What model do you need

9 Skills You Need to Become a Data Modeler in 2022

Table of Contents

Data Modeling has recently emerged as one of the best skills to have in the extremely competitive industry of data science for database generation. Data scientists have recognized the need for data modeling in data analysis, as it is the foundation for gathering clean, interpretable data that businesses can use to make decisions.

What is Data Modeling and Why Do You Need It?В

Data modeling evaluates and measures how an organization manages the flow of data in and out of the database management system. Since it is responsible for creating the space needed for your data, data modeling is one of the most important parts of a Big Data project. Data modeling structures the space for your data, and looks after the factors related to the environment your data lives in. In short, data modeling is the management of data within an organization.

Data modeling also determines how the data should be treated, how the data neurons connect with each other and define how the data is generated, and what story it will tell going into the future.

Considering the impact it has on an organization, decisions regarding data modeling need to be made early on in the data-gathering process. It is up to the organization to decide what story each data set will narrate, and for data to tell the perfect story, it needs to be modeled to perfection.

Numerous software applications make use of data modeling processes to give the most seamless customer experience. With the changing culture of the world, it is imperative that the data you hold should be altered in a way that best matches the needs of the end customer. Ensuring a perfect customer experience is something that many organizations are working on, and this experience can be achieved only through the use of perfect data modeling strategies.

Post Graduate Program in Data Analytics

The Data Modeling Process

Data modeling serves as a means to complement business modeling and to work towards generating a sufficient database. The process for designing a database includes the production of three major schemas: conceptual, logical, and physical. A Data Definition Language is used to convert these schemas into an active database. A data model that is fully attributed and covers all major aspects includes detailed descriptions for every entity contained within it.

Although data models can be created through the use of numerous methods, there are two methodologies that produce the best model. These are known as the bottom-up and top-down data modeling processes.

What Do You Need to Become a Data Modeler?

The skills required for data modeling are quite different than the skills required for programming and systems administration. While programmers and administrators are required to have sufficient expertise on the technical front, data modelers are required to be more apt at the logical side of things. The skills required for data modeling include the following:

Free Course: Python Libraries for Data Science

Based on these requirements, a person who does not have the required software and system knowledge, but has the proven ability to think conceptually and abstractly, will be considered perfect as a data modeler.

Communication skills are essential for all data modelers. Organizations look for strong communication skills in data modelers because modelers are required to translate and balance all user requirements. Moreover, they are also required to document the final results in a perspective that is easy to understand for all users.

EducationВ

Many recruiters looking for data modelers want candidates with a bachelor’s degree, preferably, in information science, applied mathematics, or computer studies. These degrees are deemed perfect for a data modeler, and the candidate is considered suitable in most cases. However, some employers may also want to look out for data modelers with multiple courses in information systems management or business management. Data Modelers should also be skilled in database administration and should know how to look over a database and to think of plausible outcomes for different data complications.

You must exhibit the following nine skills before pursuing a career in data modeling:

FREE Course: Introduction to Data Analytics

How Do You Advance as a Data Modeler?

As soon as a novice modeler starts their training period, they are assigned to an experienced mentor. The experienced mentor should preferably be someone who has years of experience in data modeling behind them and has partaken in many training programs, both as a learner and as a trainer. The mentor should be well versed with the techniques used for data modeling within the industry and should know of all the systems in place with the specific organization. The experience of the mentor and the training methodology used by them, usually defines how well the data modeler is able to apply his or her skills within the organization.

There are numerous advancement opportunities for data modelers in the workplace. A data modeler’s career can grow over time, and they can soon head their own department or even become a manager of an IT firm that works in data marketing or data modeling.

Career Outlook

Stepping into a career as a modeler, you’ll have to work with data analysts and architects to identify key dimensions and facts to support the system requirements of your client or company. You will be required to manage and keep the integrity and quality of the data. It’s essential to have domain knowledge to be able to interpret the results.

Data Modeler Responsibilities

The data modeler job description includes being responsible for designing databases and ensuring that they operate effectively. They typically work in collaboration with data architects and other IT professionals. Data modelers use specialized software to create and modify database structures, as well as manage the data itself.

Data modelers must have a strong understanding of both relational and non-relational database systems. They must be able to identify the most efficient way to store and retrieve data, taking into account the specific needs of the organization. Data modelers must also be able to work with large amounts of data and understand complex relationships between data points.

The data modeler role is often involved in the entire lifecycle of a database, from design to implementation to maintenance. In some organizations, data modelers may also be responsible for data security and performance tuning.

