Chapter 595 Call upon your comrades, I have something good!
Lou Xiao'e did not object to this suggestion. She thought that she probably wouldn't be able to cook today, so she didn't want Zhendong to go hungry.

Gao Zhendong brought the rice bowl, and the couple went straight to Sha Zhu's house.

"Hey, I just asked you for a favor yesterday, but you're busy eating it today. You're really something."

In front of his own people, Sha Zhu was still as talkative as ever. While busy adding dishes, he teased Gao Zhendong with a smile.

"Oh, by the way, collect the bills quickly, haha." Gao Zhendong didn't care. This place with Sha Zhu was one of the most relaxing places for him. This kid was cunning, but he didn't use it on his own people.

"Zhendong, guess what our department wanted me to do today?" Lou Xiao'e, who was tutoring He Yushui, looked up while He Yushui was doing some calculations.

Gao Zhendong probably guessed it, and he was quite quick. But he didn't tell her the answer directly, because that would have spoiled Lou Xiaoe's mood.

He didn't know that as soon as the technical department of the Third Branch Factory took the materials over, Lou Xiao'e's department quickly completed the information, except for the technical information that needed to be studied.

The department head was even more delighted when he saw the Defense Work Committee vaguely visible in the materials. Although this thing seems to have a low technological content, its specifications are not low.

"What do I want to see you for?" Gao Zhendong pretended to be stupid.

"The department head said that I am a good student and wanted me to participate in a microbiology project to help the teachers." Lou Xiao'e was busy vomiting just now and only now did she calm down and talk about this matter.

Gao Zhendong was surprised: "Ah? Really? That's great, really amazing. Microorganisms, I don't know anything about them." His tone was like coaxing a child, but Lou Xiao'e still felt very proud listening to it.

Sha Zhu got excited when he heard this: "Microbiology? Oh, your school is the Second Medical University of Beijing, right? What a coincidence, it should be our topic."

Lou Xiao'e also thought it was a coincidence: "Really? Then why didn't I see you?"

Sha Zhu smiled and said, "I was responsible for the cooking technology of that project, and the comrades from Zhendong were responsible for other technologies, so the ones who went there were from the technical department of their third factory. I was still cooking noodles in the factory."

Several people chatted and laughed, and Lou Xiaoe expressed her learning experience: "Zhendong, don't tell me, I read the knowledge of microorganisms, it's very interesting."

What she studied should be a major similar to future clinical medicine. She did not learn any knowledge of microorganisms, but since she wanted to get into this subject, she had to make up for it.

After learning this, Lou Xiao'e became interested. This little world is so interesting.

Bureau Chief: It’s really fun.jpg.

Gao Zhendong smiled and said, "If you are interested, just learn it. It is always good to have many skills."

Lou Xiao'e nodded vigorously: "Well, find a book for me."

There are not too many books on the study of microorganisms.

For Lou Xiao'e, Gao Zhendong is the only thing she can think of when she is in doubt, and she doesn't need to think about anything else.

No school? There is Zhendong.

No direction? There is Zhendong.

No textbooks? We still have Zhendong.

Gao Zhendong agreed immediately: "Okay, you take a look at what you have now, and I'll check it out for you later."

Sha Zhu couldn't get a word in their conversation, but instead listened to He Yushui with fascination. "Sister Xiao'e is so amazing, I want to be like her."

While eating, Gao Zhendong discovered that one of the dishes was noodles, and it was salty.

Damn it, this kid, take revenge on me.
-
The DIP sockets from Factory 1274 cannot be obtained in a short time. After all, it takes time from design to mold to production. However, the IC schematic circuit board in Gao Zhendong's hand has been soldered.

Although it looks a bit ugly and there are a lot of flying wires, I finally debugged the circuit.

The specifications of the entire circuit board are roughly the area of ​​a DJS-60D, about 50*50cm, but the entire area is not used.

Gao Zhendong connected the circuit board to DJS-59. There was no serial port, so a lot of wires were connected. This is how a parallel port is, with at least one wire for one bit of data. If the addresses are not reused, it would be even more exaggerated.

Fortunately, Gao Zhendong had already designed a simple peripheral bus for DJS-59 and 60, which could partially multiplex the address and data lines, making the situation slightly better. However, the cost was that it would reduce the speed and increase the programming complexity of the underlying driver.

Gao Zhendong first wrote a simple program on DJS-59. There was nothing special about this program. It was not even targeted at the circuit board, but at DJS-59 itself.

The program is very simple. Multiply two single-byte numbers 15 and 15 10 times! The result is 225, which can still fit in one byte. While calculating, calculate the total time taken.

It is multiplied separately, and the two multipliers each time are the same two 15s, instead of multiplying 15 10 times in a row. The number 15 to the power of 10 is not enough to be described as an astronomical figure. Of course, it is still insignificant compared to such abnormalities as Gurley's number and Tree3.

The program was simple and could be written quickly. Gao Zhendong entered the compile and run instructions.

