The first microprocessors were manufactured in the 1970s. These microprocessors were built on NMOS (n-type metal-oxide semiconductor) logic and transistors. Early on, four-bit processors, like the Intel 4004, were common. The Intel 4004 had 2300 transistors. It performed 60,000 operations per second and addressed 640 bytes of memory, and operated at a speed of 740 kHz. The Intel 4004 cost approximately $200. Later in the decade, eight-bit processors such as the Motorola 6502 superseded the four-bit chips. The Motorola 6502 was an eight micrometer process technology chip that was four millimeters square. By the end of the 1970s, 16-bit processors emerged.
第一批微處理器於1970年代製造。 這些微處理器基於NMOS(n型金屬氧化物半導體)邏輯和晶體管構建。 早期,四位處理器(例如Intel 4004)很常見。 英特爾4004具有2300個晶體管。 它每秒執行60,000次操作,尋址640字節的內存,並以740 kHz的速度運行。 英特爾4004的價格約為200美元。 十年後,諸如摩托羅拉6502之類的八位處理器取代了四位芯片。 摩托羅拉6502是8毫米製程技術芯片,面積為4毫米見方。 到1970年代末,出現了16位處理器。
In the 1980s, 16-bit and 32-bit microprocessors were common among new designs, and CMOS (complementary metal-oxide semiconductor) technology overtook NMOS. Transistor count increased dramatically during the decade. The home computers of the 1980s predominantly used processors that were introduced in the 1970s. Versions of the Motorola 6502, first released in 1975, and the Zilog Z80 (1976), were at the core of many home computers, such as the Commodore 64 and the ZX Spectrum. Even the first-generation IBM PC used a processor from the 1970s: the Intel 8088. It was not until Intel's 80286 (in the IBM PC AT), and later the 80386, that 1980s computers used 1980s-designed processors. These late-decade processors offered higher clock speeds and 32-bit word length as well as new operating modes, such as protected mode, that were not available in earlier chips. Specifically, the Intel 80386 was a 32-bit chip. It had more than 275,000 transistors and could perform more than five million instructions every second. The 80386 cost approximately $299. Critically, in these more advanced chips, protected mode allowed the use of virtual memory and brought the graphical user interface to business computers, beginning with Microsoft Windows 2.0.
在1980年代,新設計中普遍使用16位和32位微處理器,並且CMOS(互補金屬氧化物半導體)技術取代了NMOS。在過去的十年中,晶體管的數量急劇增加。 1980年代的家用計算機主要使用1970年代引入的處理器。 1975年首次發布的Motorola 6502和Zilog Z80(1976)的版本是許多家用計算機的核心,例如Commodore 64和ZX Spectrum。甚至第一代IBM PC都使用了1970年代的處理器:Intel8088。直到Intel的80286(在IBM PC AT中)和後來的80386,1980年代的計算機才使用1980年代設計的處理器。這些近十年來的處理器提供了更高的時鐘速度和32位字長,以及新的工作模式,例如保護模式,這在早期的芯片中是不可用的。具體來說,英特爾80386是32位芯片。它擁有超過275,000個晶體管,每秒可執行超過500萬條指令。 80386的價格約為299美元。至關重要的是,在這些更高級的芯片中,從Microsoft Windows 2.0開始,保護模式允許使用虛擬內存,並將圖形用戶界面帶入商用計算機。
The 32-bit microprocessor dominated the consumer market in the 1990s. Processor clock speeds increased by more than tenfold between 1990 and 1999, and 64-bit processors began to emerge later in the decade. In the 1990s, microprocessors no longer used the same clock speed for the processor and the RAM. This technology allowed for the improvement in processor speeds. In 1993, Intel released the Pentium processor. The Pentium chip was a 60 MHz processor. It incorporated 3.1 million transistors and sold for approximately $875.
32位微處理器在1990年代主導了消費市場。 在1990年至1999年之間,處理器時鐘速度提高了十倍以上,並且在該十年後期開始出現64位處理器。 在1990年代,微處理器不再為處理器和RAM使用相同的時鐘速度。 這項技術可以提高處理器速度。 1993年,英特爾發布了奔騰處理器。 奔騰芯片是60 MHz處理器。 它裝有310萬個晶體管,售價約為875美元。
In the 2000s, 64-bit processors became mainstream. Microprocessor clock speeds reached a ceiling because cooling technology peaked. The ability to dissipate heat from the processor had reached a limit. Instead of implementing expensive and impractical cooling systems, manufacturers looked to other methods to improve processor performance by using multicore processor technology. Overclocking was born in the 1990s, but came into its own in the 2000s. With the introduction of multicore technology, processor costs began to drop dramatically.
在2000年代,64位處理器成為主流。 由於冷卻技術達到頂峰,微處理器時鐘速度達到了上限。 散發處理器熱量的能力已達到極限。 製造商沒有採用昂貴且不切實際的冷卻系統,而是尋求其他方法來使用多核處理器技術來提高處理器性能。 超頻誕生於1990年代,但在2000年代就已誕生。 隨著多核技術的引入,處理器成本開始急劇下降。
Off-the-shelf cooling systems designed for overclocked processors became more and more common, as did the concept of a PC designed for gaming. Over the decade, transistor counts increased by about an order of magnitude, a trend continued from previous decades. Processor sizes decreased about fourfold, from 180 nm to 45 nm. In 2007 AMD released the Athlon X2 processor line. The AMD Athlon X2 Brisbane series processed at a speed of 1.9 to 2.6 GHz and it included a 512 KB L2 cache. In 2012, AMD released the A10-5700 desktop processor. It included a 4M L2 cache and processed at a speed of 3.4 GHz, or 4.0 GHz in turbo mode. AMD’s A10-5800K, released at the same time as the A10-5700, included the same cache, but provided for processing speeds of 3.8 GHz or 4.2 GHz in turbo mode. In the 2010s, processors typically hold between 2.5 and 4 billion transistors.