Data Modeler JobsВ

There are many different types of data modeling jobs available. Some data modelers work in the IT department of a company, developing databases and data systems. Others work in research and development, creating models to test theories or help develop new products. Still others work in marketing, using data to create better customer profiles or understand consumer behavior.

Get broad exposure to key technologies and skills used in data analytics and data science, including statistics with the PG Program in Data Analytics.

Importance of CertificationsВ

Certifications are crucial when it comes to data modeling in the formal setting. Companies agree it’s important for their data modelers to obtain reputable certifications that prove their expertise and also enhances their skills. These certifications include Big Data and Data Science courses, Big Data Engineer Master’s Programs, Big Data Hadoop Training, and Data Science with R, among others.

If you’re interested in becoming a Big Data expert then we have just the right guide for you. The Big Data Career Guide will give you insights into the most trending technologies, the top companies that are hiring, the skills required to jumpstart your career in the thriving field of Big Data, and offers you a personalized roadmap to becoming a successful Big Data expert.

Find our Professional Certificate Program in Data Analytics Online Bootcamp in top cities:

About the Author

Named by Onalytica as the world’s #1 influencer in Data and Analytics, Automation, and the Future Economy (Tech), Ronald is the CEO of Intelligent World and one of the top thought leaders in Data Science and Digital Transformation.

Recommended Programs

Post Graduate Program in Data Analytics

Introduction to Data Analytics Course

Data Science with R Language Certification Training

*Lifetime access to high-quality, self-paced e-learning content.

Find Post Graduate Program in Data Analytics in these cities

Data Science vs. Big Data vs. Data Analytics

Recommended Resources

Data Science Career Guide: A Comprehensive Playbook To Becoming A Data Scientist

Why Python Is Essential for Data Analysis and Data Science?

Data Analyst vs. Data Scientist

Data Science Interview Guide

10 Years of Data Science and Big Data Innovations

Analysis of UE5 Rendering Technology: Nanite

1. Introduction

After Epic released the UE5 technology demo at the beginning of 2021, the discussion about UE5 has never stopped. Related technical discussions mainly centered on two new features: global illumination technology Lumen and extremely high model detail technology Nanite. There have been some articles [1 ][2] analyzing Nanite technology in more detail. This article mainly starts from the RenderDoc analysis and source code of UE5, combined with some existing technical data, aims to provide an intuitive and overview understanding of Nanite, and clarify its algorithm principles and design ideas, without involving too many source code level Implementation details.

2. What do we need for next-generation model rendering?

To analyze the technical points of Nanite, we must first proceed from the perspective of technical requirements. In the past ten years, the development of 3A games has gradually tended to two main points: interactive film narrative and open world. In order to cutscene realistically, the character model needs to be exquisite; for a sufficiently flexible and rich open world, the map size and the number of objects have increased exponentially, both of which have greatly increased the requirements for the fineness and complexity of the scene: The number of objects must be large, and each model must be sufficiently detailed.

There are usually two bottlenecks in the rendering of complex scenes:

The CPU-side verification and communication overhead between CPU-GPU brought by each Draw Call;

Overdraw caused by inaccurate elimination and the resulting waste of GPU computing resources;

In recent years, the optimization of rendering technology has often revolved around these two problems, and some technical consensus in the industry has been formed.

Thanks to the more and more widespread application of GPU Driven Pipeline in games, the vertex data of the model is further divided into more fine-grained Clusters (or Meshlets) so that the granularity of each Cluster can better adapt to the Vertex Processing stage. Cache size and various types of culling (Frustum Culling, Occlusion Culling, and Backface Culling) have gradually become the best practice for complex scene optimization, and GPU vendors have gradually recognized this new vertex processing flow.

However, the traditional GPU Driven Pipeline relies on Compute Shader culling. The removed data needs to be stored in the GPU Buffer. Via APIs such as Execute Indirect, the removed Vertex/Index Buffer is fed back to the GPU’s Graphics Pipeline, which has increased the invisible overhead of reading and writing. In addition, the vertex data will be read repeatedly (Compute Shader reads before culling and Graphics Pipeline reads through Vertex Attribute Fetch when drawing).

Based on the above reasons, in order to further improve the flexibility of vertex processing, NVidia first introduced the concept of Mesh Shader[5], hoping to gradually remove some fixed units (VAF, PD, and other hardware units) in the traditional vertex processing stage. And hand over these matters to the developer to process through the programmable pipeline (Task Shader/Mesh Shader).

