Himanshu Shrivastava — Product Manager

Highly accomplished professional with over 11 years of experience in the Tech industry, holding a Master of Technology (MTech.) in Information Technology with a specialization in Embedded System Design from IIIT Bangalore.Currently serving as a Senior Performance Analyst at IBM India Systems Development Lab, focusing on: • Hardware Tracing • Post-Silicon Validation & Bring-Up for Power Systems • System-level performance analysis and debugging Additional expertise includes: • Accelerated and Technical Computing • High-Performance Computing (HPC) • Tools development for deep system-level analysis and performance optimization Innovator and Thought Leader: • 4 Patents Filed (1 Granted) • 8+ Publications and Technical Articles in reputed platforms, contributing to the advancement of performance engineering and embedded systems. Professional Experience Summary Experienced Performance Analyst & Post-Silicon Validation Expert with a strong background in IBM Power Systems, specializing in hardware-software co-analysis, accelerated computing, and performance tuning of microprocessor-based platforms. Core Experience Areas: • IBM Power Systems Post-Silicon Validation & Bring-Up  Leading post-silicon validation team, performance tuning, and power optimization for next-generation IBM POWER processors.  Hands-on experience with microarchitecture performance analysis, bottleneck characterization, and validation of key processor features. • Cross-Functional Debug & Analysis  Collaborates with hardware validation and design, software development, and architectural modelling teams to debug complex system-level issues.  Delivered insights driving hardware design improvements through trace-based analysis and simulation model projection. • Performance Analysis & Simulation  Performed detailed performance evaluations using cycle-accurate simulation models.  Collects and validate high-quality hardware traces to support performance modelling and projection of future processor generations. • Accelerated Systems & HPC Workloads  Conducted performance analysis and platform engineering for IBM Power Systems with NVIDIA GPUs.  Focused on GPU offloading, CUDA, and OpenMP. Key Skills & Technologies • Domains: Post-Silicon Validation, HPC, Processor Performance Analysis, Hardware Tracing, Platform Engineering • Technologies: Processor , Architecture, NVIDIA GPUs, CUDA, OpenMP, Linux. • Tools & Languages: Python, Bash,Performance Tools • Strengths: Cross-functional collaboration, System-level debugging, Innovation-driven mindset

Stackforce AI infers this person is a High-Performance Computing and Embedded Systems expert with extensive experience in performance analysis.

Location: Bengaluru, Karnataka, India

Experience: 12 yrs 6 mos

Skills

Post-silicon Validation
Performance Analysis
High-performance Computing
Performance Tools Development
Hardware Design Engineering
Process Automation

Career Highlights

Over 11 years of experience in the Tech industry.
4 patents filed and 8+ publications in performance engineering.
Expert in post-silicon validation and performance analysis.

Work Experience

IBM

Processor Performance Engineer (2 yrs 3 mos)

Senior Staff Software Engineer/Performance Analyst (2 yrs 4 mos)

Staff Software Engineer/Performance Analyst- Hardware Tracing (1 yr 6 mos)

Software Performance Analyst (Technical Computing/HPC) (2 yrs)

POWER Processor Performance Tools Developer (3 yrs 8 mos)

ByDesign Products & R&D (Velankani Group)

Hardware Design Intern (7 mos)

SAP Labs India Pvt. Ltd.

Project Intern (4 mos)

Education

Master of Technology (M.Tech.) at International Institute of Information Technology Bangalore

Preparation of Engineering Services at IES Made Easy, New Delhi

Bachelor of Engineering (B.E.) at Samrat Ashok Technological Institute

Himanshu Shrivastava

Product Manager

Bengaluru, Karnataka, India12 yrs 6 mos experience

Most Likely To SwitchAI ML Practitioner

Key Highlights

Over 11 years of experience in the Tech industry.
4 patents filed and 8+ publications in performance engineering.
Expert in post-silicon validation and performance analysis.

Stackforce AI infers this person is a High-Performance Computing and Embedded Systems expert with extensive experience in performance analysis.

Contact

Skills

Core Skills

Post-silicon ValidationPerformance AnalysisHigh-performance ComputingPerformance Tools DevelopmentHardware Design EngineeringProcess Automation

Other Skills

ABAPAlgorithmsAngularJSArchitectural StudyArtificial Intelligence (AI)AutomationBashCUDADDR5 Memory Design OptimizationData StructuresDebuggingDeep LearningElectronicsEmbedded SystemsGNU Compiler Collection (GCC)

About

Experience

Ibm

5 roles

Processor Performance Engineer

Dec 2023 – Present · 2 yrs 3 mos

Post-Silicon Hardware Performance Validation & Bring-Up Lead – IBM Power Systems
Leading post-silicon performance validation and bring-up for IBM Power Systems.
Driving trace collection and validation to enable accurate performance modeling and design guidance for next-gen POWER processors.
Contributing to DDR5 memory module design optimization and architectural direction.

