The difference between ASIC technology and FPGA technology to realize the productization of memory chips

Memory chip is the specific application of the concept of embedded system chip in the storage industry. Therefore, whether it is a system chip or a memory chip, it is through embedding software in a single chip to achieve multi-function and high performance, as well as support for multiple protocols, multiple hardware, and different applications.

Memory chip is the specific application of the concept of embedded system chip in the storage industry. Therefore, whether it is a system chip or a memory chip, it is through embedding software in a single chip to achieve multi-function and high performance, as well as support for multiple protocols, multiple hardware, and different applications.

Storage chip technology mainly focuses on the application of enterprise-level storage systems, providing high-quality support for access performance, storage protocols, management platforms, storage media, and a variety of applications. With the rapid growth of data and the increasing importance of data to businesses, the data storage market is evolving rapidly. From DAS, NAS, SAN to virtual data center, cloud computing, all of them pose great challenges to traditional storage design capabilities.

For storage and data disaster recovery, virtualization, data protection, data security (encryption), data compression, data deduplication, thin provisioning and other functions have increasingly become standard functions of the solution. Managing more data with fewer resources is becoming an inevitable trend in the market. However, these optimization functions mentioned above all require a lot of CPU resources. How to quickly realize the process of multi-functional productization and ensure the high performance of the optimized system is the market driving force for the development of memory chips.

Classification of memory chips

According to whether the storage chip can keep data continuously after power off, it can be divided into two types: volatile and non-volatile.

Among them, volatile memory chips can be divided into DRAM and SRAM. Compared with DRAM and SRAM: SRAM requires a large number of transistors for a single memory cell and has a faster read and write speed, but the overall price is more expensive and the capacity is small. Use in more demanding places (CPU’s primary cache, secondary cache, etc.). However, a single DRAM storage unit requires only one transistor and one capacitor. It has a higher overall integration, a larger capacity, and a significant price advantage. However, the speed will be lower than that of SRAM, and it is mostly used in the system memory of computers, mobile phones and other devices.

The non-volatile memory chip can be divided into NAND FLASH and NOR FLASH, comparing NAND and NOR: NOR is characterized by being executed in the chip, that is, the application program can run directly on the FLASH, so the efficiency of reading Very high, but only when the capacity is small (1~16MB) has a higher cost performance. NAND is characterized by larger storage capacity and better rewriting speed than NOR, and is widely used in U disks, solid state drives and other fields.

Both ASIC technology and FPGA technology can be used to realize the commercialization of memory chips.

Specifically:

ASIC (application specific integrated circuit) has been widely used in the storage and network industries. In addition to greatly improving the system’s processing capacity and speeding up product development, ASICs are more suitable for mass-produced products and complete standardized designs based on fixed requirements. In the storage industry, ASICs are usually used to implement certain functions of storage product technology, used as accelerators, or alleviate the overall performance degradation of the system caused by the excessive load on the CPU caused by a large number of optimization techniques.

FPGA (Field Programmable Gate Array) is the highest level of application-specific integrated circuits (ASIC). Compared with ASIC, FPGA can further shorten the design cycle, reduce design cost, and have higher design flexibility. When it is necessary to change the completed design, the redesign time of ASIC is usually calculated in months, while the redesign time of FPGA is calculated in hours. This enables FPGAs to have market response speeds unmatched by other technology platforms.

The new generation of FPGA has excellent low energy consumption, fast and fast (most tools calculate in picoseconds-ten billionths of a second) characteristics. At the same time, manufacturers can reconfigure FPGA function modules and I/O modules, and can also program them online to achieve system online reconfiguration. This allows FPGA to build a real-time custom soft-core processor based on computing tasks. Moreover, the function of the FPGA is not limited, and it can be a memory controller or a processor. The new generation FPGA supports a variety of hardware, with programmable I/O, IP (intellectual property) and multi-processor cores. With these comprehensive advantages, FPGAs are used by some storage vendors to develop full-featured products of the storage chip architecture.

China’s memory chip market is vast

According to statistics from authoritative organizations, China’s memory chip industry as a whole continues to develop. The market size has grown from US$4.52 billion in 2014 to US$12.38 billion in 2019, with a compound annual growth rate of 28.6%. It is expected that China’s memory chips will continue to maintain a steady growth trend in the future. By 2024, China’s memory chip market share is expected to exceed 52.26 billion U.S. dollars, accounting for 14% of the global market. The scale of China’s packaging and testing market in 2019 is about 34.061 billion U.S. dollars, accounting for about 60% of the global market. The storage packaging and testing industry is the leading driving force of my country’s semiconductor industry, and the high-end storage packaging and testing industry is currently in a state of rapid development. However, the localization is extremely low, and the domestic substitution space is huge.

The Links:   LM170E03-TLC1 3208H1-1F