Schematic of Cluster

The traditional GPU Driven Pipeline eliminates dependence on CS, and the eliminated data is passed to the vertex processing pipeline through VRAM

The Pipeline Based on the Mesh Shader, Cluster culling becomes part of the vertex processing stage, reducing unnecessary Vertex Buffer Load/Store

3. Are these enough?

So far, the problems of the number of models, the number of triangle vertices, and the number of faces have been greatly optimized and improved. However, high-precision models and small triangles at pixel level put new pressure on the rendering pipeline: rasterization and overdraw pressure.

Does soft rasterization have a chance to beat hard rasterization?

Taking the NVIDIA Rasterizer as an example, a triangle usually undergoes two stages of rasterization: Coarse Raster and Fine Raster. The former takes a triangle as input and 8×8 pixels as a block, and the triangle is rasterized into several blocks (it can also be understood as rough rasterization on the FrameBuffer whose original size is FrameBuffer 1/8*1/8).

At this stage, the occluded block will be completely eliminated through the low-resolution Z-Buffer, which is called Z Cull on the NVIDIA card; after the Coarse Raster, the block that passes through the Z Cull will be sent to the next stage for processing Fine Raster, which finally generates pixels for shading calculations. In the Fine Raster stage, we are familiar with Early Z. Due to the calculation needs of Mip-Map sampling, we must know the information of the adjacent pixels of each pixel, and use the difference of the sampled UV as the calculation basis for the Mip-Map sampling level. For this reason, the final output of Fine Raster is not a pixel, but a small 2×2 Pixel Quad.

For triangles close to the pixel size, the waste of hardware rasterization is obvious. First of all, the Coarse Raster stage is almost useless, because these triangles are usually smaller than 8×8. This situation is even worse for those long and narrow triangles because a triangle often spans multiple blocks, and these triangles cannot be removed by Coarse Raster but also add additional computational burden; in addition, for large triangles, the Fine Raster stage based on Pixel Quad will only generate a small number of useless pixels on the edge of the triangle, which is only a small part of the area of ​​the entire triangle; But for small triangles, Pixel Quad will generate pixels four times the area of ​​the triangle at worst, and these pixels are also included in the execution stage of Pixel Shader, which greatly reduces the effective pixels in WARP.

Rasterization waste of small triangles due to Pixel Quad

Deferred Material

The problem of redrawing has long been a performance bottleneck in graphics rendering, and optimizations around this topic are also emerging endlessly. On the mobile side, there is the familiar Tile Based Rendering architecture [8]; in the evolution of the rendering pipeline, some people have also proposed Z-Prepass, Deferred Rendering, Tile Based Rendering, and Clustered Rendering, these different rendering pipeline frameworks, In fact, they are all to solve the same problem: when the light source exceeds a certain number and the complexity of the material increases, how to avoid a large number of rendering logic branches in the Shader and reduce useless redrawing. On this topic, you can read my article [9].

Generally speaking, the deferred rendering pipeline needs a set of Render Targets called G-Buffers. These textures store all the material information needed for lighting calculations. In today’s 3A games, the types of materials are often complex and changeable, and the G-Buffer information that needs to be stored is increasing year by year. Taking the 2009 game “Kill Zone 2” as an example, the entire G-Buffer layout is as follows:

Excluding Lighting Buffer, in fact, the number of textures required for G-Buffer is 4, totaling 16 Bytes/Pixel; by 2016, the G-Buffer layout of the game “Uncharted 4” is as follows:

The number of textures in G-Buffer is 8, which is 32 Bytes/Pixel. In other words, in the case of the same resolution, due to the increase in material complexity and fidelity, the bandwidth required by the G-Buffer has been doubled, and this does not consider the factor of the game resolution that has increased year by year.

(1) Instance ID, which indicates which Instance (16

24 bits) the current pixel belongs to;

(2) Primitive ID, which indicates which triangle (8

16 bits) of Instance the current pixel belongs to;

(3) Barycentric Coord, which represents the position of the current pixel in the triangle, expressed in barycentric coordinates (16 bits);

(4) Depth Buffer, which represents the depth of the current pixel (16

(5) Material ID, which indicates which material the current pixel belongs to (8

Above, we only need to store about 8

In the lighting shading stage, only need to index to the relevant triangle information from the global Vertex Buffer according to the Instance ID and Primitive ID; further, according to the center of gravity coordinates of the pixel, the vertex information in the Vertex Buffer (UV, Tangent Space, etc.) Perform interpolation to obtain pixel-by-pixel information; further, according to the Material ID to index the relevant material information, perform operations such as texture sampling, and input to the lighting calculation link to complete the coloring. Sometimes this type of method is also called Deferred Texturing.

