Since the mid-eighties, when the RISC architecture matured and entered the historical stage, the battle between complex instruction set (CISC) and reduced instruction set (RISC) for processors has been fierce.

From an objective point of view, in fact, both have their advantages and disadvantages. But throughout the decade, there was a one-sided belief that CISC was obsolete and that RISC was the way forward for advanced technology. The two most important leaders are Paterson from Berkeley and Hennessy from Stanford.

At that time, almost all universities in the United States used textbooks co-edited by these two major students, "Computer Principles" and "Computer System Architecture", which were compulsory courses for computer students. For a long time, a large part of the book used Hennessy's own MIPS architecture as an example to analyze and elaborate on the RISC architecture, while the CISC architecture was rarely mentioned.

If the 8086 processor comes out a few years late, I believe that Intel will never risk the world's condemnation and embark on the road of no return to CISC. But it's a pity that when Intel was developing 8086, the RISC architecture had not yet appeared. In order to be compatible with 8086, the 286 and 386 developed by Intel can only continue to use the CIS instruction set, and they will go further and further on the road of fighting with the world.

Of course, Intel in Li Xuan's memory of the previous life is incomparably brilliant, even if it fights the world on its own, Intel still takes advantage of IBM's PCs, and still a large number of PC compatible machines on the market later, to win a war that no one is optimistic about. It not only formed a monopoly in the desktop CPU market, but also counterattacked the server-level CPU market, grabbing a large share from various RISC processors.

But in this life, because of the emergence of Li Xuan's butterfly, there is a question mark over whether Intel can still succeed. Li Xuan could guess that the proposal to enter the personal computer market must have been placed in front of the top management of IBM's board of directors at this time, and he had already prepared a well-prepared feast for this blue giant.

The main dish of this feast is the ERM architecture processor that Dongfang Shi Yàn Room is fully developing. The reason why Li Xuan's work and rest were regular some time ago, in addition to avoiding the harassment of the media, was actually more important because the research and development of ERM had entered the most critical moment, so he put aside all other complicated things, and also concentrated on joining the research of ERM, only going back and forth between home and studio every day.

Finally, a few days ago, the final good news came from the real yàn room, the initial success of ERM's research and development, the completion of all the design, and the next step is to be sent to the United States for tape-out. The processor enters the tape-out stage, which means that the design is basically finalized, and the next step is to test the sample CPU produced by the tape-out, look for errors and defects, and then make improvements.

It can be said that Li Xuan's ERM processor, which he used to prepare for the fight with IBM's PC, has made a breakthrough. Because according to the normal situation, it generally only takes half a year from the successful tape-out to the official launch of the CPU.

In fact, Dongfang Electronics does not need to wait for the official launch of the CPU, as long as it is confirmed that the tape-out sample has no heavy Dà defects, Aikang Computer and Dongfang Software and other branches will immediately carry out the research and development of supporting hardware and software for the next generation of personal computers according to the relevant technical data of the ERM architecture.

By the time the ERM processor is officially put into production, the research and development of other hardware and software will be almost underway. Dongfang Electronics Co., Ltd. can release its own new generation of personal computers before the PC goes on the market, catching IBM by surprise.

But Li Xuan's mind is very clear-headed, although the ERM processor is a RISC architecture processor that represents the advanced direction of technology, its early performance is actually very mediocre. Even to say that it is mediocre is already a bit elevated. According to many industry insiders in later generations, until DEC joined the ARM camp to develop STRONGARM, ARM was more like a microcontroller than a microprocessor.

The reason why Li Xuan decided to plagiarize the ARM architecture, which is not outstanding, and then "originally" created an ERM architecture, is actually the effect of time difference. Use the middle and upper horses of Tian Ji horse racing to deal with other people's middle horses, and use the 32-bit ERM1 to suppress the 16-bit 8086 and 80286 of Intel Corporation.

By the time Intel's 32-bit 80386 processor was launched, Dongfang Electronics had already relied on its advantages in operating systems and application software to set up many barriers in the personal computer market. At that time, the 80386 processor had no chance to compete fairly with the ERM processor, because there were no vendors on the market who were willing to make their products compatible with Intel's new processors.

Li Xuan may be able to rely on the shady tricks of IBM and Intel, but in the field of workstations, another microcomputer market that is about to rise rapidly, ERM is unlikely to be too competitive in the short term. If a personal computer is a microcomputer with normal performance, then a workstation is a more professional and high-performance microcomputer, and it also has a name called a server.

Early workstations were powered by Motorola's 32-bit MC68000 processors, and ERM had no advantage over it. The main reason why the MC68000 failed to replace the 8086 as the mainstream CPU in the personal PC field is because it is too expensive.

In this regard, ERM has the advantage of the simple design of the RISC architecture, which has just been prepared to be taped out, only integrates 30,000 transistors, while Motorola's MC68000 integrates 70,000 transistors. Under the same process, the volume of ERM chips will undoubtedly be much smaller, which means that a wafer can be divided into many more chips, and the manufacturing cost will naturally be cheaper.

But the high-end workstation market is far less price-sensitive than PCs, and customers are first and foremost concerned about the performance of their computers. This is the main reason why the MC68000 was able to occupy the workstation market in the early eighties.

Since Li Xuan can't use the existing ERM architecture to seize the workstation computer market that is about to enter a period of rapid growth, he must make other layouts, and finding a new processor architecture is undoubtedly the best solution to solve the problem.

At present, the University of Berkeley and Stanford University in the United States each have a research group to study RISC architecture, led by two future experts, Professor Paterson and Professor Hennessy. When Li Xuan was in the United States, he specially asked Dongfang Electronics Company to communicate with the two universities separately, and Professor Hennessy's MIPS research group was more interested in Li Xuan's business development plan.

Li Xuan also considered that he was more familiar with the MIPS architecture, after all, it was the mainstream architecture in the embedded field second only to ARM in later generations, and Li Xuan could also play the role of his golden finger, so he finally decided to cooperate with Professor Hennessy of Stanford University to jointly develop a commercial processor with MIPS architecture.

In fact, the architecture being developed by Professor Paterson of the University of Berkeley is also very good, and the SPARC architecture of the later Sun Company (Shengyang) was developed on this basis. Of course, for Chinese, the MIPS architecture is more familiar, and later China's Loongson adopted the relevant patent authorization of the MIPS architecture.

After reading the email that Professor Hennessy had just sent, Li Xuan quickly replied to him with an email, giving his own opinions on some of the questions he had raised in the email. Li Xuan is no stranger to the MIPS architecture, and relying on the rebirth of the golden finger can save the Hennessy team that is exploring many detours.

Therefore, Professor Hennessy has recently recognized Li Xuan's strength more and more, and the email exchanges between the two have begun to become more frequent. can make the future president of Stanford University impress him, although Li Xuan knows that he is relying on cheating, he is still a little proud in his heart.

ps: book-friend group 3-8-4-1-9-8-7-2-8, interested book friends can join in and chat together!