The program started running, and compared to the speed of the computer, it took a long time. Looking at the time, Gao Zhendong said "tsk" and shook his head. He knew the approximate range of the result, which would definitely be ugly. Now he just wanted to confirm the specific number.

Then Gao Zhendong started to write another program. This program was a bit difficult to write because it mainly required direct operation of the underlying hardware.

The operation is the same, repeated 10 times 15*15.

Moreover, Gao Zhendong had to deduct the communication time in the program, because this was the time when DJS-59 communicated with the test circuit board, controlled it to perform calculations, and then transmitted the data back.

The calculation may be very fast, but the communication time is long. Gao Zhendong's goal is to deduct the communication time to roughly calculate the total time required for the calculation.

Fortunately, this thing is not complicated, and Gao Zhendong is not slow.

An hour later, Gao Zhendong completed the compilation and started the program.

This time it took longer than the time calculated by DJS-59. Gao Zhendong had expected this and was very patient.

There is no way. The communication speed of the peripheral bus is far slower than that of the internal bus.

After a long time, a number popped up on the screen. Gao Zhendong took a look and smiled. This was what he wanted.

Compared to the calculations using the DJS-59, after deducting the communication time, this IC experimental circuit board is ridiculously fast at the same frequency.

——Twenty-five times!
This is what Gao Zhendong wants.

——Single-cycle hardware multiplier!
DJS-59 does not have a hardware multiplier. Not to mention a single-cycle hardware multiplier, there is not even a multi-cycle hardware multiplier that controls the adder to achieve multiplication.

The former can complete the multiplication calculation within one instruction cycle, but the latter may not. For example, the 51 single-chip microcomputer can complete a multiplication operation in 4 instruction cycles.

Needless to say, the former is faster but more expensive, while the latter is slightly faster and slightly more expensive.

The number of DJS-59 is huge. It has no hardware multiplier and can only complete the multiplication operation through program instructions, controlling the adder and register step by step.

For DJS-59, it takes about 15 instructions to complete an 8-bit integer multiplication operation, and there are many multi-cycle instructions among them. In total, it takes about 25 instruction cycles to complete a multiplication operation.

And this is only the case for 8 bits. If it is expanded to 16 bits or 32 bits, the number will increase.

As for floating point numbers, the situation is even worse.

This is the weakness of DJS-59, and also the weakness of most early general-purpose CPUs. It is not capable of performing more advanced mathematical operations.

However, for signal processing, multiplication is a basic operation and the most commonly used operation.

This is why general-purpose CPUs are so weak when it comes to signal processing. They can’t do the math; it’s a natural defect.

But Gao Zhendong's next step, everything, the ultimate goal is basically aimed directly at radar. Relying on DJS-60D, even if it is IC-based, is still a weak chicken and not good enough.

So Gao Zhendong thought about making a hardware multiplier himself, and his goal was to create a single-cycle floating-point hardware multiplier. He praised the Internet and his mentor. In his previous life, he had implemented this thing in VHDL and was very clear about its structure.

VHDL, hardware description language, is one of the IC design languages ​​on CPLD/FPGA, which can directly design IC hardware structure.

Although the final result of VHDL is based on logic units, which is different from the direct connection using transistors or logic gates, Gao Zhendong is very familiar with the algorithm it is based on and can still convert it.

This is the reason why the circuit board of this multiplier is so large. If it is just a hardware multiplier implemented by an adder, then it can be added inside the DJS-60D. The cost and area will not increase much, but correspondingly, the performance will not increase much either. This needs to be done, but it is not enough for Gao Zhendong's needs!
What Gao Zhendong developed is a single-cycle hardware multiplier for 16-bit floating-point numbers, which is absolutely far ahead.

Gao Zhendong happily replaced the multiplier of the second program with two 16-bit floating-point numbers and started the calculation again.

This time, he did not torture DJS-59. This kind of calculation was too torturous for the old guy DJS-59, although it was still much faster than humans.

Soon, the calculation results and time consumed popped up.

Gao Zhendong checked the calculation results he had prepared and found them to be exactly the same. As for the time, it was the same as calculating the multiplication of 8-bit integers.

This is the charm of the single-cycle hardware multiplier. As long as it does not exceed its design specifications and the numbers involved in the calculation are within its design range, no matter what is calculated, it will be at the same speed - a single instruction cycle.

Gao Zhendong laughed out loud. Although this was only an intermediate result and just a principle circuit board, for quite a few comrades, it could be used after a few modifications. After all, quite a few radars did not have high requirements for size.

Moreover, compared with the previous back-end signal processing circuit, this 50*50cm board is definitely small and exquisite!

Gao Zhendong happily ran to the confidential room and asked for the phone number of the leader of the Defense Work Committee.

On the phone, he only said one sentence to the leader of the Defense Work Committee: "Leader, please gather comrades with sufficient rank to work on radar. I have something good!"

(End of this chapter)