Skhynix Inc.

Korea University Research and Business Foundation

Kwangwoon University Industry-academic Collaboration Foundation

Young Ho Gong

Jae Hoon Chung

Donggyu Sim

Hoon Young Cho

Sung Woo Chung

Ye Bin Kwon

Woo Hyuck Park

According to a quantization interconnect apparatus and an operating method thereof according to the exemplary embodiment of the present disclosure, in a quantization artificial neural network accelerator system, the quantization is performed in the interconnect bus according to a precision without separate processing of the CPU/GPU so that as compared with the quantization by a host processor and an accelerator according to a quantization method of the related art, a number of instructions is reduced to improve the performance/memory efficiency. Further, a computational burden of the host process is reduced to reduce the power and improve the performance.

Apparatus of interconnect with on-the-fly quantization and operating method thereof

A hybrid memory system may include: a volatile memory; a nonvolatile memory; and a memory controller configured to a threshold value for a read-to-write ratio according to a refresh interval of the volatile memory, and to perform migration of a page between the volatile memory and the nonvolatile memory based on the threshold value and a read-to-write ratio of the page.

Hybrid memory system and refresh method thereof based on a read-to-write ratio of a page

Growing community of inventors

Seoul, South Korea

Young Ho Gong