The following is the rendering pipeline process based on G-Buffer:

This is the rendering pipeline process based on Visibility-Buffer:

What Graphics Card Do I Have?

Knowing what graphics card you have can be confusing; here’s how to check.

Want to play the latest games, but aren’t sure if your PC can handle them? Graphics are a huge part of the PC gaming experience, but not every computer is built for the best games on the market. You’ll need to know what graphics card you have installed and compare that to the minimum requirements for the game you want to play. Here’s how to figure it out.

PCMag-Recommended Windows Accessories

Microsoft 365 Personal Review

Microsoft Ergonomic Keyboard Review

Microsoft Precision Mouse Review

BenQ EX2780Q Review

Microsoft Modern Keyboard With Fingerprint ID Review

Microsoft Bluetooth Ergonomic Wireless Mouse Review

Microsoft Designer Compact Keyboard Review

Microsoft Surface Mobile Mouse Review

What’s a Graphics Card?

When you turn on your computer, the images that appear on screen—whether it’s a simple Word document or a complex 4K gaming experience—are generated by a graphics processing unit (or GPU). These chips can range from simple «integrated graphics,» which are part of the motherboard or processor, to larger, more powerful expansion cards.

These expansion cards—often called «discrete» or «dedicated» graphics cards—can usually perform more powerful tasks than integrated graphics, like better 3D gaming, accelerated video rendering, or even certain non-graphical jobs like mining bitcoin. This extra utility comes at the expense of higher power usage, more heat, and more space in your computer, which is why you’ll rarely find dedicated graphics cards in ultra-thin laptops.

Just like any other computer component, graphics cards can become outdated over time. The card you bought in 2012 is unlikely to play 2022’s AAA games at high settings, so if you’re ever unsure whether a game will run on your PC, you’ll want to compare its minimum or recommended requirements to the hardware you currently have.

Knowing what graphics card you have can be confusing, since there are two relevant model numbers: the model of the GPU (the actual chip that does the work), and the model of the card itself (which includes other hardware like the cooler, voltage regulation module, and so on).

There are two main discrete GPU manufacturers today: Nvidia and AMD. There are many other manufacturers, however, making the cards themselves—Asus, EVGA, MSI, Gigabyte—and other companies can produce graphics cards using chips from Nvidia and AMD, adding their own tweaks to set themselves apart from each other. One manufacturer’s version may have better fans than another, may come overclocked from the factory, or have a better warranty.

So when you’re looking up what graphics card you have, you’ll need to decide whether knowing the chipset is enough (for example, the «Nvidia GeForce GTX 1060») or whether you need the actual manufacturer and model of your card (such as the «EVGA GeForce GTX 1060 Superclocked,» which uses Nvidia’s chipset). The former is very easy to find in Windows, while the latter is a bit more complicated.

Find Out What GPU You Have in Windows

In your PC’s Start menu, type «Device Manager,» and press Enter to launch the Control Panel’s Device Manager. Click the drop-down arrow next to Display adapters, and it should list your GPU right there. (In the screenshot below, you can see that I have a Radeon RX 580.)

If you aren’t sure which company designed that chip, you can right-click on it and choose Properties to see the manufacturer—in my case, Advanced Micro Devices, or AMD. (Note that Device Manager uses your graphics drivers to determine what GPU you have, so if you suspect the wrong drivers may be installed, you should skip to the next section.)

Once you have the GPU name, you can Google around to learn more about it, or compare it to the minimum requirements on the game you want to play. Usually, a higher number denotes a better card—so a game that requires an RX 580 may not run on an RX 480, which is less powerful (though there are sometimes ways around that).

Глагол need: смысловой или модальный

Содержание статьи:

Значения глагола need

You needn’t buy any bread, I already bought some. — Тебе не нужно покупать хлеб, я уже его купила.

I needn’t your help, I can do it myself. — Мне не нужна твоя помощь, я могу сделать это самостоятельно.

In our country people need to go through regular medical checks. — В нашей стране людям нужно регулярно проходить медосмотры.

Employees don’t need to pay for insurance in our company. — Сотрудникам не нужно платить за страховку в нашей компании.

