The full text will be posted tomorrow morning. The starting point or Q_Q mobile client of this chapter has been opened. At that time, you can long press the chapter name in the directory interface and download it again.

...

At this time, Intel CEO Andy Glov was listening carefully to Tang Huan's outlook for the next generation of personal computers and the role Intel80486 can play. After all, no matter how engineers from both sides cooperate or argue on technical issues, the final decision will be made by the big boss.

For Intel, which has put Baoquan on the microprocessor business, there are currently two major problems - the latter has a slight advantage in the dispute between CISC and RISC, and the main product x86 series CPUs are always weaker than those in the same category of Motorola MC68000 series CPUs. Even the latest generation of microprocessors on both sides - Intel80486 and MC68040, continues this trend of strength and weakness.

Their products are so unsatisfactory that Andy Glov, who was outspoken, wanted to lobby the other party to abandon Motorola's MC68000 series CPUs on the grounds that "Tang Huan owns 20% of Intel's shares" and was embarrassed to speak up.

In this case, Zheru's profound skills in compilers, drivers, operating systems and other underlying system software are crucial - in terms of code optimization, as long as Tang Huan asks his subordinates to take a little thought to any party, he will be praised as the top.

It has to be said that the position of software is becoming more and more important now. In addition to being able to stick to users through the established application software operating habits in the terminal, it also largely determines whether the new hardware can perform the performance desired by the designer.

Now that Zheru has achieved such a "supporting two companies with one hand", Intel has an invisible tendency to rely on others. Of course, this embarrassment is different from the original restrained by IBM, and it is completely natural in the ecological checks and balances law, which is completely caused by natural ecological checks and balances.

Fortunately, Tang Huan's attitude towards Intel80486 seemed to exceed MC68040, which relieved Andy Glov a lot.

"In terms of performance, the MC68040 is indeed slightly better than the Intel80486. However, the outstanding heat generation problem of MC68040 is quite difficult, and it may be difficult to make up for it through the process, which has brought considerable impact on the design of the computer host." Tang Huan raised his hand and pointed outside. "You have also seen the guidance of today's press conference. Multimedia and electronic games can squeeze out hardware specifications at any time to improve the performance contributed. In this regard, Intel80486 and MC68040 still need to use the coprocessor of Zheru to share the pressure."

Andy Grove naturally had no way to refute, so he had to follow the future and said: "Intel80486 has integrated cache and floating-point computing units into the chip. In addition to continuing to work hard to increase the operating frequency, the goal of the next-generation product is to learn from RISC's design concepts, such as superscalar-scalar. This requires Intel and Zheru and Fang Yuan to communicate further on patent authorization."

At this stage, one of the main reasons why RISC processors perform faster than CISC processors, the industry and academic circles are quite pessimistic about the prospects of the latter is the parallel computing power of the former.

Compared with serial computing, parallel computing can be divided into parallelism of time angles and parallelism of space angles. Time parallelism is mainly instruction pipeline technology, while spatial parallelism uses multiple processing units to perform concurrent computing tasks, such as superscalars.

Instruction pipeline technology divides the computer instruction processing process into multiple steps, and then hands it over to multiple hardware processing units to execute in parallel to speed up the execution of instructions - very similar to the assembly line in a factory, computer instructions are equivalent to products on the assembly line conveyor belt, and each hardware processing unit is equivalent to workers next to the assembly line.

Intel has implemented a certain degree of instruction pipeline technology within Intel80486. Under the most ideal conditions, Intel80486 can process an instruction in a time period, which is twice as fast as Intel80386 with the same clock frequency.

Superscalar architecture can be regarded as MIMD - a design solution for multiple instructions and multiple data. It often implements instruction flow technology, which is naturally more complex in mechanisms.

A microprocessor that adopts this architecture will have multiple execution units inside, such as arithmetic logic units, displacement units, multipliers, etc., so that the entire CPU can be assigned multiple instructions at the same time within one clock cycle and executed in different execution units, ultimately realizing instruction-level parallelism.

As early as the 1960s, the supercomputer CDC6600, which controlled the data company, took the lead in designing superscalars, but implementing this mechanism on microprocessors was the first to be the RISC microprocessor Holder, which was the 1980s.

Holder, which successfully realizes a lot of cutting-edge technical concepts such as superscalar architecture, has the best performance. The top model helps Fangyuan supercomputers become the fastest computer in the world; the mid-to-high-end model helps Fangyuan network servers and Fangyuan personal workstations compete for the market share of traditional mainframes and minicomputers; the lightweight model helps telecom switches, Internet routers and other devices to achieve a leap in data throughput capabilities; the most eye-catching application of specific models is the CPU that has become the third-generation Xiaobawang game console. Although it has not been officially released, the review media has been praised in one-sidedly.

Another successful application of this parallel technology is video processors, audio processors, and other multimedia hard-coded decoding chips. For example, today's CPUs do not have the ability to soft decompress and play VCDs, and must rely on special video acceleration cards.

Such technologies cannot be completely analyzed even if the chip is reversely engineered in the laboratory. Whoever is ahead will naturally have the advantage in patents.

At this stage, Intel is facing siege and interception from Motorola, AMD, National Semiconductor and other companies within CISC, and there are uncertainties in the product prospects brought by RISC externally. It is not an exaggeration to describe life as if it is walking on thin ice. In terms of patents, it is only possible to bully AMD and others, and they have to bend down in front of Zheru.

