Nishank Chandawala
Director, GPU Communications and Networking
- Role
- Director, Gpu Communications and Networking at NVIDIA
- Location
- Santa Clara, CA, US
- LinkedIn followers
- 500 followers
About Nishank Chandawala
I lead a team of world-class experts in High-Performance Computing (HPC), specializing in communication runtimes, parallel programming models, network design, high-speed interconnects, and scale-out GPU systems. Our focus is on optimizing communication between GPUs, ensuring high bandwidth, low latency, and minimal overhead to achieve the highest level of performance on NVIDIA platforms for Deep Learning and Scientific Computing applications.Our work at the bleeding edge of innovation includes developing communication libraries such as NCCL, NVSHMEM, and CUDA-aware MPI (via UCX), enabling applications and frameworks to achieve speed-of-light performance for collective and point-to-point communication on NVIDIA platforms. We are also pioneering technologies like GPUDirect, facilitating direct data movement between GPUs, networks, and storage without CPU involvement.Let\'s connect if you are ready to push the boundaries and drive innovation in this space!
Experience
Director, Gpu Communications and Networking
Jun 2023 — Present
I lead a team of world-class experts in High-Performance Computing (HPC), specializing in communication runtimes, parallel programming models, network design, high-speed interconnects, and scale-out GPU systems. Our focus is on optimizing communication between GPUs, ensuring high bandwidth, low latency, and minimal overhead to achieve the highest level of performance on NVIDIA platforms for Deep Learning and Scientific Computing applications.Our work at the bleeding edge of innovation includes developing communication libraries such as NCCL, NVSHMEM, and CUDA-aware MPI (via UCX), enabling applications and frameworks to achieve speed-of-light performance for collective and point-to-point communication on NVIDIA platforms. We are also pioneering technologies like GPUDirect, facilitating direct data movement between GPUs, networks, and storage without CPU involvement.Let\'s connect if you are ready to push the boundaries and drive innovation in this space!
Education
Georgia Institute of Technology
MS, Electrical and Computer Engineering
2005 — 2007
University of Mumbai
BE, Electronic Engineering
2001 — 2005
Skills
- Performance Analysis
- Simulations
- X86
- Intel
- Hardware Architecture
- Perl
- Performance Architecture
- Performance Validation (Pre-Si/Post-Si)
- Microarchitecture
- Debugging
- C
- Scripting
- Computer Architecture
- Verilog
- Pcie
- Processors
- Microprocessors
- Functional Verification
- C++
- Soc
- Performance Modeling and Analysis
Find verified contacts for anyone on LinkedIn
Unifers gives sales teams verified emails and direct dials, enriched profiles, and outreach that lands in the inbox.
Free plan included · No credit card required
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.