Кстати, после need может использоваться не только глагол, но и существительное:

I need your help. — Мне нужна твоя помощь.

We will need some water, some sugar and some flour. — Нам понадобится немного воды, немного сахара и немного муки.

Формы глагола need

Everyone needs to be respected. — Каждый нуждается в уважении.

I do not need to use public transport. I live near my office. — Мне не нужно пользоваться общественным транспортом. Я живу недалеко от офиса.

Do we need to book tickets in advance? — Нам нужно заказывать билеты заранее?

I needed your help yesterday. — Мне нужна была твоя помощь вчера.

We needed a breath of fresh air after that long meeting. — Нам нужен был глоток свежего воздуха после этой долгой встречи.

Когда need проявляет свойства модального глагола он имеет только одну форму — форму настоящего времени, одинаковую для всех лиц в единственном числе.

Утвердительная форма:

I need never tell you that I am allergic to oranges. — Мне же не нужно рассказывать тебе, что у меня аллергия на апельсины.

You need scarcely worry about us; we know what we are doing. — Едва ли тебе нужно волноваться за нас, мы знаем, что делаем.

You need hardly explain this to her, she won’t listen. — Вряд ли нужно это ей объяснять, она не послушает.

Отрицательная форма:

Обратите внимание, что как модальный need используются по большей части в отрицаниях ( needn’t ) и вопросах, также можно встретить его после if и в других «неутвердительных» предложениях:

You needn’t book tickets in advance, you can always buy them at the station. — Тебе не нужно бронировать билеты заранее, вы всегда сможете купить их на станции.

You needn’t pay for this. — Не нужно за это платить.

I want to know if I need to pay for this. — Я хотел бы знать, нужно ли за это платить.

This is the only thing you need pay for. — Это единственное, за что вам нужно платить.

В американском английском вместо need часто используются формы have to/ don’t have to.

Вопросительная форма:

Модальный need в вопросах выходит на первое место, и такие вопросы передают нежелание что-то делать или сомнение в необходимости действия:

Need we wait here? — Нам точно нужно ждать здесь?

Need I pay for this? — Мне надо за это платить?

Need we really invite him to the party? I do not like his company. — Нам действительно нужно приглашать его на вечеринку? Мне не нравится его общество.

Ответы на вопросы c need

Если вопрос типа yes/no, то скорее всего ожидается отрицательный ответ:

— Need we wait here? — Нам обязательно нужно ждать здесь?
— No, we needn’t. We can wait outside. — Нет, не обязательно. Мы можем подождать снаружи.

— Need you go there tomorrow? — Нам действительно нужно идти туда завтра?
— No, I needn’t. We can stay at home. — Нет, мы можем остаться дома.

Возможны и другие отрицательные ответы, в которых не обязательно должен присутствовать need :

I hope not. — Надеюсь, что нет.

Of course not. — Конечно, нет.

Если же ответ утвердительный, в коротком ответе используется must:

— Need I correct the mistakes? — Мне нужно исправить ошибки?
— Yes, you must. It is a part of your hometask. — Да, нужно. Это часть твоей домашней работы.

— Need you go there tomorrow? — Тебе обязательно идти туда завтра?
— Yes, I must. It will be an important meeting. — Да, это будет важная встреча.

Need для обозначения будущих действий

Если речь идет о решении по поводу необходимости в ближайшем будущем (не постоянной необходимости), то используются формы настоящего времени глагола need :

Need I call you tomorrow? — Мне нужно позвонить тебе завтра?

Tell him he doesn’t need to come tonight. — Скажите ему, что ему не нужно/необязательно приходить сегодня вечером.

You will need to fix your car next month. — Тебе нужно будет отремонтировать машину в следующем месяце.

He will need to start preparation soon if he wants to pass his exams. — Ему нужно будет начать подготовку в ближайшем времени, если он хочет сдать экзамены.

You will need to produce your pass before you enter the building. — Вам нужно будет предъявить ваш пропуск перед тем, как вы войдете в здание.

Need c Present Perfect: need not have done

You needn’t have bought any bread. We still have some! — Не нужно было покупать хлеб! У нас еще есть хлеб!

I needn’t have driven to the supermarket. They do not work on Sundays. — Я напрасно ездил в супермаркет. Они не работают по воскресеньям.

Need not have done и did not need to do — это две разные конструкции и обозначают они разные вещи. Давайте научимся их различать. Первая, как вы уже знаете, говорит о том, что не было нужды делать то, что было сделано.
А вторая — в Past Simple, просто указывает на то, что действие было необязательным, но мы не знаем, было оно выполнено или нет.

