Although he has been away from Yuanxin for two years, Jiang Tao has never ranked himself outside Yuanxin in terms of system. Seeing Su Yuanshan saying two things in a very formal manner, he also became serious.

"Well, you say. ”

Su Yuanshan smiled: "In a few days, Senior Brother Gao Xiaodi will pull the entire CPU team of Yuanxin over." ”

"I'll wipe it?" Jiang Tao suddenly tilted his neck forward when he heard it.

Then he immediately realized that he had reacted a little bigger, and smiled: "That guy is going to make a fuss when he comes here." ”

Su Yuanshan laughed.

Jiang Tao and Gao Xiaodi are classmates, and even Gao Xiaodi is still the brother who sleeps on his top bunk.

At the beginning, Su Yuanshan joked with Gao Xiaodi and asked him to come over to make a cache, but Gao Xiaodi's excuse was not to come, and he was embarrassed to bully Jiang Tao.

"Hehe, after pulling it over, the cache team will be directly merged into the CPU team, and then return to the remote core architecture, and then it will be separated from your side in the future. ”

Jiang Tao nodded naturally, but immediately realized a problem.

There's someone else downstairs here!

In other words, there are still dozens of people in the cache team who are from Yuanzhong Microelectronics!

And then that's a long story.

——When Su Yuanshan started to work on CPUs, there were only seventy or eighty people in total. Among these seventy or eighty people, except for the dozen or so people who have been following Li Mingliu to support Chengguang, the remaining fifty or sixty people are all "recruits" led by Gao Xiaodi.

At this point, Su Yuanshan has to engage in architecture and cache, which is really a bit unclear. So Su Yuanshan hit the idea to Yuanzhong Microelectronics - he asked Li Mingliu to come to Yuanzhong with only a few core team members, and then directly pulled half of the people from Yuanzhong away.

You must know that Yuanzhong was only in his early 100s at that time, and he was gritting his teeth to support Su Yuanshan.

Now that the cache is done, Jiang Tao is still waiting for the return of people - those veterans who have been tempered by Li Mingliu are all real treasures.

So Jiang Tao immediately became a little nervous: "When will my people pay me back?"

Li Mingliu threw a cigarette to Jiang Tao, and said with a smile: "Old Jiang, don't be so stingy!"

"I wipe ...... Xiaoshan, I was talking about joint development. Jiang Tao stared at Su Yuanshan: "Their salaries are all paid by me!"

Su Yuanshan was a little embarrassed by Jiang Tao, and said with a smile: "Didn't you give you a subsidy for joint development? ”

“......”

"Senior brother, what about people, I really can't pay you back. Su Yuanshan knew that he was a little unkind to do this, and thought for a while: "Otherwise, let's discuss a compensation plan." ”

"What's the plan?"

"We'll talk about it later. Su Yuanshan smiled and said, "Let's talk about the second thing first." ”

“......”

"The second thing is that the new team newly established by Lao Zhu is specialized in flash memory, to be precise, it is specialized in NAND flash memory, you should understand. ”

Jiang Tao nodded.

Su Yuanshan said: "That's the case, the application of flash memory, there must be one, and it hasn't been launched now, the only reason is that the price is too expensive." ”

"But we have a basic common sense that ...... In the field of semiconductors, any problem caused by high prices can be broken through, or it is worth breaking through. ”

"Therefore, I hope that you can also send a small team to cooperate with the main control chip. ”

Su Yuanshan said and looked at Jiang Tao: "You don't need me to explain the control mode of flash memory, right?"

Here, Li Mingliu smiled again: "You'd better say it." ”

Jiang Tao glared at Li Mingliu: "Who do you look down on? A MOSFET (MOS field-effect transistor) stores electrons through a doped layer, and it can maintain a state even after power-off, which is the basic principle of memory. Then design a chip, obtain the 0,1 state of the memory, then the data distribution can be obtained, and then the voltage can be applied according to the read and erase commands to complete the data operation. ”

"Finally, communicate with the protocol interface of the computer......"

Su Yuanshan looked at Jiang Tao in surprise: "Senior brother is awesome...... When did you find out?"

“...... After Lao Li came back, he started to do this, is there anything wrong with me touching it?" Jiang Tao rubbed the cigarette that Li Mingliu threw at him on the table a few times, and lit it with a click.

Su Yuanshan smiled and nodded: "The principle of this thing is actually quite simple, and it is always inseparable from the MOS field tube to turn it over and over." ”

Jiang Tao said: "But the cost cannot be reduced is always a big problem. ”

"So we're just going to solve the cost problem. ”

Su Yuanshan said with a smile.

......

NAND flash memory is still in its infancy, and it is far from being commercialized.

One of the most fundamental reasons is that it is expensive.

The current architecture is still just the SLC architecture, Single Level Cell. It has only two variations, 0 and 1, in one unit, and can only store 1 bit of data.

It has the advantage of being fast, stable, and long-lived – theoretically up to 100,000 times of full erase life.

But the point is also obvious, the capacity is low, the cost is high. In later generations, it will only be used in the industrial field in extreme environments and other fields regardless of cost.

However, cost has always been the biggest obstacle to the popularization of a technology product, and it is also the easiest to get rid of.

So a few years later, Intel got a new architecture, MLC - Multi Level Cell.

Compared to SLC, it can store 2 bits of information per cell.

Correspondingly, the process is more complex, the reliability is reduced, the read and write speed is reduced, and the service life is exponentially reduced.

But even so, it's still a little expensive and hasn't really brought widespread use to flash memory.

What really popularized flash memory was actually TLC - Trinary Level Cell, which translates to triple cell.

It can store 3 bits of information per cell, which requires more complex process and voltage control.

The cons, as always, are the cons.

However, it is the absolute hero who has brought flash memory into thousands of households.

As a result, QLC was born later - each cell unit can store 4 bits of information, with a larger capacity, but slower, shorter lifespan, but the cost can also be compressed to a lower level.

Moreover, Su Yuanshan, who came from later generations, knew that in the development process of flash memory products, the architecture of flash memory was only one of the factors restricting the read and write speed of the product, and it was not even the biggest factor.

The biggest factor is actually the interface protocol standard for data transmission, followed by the main control chip and related technologies, and finally the architecture.

Just like the upcoming USB1.0 protocol, although under the initiative of Yuanxin and Xinghai, a more radical scheme has been adopted, and the transmission rate at full speed is only 48Mbps - which is already four times the historical 12Mbps.

Under this protocol, even if you use the most awesome main control chip and the most awesome flash memory particles, it is slow.

Therefore, the future of flash memory must be promoted at the same time by the protocol, master control, and granular architecture.

......

Su Yuanshan came over this time, mainly to point out two directions to Lao Li's side.

The first direction is to turn a single-layer structure into a multi-layer, so that as many transistors can be stacked per unit area.

The second direction is, of course, MLC.

Coincidentally, the underlying technologies and principles related to these two directions ...... Su Yuanshan understands.

But the irritability was that he didn't know how to skillfully guide Li Mingliu and them to the right path.

Just like his attitude towards his senior brothers, Li Mingliu and them are also the cornerstone of Yuanxin, and they have great uses. Unless it is a last resort, it is impossible for Su Yuanshan to throw out the plan in person and wait for these people to applaud him.

That doesn't do the far core any good.

Book Reading House