32.7157°N 117.1611°W // San Diego, CA // 2026.04
currently in San Diego
Performance and Power Engineer at Arm. Hardware/software co-design for ML systems — energy-harvesting sensors, computational storage, intermittent and continuous learning at the edge.
23
01 // publications
498
02 // citations
10
03 // h-index
10+
04 // years exp.
// source: Google Scholar · synced 2026-04-26
Intermittency-aware DNN training for energy-harvesting micro-computers.
Dynamically adjusts dropout and quantization in response to intermittent energy. DynFit optimizer + DynInfer scheduler. Up to 22% accuracy gain at <5% compute overhead.
read more →
Computational storage for continuous-learning edge servers.
FPGA-accelerated computational storage devices handle compression, encryption, and redundancy near the data. 6× throughput, 6.1× less data movement.
read more →
Battery-free continuous learning on solar-powered edge servers.
A morphable accelerator that adapts to fluctuating solar power, paired with teacher-student training. Hundreds of kWh/year saved per device, no battery required.
read more →
Coreset-based partial inference on energy-harvesting wearables.
Sensors compute compressed coresets locally and ship only those to the host for final inference. Up to 8.9× communication reduction with near-baseline accuracy.
read more →
Scheduling and ensemble learning for HAR on energy-harvesting body networks.
Coordinates intermittent sensors across the body for human activity recognition. 2.5–5% accuracy gain under tight harvested-power constraints.
read more →
Neural expert prediction for efficient mixture-of-experts inference.
Predicts which experts will be activated before the routing layer fires, letting MoE inference avoid round-trips to dormant experts.
read more →
Pre-silicon perf/power analysis for next-generation heterogeneous SoCs.
Current work on the SoC Architecture Performance team — informing trade-off decisions for compute subsystems targeting Edge AI, IoT, and automotive workloads. Public-facing description; no internal details.
read more →
Site v3.0 launched
Joined Arm in San Diego
Defended my Ph.D. thesis at Penn State
CORD accepted at IPDPS 2025
01
IPDPS 2025
Wahid Uz Zaman , Cyan Subhra Mishra , Saleh AlSaleh , Abutalib Aghayev , Mahmut Taylan Kandemir
Conference · IEEE International Parallel and Distributed Processing Symposium (IPDPS '25)
02
ICLR 2025
Cyan Subhra Mishra , Deeksha Chaudhary , Jack Sampson , Mahmut Taylan Kandemir , Chita R. Das
Conference · International Conference on Learning Representations (ICLR '25)
03
PACT 2025
Cyan Subhra Mishra , Deeksha Chaudhary , Mahmut Taylan Kandemir , Chita R. Das
Conference · International Conference on Parallel Architectures and Compilation Techniques (PACT '25)
04
HPCA 2024
Cyan Subhra Mishra , Jack Sampson , Mahmut Taylan Kandemir , Vijaykrishnan Narayanan , Chita R. Das
Conference · IEEE International Symposium on High-Performance Computer Architecture (HPCA)
05
arXiv 2024
Cyan Subhra Mishra , Jack Sampson , Mahmut Taylan Kandemir , Vijaykrishnan Narayanan
arXiv · arXiv preprint
github
@cyanmishra92
40
repos
19
stars
top languages
view on github →
02 / 03blog
Notes & long-form
Performance engineering pragmatics, ML systems on constrained hardware, side projects, and the occasional paper read. Roughly monthly.
read posts →
03 / 03talks
Conference + invited
2
deep dives
latest
Cocktail: A Multidimensional Optimization for Model Serving in Cloud
NSDI · 2022
view all talks →