Su Yuanshan led Claude to his office.

Although Yuanxin’s desktop CPU processor design department has been moved to the Shanghai Stock Exchange now, Su Yuanshan’s office still has the most complete information and the latest progress.

"We thought about it very seriously and believed that the speed of floating-point calculations will definitely be an important indicator for measuring the performance of a CPU in the future, and it is particularly affected by the intuitive frequency."

Claude sat opposite Su Yuanshan, staring at the heat of the coffee pot and said seriously: "Cyrix has never had the opportunity to face Intel before. In addition to our lack of resources, there are also reasons why we have never been able to break through the shackles of architecture."

His words seemed to be explaining why the old village was before, but in fact... they were complimenting Su Yuanshan.

Because the current Sol architecture is provided by Su Yuanshan, and when he first obtained the architecture, he intuitively determined that the architecture provided by Su Yuanshan has exceeded Intel's Pentium architecture.

Su Yuanshan smiled after hearing this, and slowly poured a cup of coffee for Claude. Then he whispered a few words.

“instruction    per     clock”

Claude was stunned when he heard this.

Su Yuanshan thought for a while and said, "Let's abbreviate it and call it IPc, it means the instruction efficiency of each clock - this is the most fundamental indicator, frequency is just a manifestation, it is just a means to improve IPc."

"Take bricks as an example. If a person wants to improve the efficiency of bricks, he can of course run faster - this is to increase the frequency. But he can also move two or three at a time. Although the frequency has not changed, the efficiency has doubled."

Claude slowly fell into thinking.

Su Yuanshan was not in a hurry and slowly savored the coffee.

There are many ways to improve ipc. Whether it is superscalar, super pipeline, dynamic branch prediction, or super long instruction words in later generations, they can all improve ipc.

"What do you mean is that we should focus on super scalars and super assembly lines in the future?" A few seconds later, Claude immediately looked up at Su Yuanshan and asked.

"If you don't focus on a certain direction, you can't give up any direction. If you focus on frequency, you really have embarked on the wrong path." Su Yuanshan said, paused and said with a smile: "For example, now Intel and Amd, they have embarked on the evil path."

Claude became speechless.

Perhaps only Su Yuanshan dares to say this, he dares not say it anyway...

In the past year, he and Su Yuanshan have contacted Su Yuanshan hundreds of times by email. He has long known that Su Yuanshan is a real genius architect in CPU design. Every time he discusses technical issues, he mistakenly thinks that Su Yuanshan is an old world who has been immersed in for many years.

"Haha, but we can't give up on frequency. 1ghz is indeed a very attractive commanding height. The performance improvement brought about by the increase in frequency is too intuitive." Su Yuanshan smiled again and said, "Let's go, I'll show you the ideas of the next generation of architecture."

...

In the afternoon of the same day, Li Mingliu and Gao Xiaodi also rushed to the provincial capital from the Shanghai Stock Exchange. As the current leaders of the CPU team, they are the people who are truly responsible for front-line technology.

Together with Claude, the four of them began to discuss the ideas of the next generation architecture in Su Yuanshan's office.

Nowadays, Yuanxin and Xinghai have not enough technical background. Even if Su Yuanshan, a "genius", can only say that he can catch up with Intel. To truly surpass him, it is better to have the ability to achieve "mass production generation, reserve generation, and research and development generation".

Now that both CPU teams have completed their current designs, it is natural to intervene in the research and development of the next-generation architecture in advance.

"The 32-bit processor will be eliminated by the 64-bit processor, which is inevitable." Su Yuanshan turned the pencil in his hand. Although he spoke very quietly, his voice was extremely calm: "It doesn't matter how an amateur thinks it, but we must clearly recognize this."

"But when you take a big step, will you pull the egg?" Li Mingliu blew the ashes and his face was solemn - he learned this sentence from Su Yuanshan. Seeing that Claude looked at him in a daze, he immediately said it again in English.

Claude laughed: "We all agree that the 64-bit processor is the future, but it still needs the support of the operating system... The current operating system does not even count as 32-bit."

"If you walk too fast, you will easily become cannon fodder." Gao Xiaodi also nodded and smiled: "Don't be able to use our CPU because ours is too advanced...then it will be funny."

Seeing that the three of them were cautious about the 64-bit processor, Su Yuanshan couldn't help but smile and was quite relieved.

——What he feared the most was because he was too awesome, which led to all these buddies listening to their own pictures and becoming monsters of drawings and applause.

That would be boring.

"Yes, but we can't wait until the demand comes before we rush to solve the problem. That's just a work that only mediocre companies will do." Su Yuanshan first affirmed the concerns of several people and continued: "I'll make a bold prediction that even without us, a 64-bit processor will appear in only five years at most."

The three of them were all stunned.

Especially Li Mingliu, he looked at him very seriously.

Li Mingliu knew that if Su Yuanshan started to predict, he would really not run away.

——Did this guy hear some news?

It's impossible! Xinghai is a pure commercial enterprise there, not a spy company.

"And we have a 64-bit processor, which means another thing - we can completely get rid of Intel's x86 stick." Su Yuanshan said calmly.

Whether it is multi-core or 64-bit, these technologies that belong to the "near future" have actually been proposed. Even Intel is considering developing a 64-bit processor, and Amd has not lost much.

But they are all currently considering and are "seeing" future trends, but have not taken action.

Yuanxin and Xinghai didn’t see it, or they saw it, and they still thought it was a fantasy, it was a long time ago... and then we will make a profit from CPU first.

This kind of thinking is nothing wrong with small companies like Cyrix, after all, it is mainly about survival.

But for big companies, this is deadly.

When Cyrix sold itself to National Semiconductor, it sold it to VIA. In the end, it just took out a mii and m3, and then stopped cpu again.

The reason is very simple, VIA can't keep up.

When others' forward-looking technology has begun to be implemented and implemented, you are still struggling to follow the old paths they have already walked and cooperating with their old architecture. How do you play with others?

"So I suggest that Xinghai will start to explore the multi-core architecture forward-lookingly, while Shanghai Stock Exchange will explore the 64-bit instruction set."

Su Yuanshan paused and smiled, "Of course, I will be involved."

"How much force does that need to be put into?" asked Claude.
Chapter completed!