ph3About Us: /h3 pAt Huawei Technologies Switzerland AG, we are a leading technology firm dedicated to developing cutting-edge solutions that redefine industry standards and push technological boundaries. Our core focus is on creating advanced computing architectures that can efficiently support and enhance the performance of artificial intelligence systems. We believe in innovation as a driving force for improvement and are committed to achieving excellence in all areas of research and development. /p h3General /h3 pUsually the performance of libraries on modern hardware is still determined by measurement: implementations are chosen by benchmarking and their parameters by search or heuristics; neither result are portable to arbitrary hardware. Our team works towards developing an approach to determine it analytically instead, with an arbitrary machine model (for any system) and a parametrized representation for algorithms, which we compose to predict performance, enable autotuning and guide co-design. /p h3Key Responsibilities: /h3 ul liSystem characterization micro benchmarking - develop a microbenchmark suite for machine model coefficients: ul liExplore options for encoding and initializing machine characteristics: transfer costs, latencies, synchronization overheads, and compute rates. /li liMeasurement methodology: how raw timings become model coefficients — fit quality, run-to-run variance, outlier handling, and reproducibility across machines. /li liCoverage of matrix/tensor engines and mixed- and low-precision arithmetic, rather than inferring their roofs from SIMD /li liNew backends (GPU or accelerator) and extension of the measured hierarchy to inter-node levels /li /ul /li liImplementation side: Extend current GraphBLAS backends and model application ul liDense linear-algebra implementation, integration and model-validation/co-design. /li liExplore cost-model-driven autotuning: predicting blocking, thread count, and data placement ahead of execution. /li /ul /li /ul h3Requirements: /h3 ul liMSc or PhD in Computer Science, Engineering, or a related technical discipline /li liStrong knowledge of computer architecture and solid parallel processing: memory hierarchies, OpenMP (or similar), NUMA, SIMD etc. /li liStrong C/C++ programing skills for architecture/parallel processing and some python for orchestration and analysis /li liExperience in benchmarking performance engineering for parallel code /li liResearch experience in one of: ul liAnalytical performance modeling: Roofline(s), Communication modeling(Hockney, LogP etc), Machine models (BSP, Multi-BSP) /li liDense or sparse linear-algebra libraries and kernel optimization (BLAS/GEMM, GraphBLAS) /li liApplied statistics and numerical methods: regression and robust estimation, experiment design, portability, reproducibility etc. /li liDistributed execution(MPI etc), GPU/accelerator programming, or Autotuning /li /ul /li /ul h3What We Offer: /h3 ul liCompetitive salary and benefits package. /li liOpportunities for professional growth and development. /li liBe part of innovative projects that make a difference. /li liAccess to state-of-the-art technology and tools. /li /ul /p #J-18808-Ljbffr
HPC Optimization and Performance Model Engineer(Fixed Term Contract) Arbeitgeber: Huawei Switzerland
Huawei Schweiz bietet eine inspirierende Arbeitsumgebung in Zürich, die von Innovation und Zusammenarbeit geprägt ist. Als Senior SoC Architect & Researcher haben Sie die Möglichkeit, an bahnbrechenden Projekten zu arbeiten und Ihre Expertise in einem dynamischen Team einzubringen. Das Unternehmen fördert aktiv das Wachstum seiner Mitarbeiter durch kontinuierliche Weiterbildung und bietet attraktive Benefits, die eine ausgewogene Work-Life-Balance unterstützen.
