XC6VLX240T-1FF1759C_XC6VLX550T-1FF1759C Introduction

The accelerated computing of CPU+GPU+FPGA is undoubtedly aimed at the blue ocean of the data center field. Intel has repeatedly stated that it is a data-centric company, while NVIDIA has recently proposed acquisitions and released various The determination to "take the high ground" is constantly revealed in new products….

Recently, as the head of the CEO, Peng Rongkui introduced Cylinth's future vision and strategic blueprint for the first time, and released a new breakthrough product that surpasses FPGA-ACAP (AdaptiveCompute Acceleration Platform, AdaptiveCompute Acceleration Platform), which enables Cylinth Inspiration goes beyond the limitations of FPGAs to support the rapid innovation of many different technologies from end-to-edge to cloud. Since joining Xilinx in 2008, the company has won the championship for three consecutive times in the 28 nm, 20 nm and 16 nm three-generation process products, and won the first place in the industry. Broad application field development.

XC6VLX240T-1FF1759C_XC6VLX550T-1FF1759C

XC5VLX85-3FFG676C

Softnautics chose Xilinx technology to implement this solution because it integrates both the Vitis™ AI stack and powerful hardware capabilities. Today, Xilinx's rich and powerful platform supports 70% of new developments, leading the way in FPGA-based system design.

The dynamic power problem is solved with low-capacitance circuits and custom modules. The power consumption of the multipliers in the DSP block is less than 20% of the power consumption of the multipliers built in the FPGA fabric. Given the wide range of leakage current distributions that can result from manufacturing variations, low leakage current devices can be screened to effectively provide devices with core leakage power consumption below 60%. To reduce static power dissipation, longer-channel and higher-threshold transistors are also used across the board. A variety of power-driven design techniques are used in the design of FPGAs. Taking the Xilinx Virtex series as an example, because the configuration memory cells can occupy 1/3 of the number of transistors in the FPGA, a low leakage current "midox" transistor is used in this series to reduce the leakage current of the memory cells.

Similar to AI inference implementations, non-AI preprocessing and postprocessing functions begin to require some form of acceleration. There is also a third challenge, and this is a lesser known one, which arises because AI inference cannot be deployed on its own. These traditional processing functions must run at the same throughput as the AI functions, with the same high performance and low power consumption. For example, an image may need to be decompressed and scaled to meet the data input requirements of an AI model. True AI deployments often require non-AI processing, either before or after AI capabilities.

However, with opportunities come challenges. AI inference, the process of using trained machine learning algorithms to make predictions, whether deployed in the cloud, edge, or on-device, requires excellent processing performance within a tight power budget. The prevailing view is that this requirement cannot be met by CPUs alone, and that some form of computational acceleration is needed to handle AI inference workloads more efficiently.

XC6VLX240T-1FF1759C_XC6VLX550T-1FF1759C

XC5VSX50T-2FF665C

XC6VLX240T-1FFG784I XC6VLX240T-2FF1156C XC6VLX365T-1FFG1759C XC6VLX240T-1FFG784C XC6VLX240T-3FF784C XC6VLX240T-3FFG784C XC6VLX365T-1FF1759C XC6VLX240T-3FFG1156C XC6VLX365T-2FF1156C XC6VLX365T-2FF1759I XC6VLX240T-3FFG1759C XC6VLX365T-2FF1156I XC6VLX550T-1FFG1760I XC6VLX550T-2FF1760C XC6VLX550T-2FF1759I XC6VLX550T-1FFG1759C XC6VLX365T- 1FF1759I XC6VLX365T-1FF1156C XC6VLX365T-1FF1156I XC6VLX550T-2FF1759C.

XC6VLX130T-2FF784I XC6VLX130T-3FFG784C XC6VLX195T-1FF784I XC6VLX130T-2FFG1156C XC6VLX130T-2FFG784C XC6VLX130T-2FF484I XC6VLX130T-2FFG1156I XC6VLX130T-1FF484I XC6VLX130T-3FF784C XC6VLX130T-1FFG1156I XC6VLX130T-1FFG1156C XC6VLX130T-3FFG1156C XC6VLX195T-1FF1156C XC6VLX130T-3FF484C XC6VLX130T-3FFG484C XC6VLX130T-2FF484C XC5VTX240T- 2FF1759I XC5VTX240T-2FFG1759C XC5VTX240T-2FFG1759I XC6VLX130T-1FFG484C XC6VLX130T-1FFG484I.

XC6VLX240T-1FF784I XC6VLX195T-2FF1156I XC6VLX195T-2FF1156C XC6VLX195T-2FF784I XC6VLX195T-2FF784C XC6VLX130T-3FF1156C XC6VLX130T-2FFG484C XC6VLX195T-3FFG1156C XC6VLX130T-2FFG784I XC6VLX240T-1FF1156C XC6VLX195T-3FFG784C XC6VLX240T-1FF1759C XC6VLX240T-1FF1156I XC6VLX195T-1FF784C XC6VLX130T-2FF784I XC6VLX130T-3FFG784C XC6VLX195T- 1FF784I XC6VLX130T-2FFG1156C XC6VLX130T-2FFG784C XC6VLX130T-2FF484I XC6VLX130T-2FFG1156I XC6VLX130T-1FF484I XC6VLX130T-3FF784C XC6VLX130T-1FFG1156I .

XC4VLX200-11FFG1513I XC4VLX200-12FF1513C XC4VLX200-12FFG1513C XC4VLX200-10FFG1513C XC4VLX200-10FFG1513I XC4VLX200-11FF1513C XC4VLX40-10FF1148I XC4VLX25-11FFG668C XC4VLX40-10FF668I XC4VLX40-10FF1148C XC4VLX25-12FFG668C XC4VLX40-10FF668C XC4VLX25-12SFG363C XC4VLX25-12FF668C XC4VLX25-11SF363I XC4VLX60-10FF1148I XC4VLX25- 11SFG363I XC4VLX25-11SF363C XC4VLX25-11FF668I XC4VLX25-11SFG363C XC4VLX25-11FFG668I XC4VLX25-11FF668C XC4VLX160-10FFG1148I.

XC6VLX240T-1FF1759C_XC6VLX550T-1FF1759C

Especially in the era of artificial intelligence, Xilinx also hopes to use this advantage to achieve the inheritance of Intel and Invida. The introduction of acap will help salespeople compete with higher-level competitors in new markets. In the face of competitors such as Intel and Nvidia, we should focus on the core competitiveness of sales, that is, the hardware level can be very flexible and adaptable according to different workloads and efforts, rather than competing with them in the traditional field. This equates to a successful promotion of sales, which will compete on a higher level with the likes of Intel and Nvidia. Since larger competitor altera has fallen into Intel's pocket in 2015, new competitors in sales have become Intel, nvida, and others. Flexibility is one of the core selling points of acap. Obviously, this is for Intel and Nvidia.

In July 2016, Xilinx said it would become an all-programmable company within the next five years, using its strengths to help customers differentiate and target emerging areas such as cloud computing, Internet of Things, 5G wireless and embedded vision. This is an adaptive computing acceleration platform. At present, the main series of FPGA products include high-performance virtex series, mid-range kintex series and low-cost artix and spartan series. Cyrus defines it as a new product different from CPU, GPU and FPGA. In fact, in 2014, Xilinx began work on a new generation of products that debuted in early 2018.