Minsik Cho

MEMORY-EFFICIENT DIFFERENTIABLE WEIGHT CLUSTERING FOR LARGE LANGUAGE MODEL COMPRESSION

Mirroring matrices for batched cholesky decomposition on a graphic processing unit

Large model support in deep learning

SENSOR COMPENSATION USING BACKPROPAGATION

System, method, and recording medium for mirroring matrices for batched cholesky decomposition on a graphic processing unit

ISA-based compression in distributed training of neural networks

TRANSFER LEARNING WITH AUGMENTED NEURAL NETWORKS

Method to measure similarity of datasets for given AI task

Hamming distance based robust output encoding for improved generalization

Separating public and private knowledge in AI

Cloud computing data compression for allreduce in deep learning

Matrix-factorization based gradient compression

Method for flexible, fast all-reduce on arbitrary tree topology

Pessimistic scheduling for topology optimized workload placement

Pipelining multi-directional reduction

Decentralized distributed deep learning

Large model support in deep learning

System, method, and recording medium for mirroring matrices for batched Cholesky decomposition on a graphic processing unit

System, Method, and recording medium for mirroring matrices for batched Cholesky decomposition on a graphic processing unit

System, method and computer program product for accelerating iterative graph algorithms by memory layout optimization

Variable ISA vector-based compaction in distributed training of neural networks

ISA-based compression in distributed training of neural networks

Multi-directional reduction in large scale deep-learning

Parallel quicksort

Memory efficient convolution operations in deep learning neural networks

System, method and computer program product for accelerating iterative graph algorithms by memory layout optimization

System, method, and recording medium for mirroring matrices for batched Cholesky decomposition on a graphic processing unit

Radix sort acceleration using custom asic

Parallelized in-place radix sorting

System, method, and recording medium for mirroring matrices for batched cholesky decomposition on a graphic processing unit

LLVM-based system C compiler for architecture synthesis

Adaptive radix external in-place radix sort

Condition analysis

Parallel quicksort

In-cycle resource sharing for high-level synthesis of microprocessors

Automating a microarchitecture design exploration environment

Automating a microarchitecture design exploration environment

Automating a microarchitecture design exploration environment

Lookup table sharing for memory-based computing

Lookup table sharing for memory-based computing

Parallelized in-place radix sorting

Parallelized in-place radix sorting

Radix sort acceleration using custom ASIC

Parallelized in-place radix sorting

Parallelized in-place radix sorting

Radix sort acceleration using custom ASIC

Mapping a lookup table to prefabricated TCAMS

Lookup table sharing for memory-based computing

Lookup table sharing for memory-based computing

Structured Latch and Local-Clock-Buffer Planning

Relative ordering circuit synthesis

Structured latch and local-clock-buffer planning

Network flow based datapath bit slicing

Soft hierarchy-based physical synthesis for large-scale, high-performance circuits

Method and system for performing global routing on an integrated circuit design