Сравните две ситуации:

You needn’t have bought bread! We still have some! — Не нужно было покупать хлеба! У нас еще есть хлеб!

I did not need to buy bread, because we had some left. — Мне не было нужно покупать хлеб, потому что у нас еще оставалось немного.

Need not или must not?

Need not иногда путают с must not, потому что на русский язык обе формы переводятся одинаково: «не нужно».

Need not или don’t need to передает отсутствие необходимости в то время, как must not — запрет что-то делать.

You need not call Bob, I already talked to him. — Не нужно звонить Бобу, я уже с ним поговорил.

You must not call Bob, I do not want him to know this news. — Не нужно звонить Бобу, я не хочу, чтобы он знал эти новости.

Need not также может переводиться как «не обязательно», когда мы имеем в виду, что что-то не обязательно является правдой.

— She is very quiet all evening. She might be ill. — Она очень тихо ведет себя весь вечер. Возможно, она больна.

— It need not be. She might be just tired after work. — Не обязательно. Возможно, она устала на работе.

Need: смысловой или модальный?

И вот мы приближаемся к завершению статьи, и снова возникает главный вопрос: когда же использовать need как модальный, и когда как обычный глагол?

В большинстве случаев: в утверждениях, отрицаниях и вопросах, в которых идет речь об общей необходимости, потребности что-либо сделать need ведёт себя как обычный смысловой глагол:

When will you need to go to the oculist next time? — Когда тебе нужно будет идти к окулисту в следующий раз?

The child does not need to go to the dentist. — Ребенку не нужно идти к дантисту.

He would always lend me his guitar when I needed to practice. — Он всегда одалживал мне свою гитару, когда мне нужно было попрактиковаться.

В разговорной речи, когда нужно передать определенную эмоцию или настроение: в отрицаниях, передающих необязательность действия ( lack of necessity ), и в вопросах, выражающих сомнение и нежелание выполнять действие, need используется как модальный.

Do we need to wait? — Нам нужно подождать?
Need we wait? — Нам действительно нужно ждать?

We don’t need to stay here longer. — Нам не нужно больше здесь оставаться.
We needn’t stay here longer. — Нам действительно не нужно больше здесь оставаться.

Заключение

Думаю, все оказалось проще, чем вам казалось. Need — не такой уж и сложный глагол. Главное — понять его значения и понимать, в каких формах и ситуациях он уместен как модальный и как смысловой.
Если у вас остались вопросы по этой теме — пишите их в комментариях. А чтобы воплотить теорию на практике, отработать использование глагола в разговорной речи — приглашаю вас на персональные занятия с нашими преподавателями!

До начала обучения мы проводим бесплатное вводное занятие, которое длится 60 минут.
И занятие это не шаблонно-общее с целью разрекламировать продукт, а спланированное и составленное именно по тому курсу, который вы выбрали и соответствует вашему уровню.
Цель вводного занятия — определить ваши цели, ваш уровень знаний, продемонстрировать как проходит обучение в ENGINFORM, дать вам исчерпывающую информацию об интересующем вас курсе и о том, как мы обучаем.

Записывайтесь сейчас, пробуйте наше персонализированное обучение, а я традиционно желаю вам успехов в изучении английского языка и верю, что у вас все получится!

avilchezj

Activity: Buying a computer (dialog)

BUYING A COMPUTER

Paul: Um, yes, we’re looking for a Mac computer. Have you got any fairly basic ones?

Paul: What different models are there?

Assistant: At the moment we’ve got these two models : the iMac, which is a desktop computer with an Intel Core 2 Duo processor operating at 2.33 gigahertz, and the portable MacBook, which has a processor running at 2.0 gigahertz. Core Duo technology actually means two cores, or processors, built into a single chip, offering up to twice the speed of a traditional chip.

Correcting mistakes and language functions

1 The Ulysses is a powerful, expandable computer that offers high-end graphics at a low price.

2 A laptop is likely to be more expensive than the equivalent desktop computer, but a laptop is more practical if you travel a lot.

3 What’s the storage capacity of the hard drive?

4 I’m looking for a desktop computer that has good graphics for games.

5 Do you need the any/some help?

6 How much does the PDA cost?

7 This workstation has / has got a Pentium processor with dual-core technology, 1.024 megabytes of RAM, and 1 terabyte of disk space.