Comparison of NorFlash, NandFlash and eMMC (1)

Source: 　　Editor: Jacquelyn Update Time :2019-01-25

This paper mainly introduces NorFlash, NandFlash and eMMC, and emphatically expounds their differences.

　　NorFlash

NorFlash is one of the two main non-volatile flash memory technologies in the current market. Intel first developed NorFlash technology in 1988, revolutionizing the situation that EPROM (Erasable Programmable Read-Only-Memory) and EEPROM (Electrically Erasable Read-Only-Memory) dominated the market. Then, in 1989, Toshiba published NandFlash architecture, which emphasizes lower cost per bit, higher performance, and easy upgrade through the interface like a disk. NorFlash is characterized by chip executing in place (XIP) so that applications can run directly within flash without having to read the code into system RAM. The transmission efficiency of NOR is very high, and it has high cost-effectiveness in small capacity of 1~4MB, but the low writing and erasing speed greatly affects its performance. The structure of NAND provides extremely high unit density, leading to high storage density, and fast speed in writing and erasing. The difficulty in applying NAND is that flash management requires a special system interface. NOR is slightly faster than NAND in reading, while NAND is much faster than NOR in writing, which should be considered in the design.

Performance comparison

Flash memory is a non-volatile memory that can be erased and reprogrammed memory unit blocks called blocks. Write operations of any flash device can only be performed in empty or erased cells, so in most cases, the erasure must be performed before write operation. It is very simple for NAND device to perform erasure operations, but NOR requires that all bits in the target block should be written as 0 before erasure.

NOR device is erased in blocks of 64-128kb with writing and erasing operation of 5s. In contrast, NAND device is erased in blocks of 8-32kb and it only takes 4ms to perform the same operation at most.

The difference in block size when performing erasure further widens the performance gap between NOR and NAND. Statistics show that for a given set of write operations, especially when updating small files, more erasure operations must be performed in NOR-based unit. In this way, when choosing a storage solution, designers must weigh the following factors.

1、 NOR reads slightly faster than NAND.

2、NAND writes much faster than NOR.

3、4ms erasing speed of NAND is much faster than 5s of NOR.

4、Most write operations require erasing first.

5、NAND erasure unit is smaller, so the corresponding erasure circuit is less.

In addition, NAND is more complex than NOR in practical application. Nor can be used directly, and the code can be run directly on it. However, NAND requires an I/O interface, so a driver is required for use. But today's popular operating systems support NAND flash, as well as Linux kernel.

Detailed annotation

Because NAND is often used interchangeably with NOR, many industrial people are also confused about the superiority of NAND technology over NOR. In most cases, when flash is only used to store a small amount of code, NOR is more suitable. NAND is an ideal solution for high data storage density.

NorFlash is characterized by chip executing in place (XIP) so that applications can run directly within flash without having to read the code into system RAM. The transmission efficiency of NOR is very high, and it has high cost-effectiveness in small capacity of 1~4MB, but the low writing and erasing speed greatly affects its performance.

The structure of NAND provides extremely high unit density, leading to high storage density, and fast speed in writing and erasing. The difficulty in applying NAND is that flash management requires a special system interface.