Inventor

DAS DIPANKAR

IN56 patents

⚠️ This page may combine multiple inventors who share the name “DAS DIPANKAR”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

DAS DIPANKAR

INTEL CORP

Abstraction layers for scalable distributed machine learning

Communication optimizations for distributed machine learning

Optimized compute hardware for machine learning operations

Technologies for scaling deep learning training

Abstraction library to enable scalable distributed machine learning

Dynamic precision management for integer deep learning primitives

Apparatus and method for vector multiply and accumulate of packed bytes

Scaling half-precision floating point tensors for training deep neural networks

Scaling half-precision floating point tensors for training deep neural networks

Apparatus and method for vector multiply and accumulate of packed words

Optimized compute hardware for machine learning operations

Dynamic precision management for integer deep learning primitives

Utilizing structured sparsity in systolic arrays

Abstraction layers for scalable distributed machine learning

Dynamic precision management for integer deep learning primitives

Hardware implemented point to point communication primitives for machine learning

Data parallelism and halo exchange for distributed machine learning

Dynamic precision management for integer deep learning primitives

Dynamic precision management for integer deep learning primitives

Incremental precision networks using residual inference and fine-grain quantization

Communication optimizations for distributed machine learning

Incremental precision networks using residual inference and fine-grain quantization

Apparatuses, methods, and systems for access synchronization in a shared memory

Apparatuses, methods, and systems for access synchronization in a shared memory

Circuitry for low-precision deep learning

Abstraction library to enable scalable distributed machine learning

Dynamic precision management for integer deep learning primitives

Abstraction layers for scalable distributed machine learning

Optimized compute hardware for machine learning operations

Data parallelism and halo exchange for distributed machine learning

Scaling half-precision floating point tensors for training deep neural networks

Scaling half-precision floating point tensors for training deep neural networks

Scaling half-precision floating point tensors for training deep neural networks

Communication optimizations for distributed machine learning

Utilizing structured sparsity in systolic arrays

Instructions for fused multiply-add operations with variable precision input operands

Incremental precision networks using residual inference and fine-grain quantization

Instructions for fused multiply-add operations with variable precision input operands

Instructions and logic for vector multiply add with zero skipping

Instructions for fused multiply-add operations with variable precision input operands

Instructions and logic for vector multiply add with zero skipping

Conversion hardware mechanism

Hardware implemented point to point communication primitives for machine learning

DAS DIPANKAR

Recovering from stack corruption faults in embedded software systems

Method and apparatus for operational-level functional and degradation fault analysis

PRAMANA INC

System and methods for detecting and cleaning contaminants from an imaging optical path

System and method for automated calibration for a scanning system

SPECTRAL INSIGHTS PRIVATE LTD

Spectral imaging system

SINHA PURNENDU

Methods and systems for diagnosing hardware and software faults using time-stamped events

VENKATESAN VARUN AKUR

Test strip assembly for analysing bodily fluids and devices thereof