Master Lu releases the top 10 AI chips for 2019


According to Master Lu’s AI ​​chip rankings for the first half of 2019, Qualcomm Snapdragon 855 remains the best. In addition to the SD855, Apple A12, and MediaTek P90 is second and third respectively on the list. This is the first time that a MediaTek chip is on Master Lu top 10 AI chips. Master Lu AI performance runs on the new AImark2.0. With the new systems and algorithms, ARM, Qualcomm, HiSilicon, MediaTek, Samsung, and other AI core SoC can be comprehensively evaluated.

Master Lu AI 2019 chip ranking

MediaTek’s Helio P90 is a flagship SoC and the AI capability is at the flagship level. In addition to the improvement of CPU and GPU, Helio P90 also adds AI core APU2.0. This can handle multiple AI tasks simultaneously. Officially, APU 2.0 can achieve 50 times AI performance improvement.

Gizchina News of the week


Master Lu top 10 AI chips for 2019

  • Qualcomm Snapdragon 855
  • Apple A12
  • MediaTek Helio P90
  • Huawei Kirin 980
  • Qualcomm Snapdragon 845 AIE
  • Snapdragon 845
  • Qualcomm Snapdragon 710 AIE
  • Snapdragon 670 AIE
  • Qualcomm Snapdragon 710
  • Qualcomm Snapdragon 835

American chipmaker, Qualcomm, completely dominates the mid-range section while others lag behind. Recent mid-range chips such as Snapdragon 710 AIE and the Snapdragon 670 AIE is ahead of 2017 flagship, Snapdragon 835. However, the Snapdragon 700 series will definitely contend with the new Huawei Kirin 810 mid-range SoC. Huawei’s Kirin 980 SoC is a top AI chip. According to Huawei’s timeline, Kirin’s flagship processor will be updated in the second half of this year. Kirin focuses on AI optimization and the new self-developed DaVinci architecture NPU features on the Kirin 810. Kirin 990 will promise to beat the likes of SD855 and Apple A12 in AI performance.

Via

Disclaimer: We may be compensated by some of the companies whose products we talk about, but our articles and reviews are always our honest opinions. For more details, you can check out our editorial guidelines and learn about how we use affiliate links.

Previous Xiaomi Mi 9 gets MIUI 10 based on Android Q
Next Google Fuchsia OS adds support for Snapdragon 835 SoC