com/go/workstations.
Where Electronics Meet 3-D Wire Harness Design (Advertorial by Zuken)
****************Advertorial*********************
Back in the "good old days" of automotive electronics, designing the wiring harness was simple: a paper sketch, some 'rule-of-thumb' estimates of current carrying capacity and wire diameter, and perhaps a check of the initial calculations with the aid of a mechanical model and a piece of string. This was the accepted "design flow" for harness design.
Today, things are usually a little more complicated. The average mid-range car might contain anything between 50 and 100 individual electronic systems, with perhaps 2500 interconnections to be made. And this is likely to increase even more: Formula One cars - traditional pointers to the future shape of consumer models - have around twice this number of interconnects.
The situation is made even more complex by the move toward distributing systems throughout the vehicle, rather than having a single central control circuit to which devices are connected. This change has been driven by the need to reduce fuel consumption and costs by reducing weight. A centralized system requires numerous cables to carry high currents around the vehicle; in contrast, decentralized architectures allow the use of a simple power bus with thinner, lighter cables. The penalty is design complexity.
The final element in the mix is the fact that a typical mid-range car will have thousands of variants, allowing the same basic model to appeal to a variety of demographic markets and to be sold in different areas of the world. Each variant has its own wiring requirements, again increasing complexity.
All of these factors have led to increasing use of electronic design automation (EDA) tools in the design of automotive wiring harnesses, particularly in the Far East. The unique feature of such EDA solutions is the need to combine electrical and spatial parameters. The optimum design flow will make use of EDA tools such as Zuken's CR-5000 suite, which offers tight integration with CATIA V5, the product design and simulation solution in the PLM offering from the dominant supplier to the automotive industry, Dassault Systèmes.
Such integration is the only way to effectively minimize the size of each individual conductor, reduce wire bundle sizes and minimize cost and weight, because the 3D route taken by a wire affects its length and hence its overall resistance. Its diameter, meanwhile, will determine the temperature rise along its length.
The tools used in an integrated design flow are shown in Figure 1. The flow links the design of the vehicle's individual electronic systems to the wire harness design process, and allows the electrical design to be linked to (and back-annotated from) the physical design. This allows connectors to be specified from a common parts library, and the complete vehicle system to be simulated and verified as a whole.
Figure 1
The designer will typically begin by using a cabling design tool to define the circuit connections and the most important attributes of individual pin connections between systems. Connector selection and pin assignment is done while viewing graphical connector shapes: connectors are selected semi-automatically from a library of checked and verified connector pairs. Connector pins are defined in terms of their current carrying capacity, plating materials, metal gauge, and other attributes. The engineer specifies minimum wire sizes, wire colors, and lengths at this stage.
The initial electrical schematic is then built up hierarchically and updated in real time as wire and pin attributes are edited. Junction boxes and connector junctions can also be defined on the schematic to ensure efficient implementation of these in the design.
Figure 2
At this point the tool will carry out the first design rule checks (DRCs), at two levels: "absolute" and "possible". Absolute errors are those that are disallowed under any circumstances. Possible errors include conditions that may or may not be correct. For instance, tools such as Zuken's will provide a "duplicate label" warning if two wires are labeled as "earth" - although this situation may well be correct.
When the vehicle schematic is complete, the cabling design tool will generate wire and connector drawings for the individual sections of the complete vehicle harness. It is also possible to produce ASCII or similar outputs of bill of materials information, specifying connector part numbers and wire types.
After schematic production, data is moved into a topology design tool. This will incorporate the physical routing constraints, to create a flat layout for system placement, basic routing, and partitioning. Breaks in the harness are also defined at this point. Automated routing algorithms are used to optimize the signal path, and placement of junction boxes and splices is defined, with back annotation allowing the harness-to-harness breaks to be assigned in their correct positions in the schematic.
Figure 3
Cross-probing between the cabling design and topology design tools is a useful feature, which allows the engineer to view a selected conductor's path within the topology view of the harness and vice versa. Designers can thus experiment with a variety of electrical and physical design trade-offs to reach an optimum solution.
At this point a second DRC cycle takes place - rules can be defined by the user, and cover both electrical and physical attributes of the design. Finally, it is now possible to produce an estimate of the weight and cost of the complete set of wiring harnesses within the vehicle.
As we have seen, integration between 2D electrical and physical layout tools and 3D mechanical CAD tools is vital. Zuken's tools, for instance, are integrated with the CATIA V5 tool via an XML interface.
Figure 4
The integration between mechanical parts, electrical devices, and bundle segments produces accurate calculations of bundle diameters for use in digital mock-ups, and wire lengths for manufacturing. The ability to back-annotate into the cabling design tool allows automatic re-calculation of wire diameters.
At this stage, the designer will typically use a simulation tool to calculate the voltage and current distribution around the harness. The same tool may carry out DRC for parameters such as matching of fuses and wiring, terminal voltage loads, and maximum current capacity of connections.
What all of this adds up to is an ability to complete designs more quickly, and elimination of the late design changes that can prove so costly in any design environment. But the advantages of an integrated flow do not stop at design. Integration also allows the cabling and topology tools to assist at the manufacturing stage, automatically generating drawings and providing detailed assembly information linked to objects such as connectors or shielding materials.
This methodology - already widely used in Japan - is increasingly the only way of minimizing the size, weight and costs of vehicle wire harnesses while ensuring that all electrical and mechanical constraints on the design are taken into account. Its increasing use in Europe and the US is certain to make the old paper-based techniques a thing of the past.
For further information and reader inquiries, contact:
Amy Clements
2201 Long Prairie RD, STE 107-763
Flower Mound, TX 75022
USA
Tel: 972-691-3284
Fax: 972-691-1304
E-mail: amy.clements@zuken.com
Web: www.zuken.com
About Zuken
Established in 1976, Zuken has evolved into a provider of solutions that maximize the efficiency of the design and manufacturing processes of electronics companies around the world. Zuken holds a leading global share of the PCB/MCM/HIC software market in the field of electronic design automation (EDA). In addition to its longstanding experience as a provider of innovative solutions for PCB design, Zuken's expanded portfolio encompasses proven solutions for the development of information technology (IT) infrastructures. Listed on Level 1 of the Tokyo Stock Exchange, the company is headquartered in Japan and has development, sales and support centers in 10 countries including the US, Germany, UK and France. Zuken's customers include the world's top 30 electronics manufacturers from automotive to aerospace, communications to consumer electronics, and medical to military. For further information please see our website: www.zuken.com.
About the Author
Mike Petersen is Business Development Manager for Harness Design Solutions. He has been with Zuken USA for over 14 years with expertise in Hybrid/MCM Technologies. Since 1998 he has served in a management role directing teams of Application Engineers who work hand in hand with the Sales Organization.
During this time with Zuken USA, he has been guest speaker to several organizations lecturing on Hybrid Design Technologies, Advanced Packaging Techniques, Three Dimensional Electrical Design, along with more recently speaking on the role of Wire Harness Design.
In the 14 years prior to working for Zuken USA, he worked in the Hybrid Micro-Electronic field, doing both Hybrid Design Engineering, Design Management and Production Management for several Companies.
| 