"In order to make Intel's R&D smoother, there is no problem in principle." Tang Huan said happily: "You are not unclear about my pursuit of microprocessor performance. I have not been personally responsible for the Intel80286 and Intel80386 over the years to obtain high clock frequency products."

Andy Glov asked curiously: "In this fierce RISC and CISC battle, Don not only did not express his attitude, but seemed to have confidence in CISC?"

"This kind of technological dispute has its own opinions, and no one can guarantee that it will be 100% accurate in its predictions. I, who represents the interests of many teams, cannot speak up. However, I do have great hope for the future prospects of CISC." Tang Huan replied frankly: "After all, in a complex use environment, RISC cannot replace the advantages of CISC. The real technological development trend should be that CISC continues to absorb the advantages of RISC, just like Intel's next-generation microprocessor Intel80586 will introduce a superscalar architecture."

Andy Glov laughed, "This should be the most exciting news I've heard this month."

"However, Intel seems to be somewhat confident about the future of its main product, the CISC-architecture x86 series microprocessor, and is preparing to release a new RISC product, Inteli960, this year?" Some things naturally cannot be hidden from Tang Huan, the largest individual shareholder.

As early as the 1960s, the supercomputer CDC6600, which controlled the data company, was the first to design superscalars.

The full text will be posted tomorrow morning. The starting point or Q_Q mobile client of this chapter has been opened. At that time, you can long press the chapter name in the directory interface and download it again.

...

At this time, Intel CEO Andy Glov was listening carefully to Tang Huan's outlook for the next generation of personal computers and the role Intel80486 can play. After all, no matter how engineers from both sides cooperate or argue on technical issues, the final decision will be made by the big boss.

For Intel, which has put Baoquan on the microprocessor business, there are currently two major problems - the latter has a slight advantage in the dispute between CISC and RISC, and the main product x86 series CPUs are always weaker than those in the same category of Motorola MC68000 series CPUs. Even the latest generation of microprocessors on both sides - Intel80486 and MC68040, continues this trend of strength and weakness.

Their products are so unsatisfactory that Andy Glov, who was outspoken, wanted to lobby the other party to abandon Motorola's MC68000 series CPUs on the grounds that "Tang Huan owns 20% of Intel's shares" and was embarrassed to speak up.

In this case, Zheru's profound skills in compilers, drivers, operating systems and other underlying system software are crucial - in terms of code optimization, as long as Tang Huan asks his subordinates to take a little thought to any party, he will be praised as the top.

It has to be said that the position of software is becoming more and more important now. In addition to being able to stick to users through the established application software operating habits in the terminal, it also largely determines whether the new hardware can perform the performance desired by the designer.

Now that Zheru has achieved such a "supporting two companies with one hand", Intel has an invisible tendency to rely on others. Of course, this embarrassment is different from the original restrained by IBM, and it is completely natural in the ecological checks and balances law, which is completely caused by natural ecological checks and balances.

Fortunately, Tang Huan's attitude towards Intel80486 seemed to exceed MC68040, which relieved Andy Glov a lot.

"In terms of performance, the MC68040 is indeed slightly better than the Intel80486. However, the outstanding heat generation problem of MC68040 is quite difficult, and it may be difficult to make up for it through the process, which has brought considerable impact on the design of the computer host." Tang Huan raised his hand and pointed outside. "You have also seen the guidance of today's press conference. Multimedia and electronic games can squeeze out hardware specifications at any time to improve the performance contributed. In this regard, Intel80486 and MC68040 still need to use the coprocessor of Zheru to share the pressure."

Andy Grove naturally had no way to refute, so he had to follow the future and said: "Intel80486 has integrated cache and floating-point computing units into the chip. In addition to continuing to work hard to increase the operating frequency, the goal of the next-generation product is to learn from RISC's design concepts, such as superscalar-scalar. This requires Intel and Zheru and Fang Yuan to communicate further on patent authorization."

At this stage, one of the main reasons why RISC processors perform faster than CISC processors, the industry and academic circles are quite pessimistic about the prospects of the latter is the parallel computing power of the former.

Compared with serial computing, parallel computing can be divided into parallelism of time angles and parallelism of space angles. Time parallelism is mainly instruction pipeline technology, while spatial parallelism uses multiple processing units to perform concurrent computing tasks, such as superscalars.

Instruction pipeline technology divides the computer instruction processing process into multiple steps, and then hands it over to multiple hardware processing units to execute in parallel to speed up the execution of instructions - very similar to the assembly line in a factory, computer instructions are equivalent to products on the assembly line conveyor belt, and each hardware processing unit is equivalent to workers next to the assembly line.

Intel has implemented a certain degree of instruction pipeline technology within Intel80486. Under the most ideal conditions, Intel80486 can process an instruction in a time period, which is twice as fast as Intel80386 with the same clock frequency.

Superscalar architecture can be regarded as MIMD - a design solution for multiple instructions and multiple data. It often implements instruction flow technology, which is naturally more complex in mechanisms.

A microprocessor that adopts this architecture will have multiple execution units inside, such as arithmetic logic units, displacement units, multipliers, etc., so that the entire CPU can be assigned multiple instructions at the same time within one clock cycle and executed in different execution units, ultimately realizing instruction-level parallelism.
Chapter completed!