設計用於超頻處理器的現成的冷卻系統變得越來越普遍,而設計用於遊戲的PC的概念也越來越普遍。 在過去的十年中,晶體管的數量增加了大約一個數量級,這一趨勢延續了過去的幾十年。 處理器尺寸從180 nm減少到45 nm約四倍。 AMD在2007年發布了Athlon X2處理器系列。 AMD Athlon X2 Brisbane系列以1.9至2.6 GHz的速度進行處理,並包含512 KB L2緩存。 2012年,AMD發布了A10-5700台式機處理器。 它包括一個4M L2高速緩存,並以3.4 GHz或Turbo模式下的4.0 GHz的速度進行處理。 AMD的A10-5800K與A10-5700同時發布,具有相同的緩存,但在Turbo模式下可提供3.8 GHz或4.2 GHz的處理速度。 在2010年代,處理器通常容納2.5至40億個晶體管。
CPU Technology (CPU技術)
Over the years, various technologies have been added to the CPU to increase its speed and efficiency. The first of these technologies is called hyperthreading or HT technology. HT technology was originally developed by Intel. It allows the CPU to execute two “threads” within a single processor core. Essentially, the CPU emulates (or pretends to be) two CPUs instead of the single physical processor it really is. This allows for faster execution of programs. Consider a large classroom with many students, but only one instructor. If multiple students are asking questions, the instructor needs to answer everyone’s questions as quickly as possible. Instead of finishing the first question, then taking the second question, the hyperthreading would allow the instructor to begin answering the second question while the first question was still being answered. This effectively increases the instructor’s ability to answer more questions in a shorter period of time.
多年來,CPU已添加了各種技術以提高其速度和效率。 這些技術中的第一個稱為超線程或HT技術。 HT技術最初是由Intel開發的。 它允許CPU在單個處理器內核中執行兩個“線程”。 本質上,CPU模擬(或假裝為)兩個CPU,而不是實際的單個物理處理器。 這樣可以更快地執行程序。 考慮一個大教室,教室裡有很多學生,但只有一位老師。 如果有多個學生提出問題,則講師需要盡快回答每個人的問題。 無需完成第一個問題,而是處理第二個問題,超線程將允許教師在第一個問題仍在回答的同時開始回答第二個問題。 這有效地提高了教師在較短的時間內回答更多問題的能力。
The second technology, which is a vast improvement over hyperthreading, is called multicore design. In multicore designs, the processor (physically a single piece of hardware) contains multiple processors in the chip itself. These come in dual (two), quad (four), hexa (six), and octa (eight) core designs. An octa core design allows a single chip to contain up to eight processor cores. The eight processor cores enable simultaneous execution of eight different and unique processes. Previous to the multicore design, if you wanted multiple processors (like on a server), you had to have a special motherboard with multiple processor sockets and a special operating system that understood multiple processors. With a multicore design, a singular socket can be used, and any operating system can understand how to use the singular CPU (with multiple cores).
Bus Speeds 巴士速度
The bus is the backbone communication system that transfers data between components inside a computer. The bus is measured in megahertz (MHz), which is the speed at which the bus operates. MHz is the number of clock-cycles that occur in a given second (MHz equals millions of times a second). While the motherboard’s bus operates at a fixed speed, the input/output ports and expansion slots all run at a unique speed determined by the devices connected to the respective slot. Each port can be configured or negotiated to run at the appropriate speed (up to a maximum value) for each device (such as FireWire, AGP, PCIe, PATA, SATA) as each connection type supports a different speed.
總線是骨幹通信系統,可在計算機內部組件之間傳輸數據。 總線以兆赫(MHz)為單位,這是總線運行的速度。 MHz是在給定的每秒內發生的時鐘週期數(MHz等於每秒數百萬次)。 主板總線以固定速度運行時,輸入/輸出端口和擴展插槽均以連接到相應插槽的設備確定的唯一速度運行。 每個端口都可以配置或協商為每個設備(例如FireWire,AGP,PCIe,PATA,SATA)以適當的速度(最大值)運行,因為每種連接類型都支持不同的速度。
There are both 32-bit and 64-bit processors. This is an important concept because if you are running a 32-bit processor or a 32-bit operating system, your computer can only access up to 4 GB of RAM. Windows will only access 3.25 GB of RAM if you are using a 32-bit version of Windows (such as Windows XP, or Vista/7 x86). The first 64-bit processor was the AMD Athlon 64. Those x64 processors are fully backward compatible with slower x86 software and devices. By using x64, the 4 GB limit of RAM is removed, allowing us to access 16 GB, 32 GB, 64 GB, or more of memory.
Copyright © All rights reserved | This template is made with by Colorlib