Post-Silicon ValidationPerformance ValidationTrace CollectionPerformance ModelingDDR5 Memory Design OptimizationPerformance Analysis

Senior Staff Software Engineer/Performance Analyst

Promoted

Oct 2021 – Feb 2024 · 2 yrs 4 mos

Performance Analysis of various architectural features of future IBM Power Processor core,
Power system post silicon Validation and Bring up.
Workload characterization and workload setup on simulation models.
Projection quality trace collection and validation.
Performance Analysis of various workloads on POWER systems platform.
Hardware tracing to enable modelling and designing the future generation of POWER processors.

Performance AnalysisPower System ValidationWorkload CharacterizationSimulation ModelsHardware TracingPost-Silicon Validation

Staff Software Engineer/Performance Analyst- Hardware Tracing

Mar 2020 – Sep 2021 · 1 yr 6 mos

Software Performance Analyst (Technical Computing/HPC)

Apr 2018 – Apr 2020 · 2 yrs

Performance Analysis for technical computing includes the architectural study of IBM POWER System with Nvidia GPU (Volta). Involved in the performance analysis and health check of the system through engineering works. Also, the workload/application evaluation on IBM HPC System AC922. Work includes experiments and knowledge of:
Architectural study and projections on the new architectural design of future HPC Systems.
Parallel programming using CUDA , OpenMP , MPI and Performance analysis.
OpenMPGO – For offloading the compute intensive part of the application to GPU using OpenMP4.5 pragmas and conversion of CUDA and C to OpenMP codes.
Development of micro codes for new technologies in parallel computing – Unified Virtual Memory and Address translation services and OpenMP (Sync and Async) codes.
HPC Workloads/applications evaluation on IBM HPC Systems and Collaterals Publications.
Profiling for HPC Workloads using Nvidia Visual profiler.
Involved in Systems bring up and upgradation of Nvidia drivers and CUDA toolkit, firmware, Compilers and Engineering works.
Automation for the Engineering works and applications using Jenkins Continuous Integration(CI).
SYSTEM analysis using Nvidia kernel launch latency, SGEMM/DGEMM(TFLOPS),Bandwidth test -same socket/across the socket, HtoD/DtoH bandwidth, data transfers and NVLINK analysis – Latency and BW.
Compilers – XLC, LLVM, GCC

Performance AnalysisArchitectural StudyParallel ProgrammingCUDAOpenMPMPI+1

POWER Processor Performance Tools Developer

Aug 2014 – Apr 2018 · 3 yrs 8 mos

IBM Systems Development Lab (ISDL) is one of the largest product development centers for IBM globally. Teams at ISDL are involved in designing and developing Operating Systems including Linux, AIX, zOS, Storage Systems and High Performance Systems. Apart from these areas, teams also work on key technologies in the areas of Networking, File Systems, Virtualization, Super Computing and Processor Architecture.
I am a part of IBM Systems development lab working with power system performance team on the Development of Power Processor Performance Instrumentation Tools. Develop tools for compilers performance and for High Performance Computing team to evaluate the GPU performance.(PCIe and Nvlink) front-end and back-end.
 INSTRUMENTATION TOOLS
 Performance Data Analysis Tool ({PHP, Python , HTML,JavaScript)
 PMU Validation tool ({PHP, Python , HTML, JavaScript)
 GPU TOOLING
 CPU-GPU Visualization tool (PHP, python,HTML, LAMP, nvidia-smi, shell/bash, jupyter notebook)
 Nvlink Advisor tool (PHP, python,HTML, LAMP)
 Nvvp Visualizer tool (PHP, python, HTML,LAMP)

Performance Instrumentation ToolsGPU Performance EvaluationTool DevelopmentPHPPythonHTML+3

Bydesign products & r&d (velankani group)

Hardware Design Intern

Dec 2013 – Jul 2014 · 7 mos · Bangalore

DVB-C Android Set top box concentrates on the development hardware system of IPTV eco-system also known as Set-Top-Box (STB). STB added with Android user interface provides rich user experience and Android Application and Games eco system. Android IPTV STB will be developed on Android STB platforms mostly on ARM 7 Architecture.
Services: watching Live TV with interactive features, using Electronic Program Guide (EPG), enjoy Video on Demand movies and many more. With the help of tools and software we developed the hardware design of the project which includes the designing and verification. The work was about development hardware functional blocks, Power calculation, Memory configuration and External connector details and development of Applications and it includes,
Designing of schematic using ORCAD and Verification.
Verification of PCB Layout.(Footprint Verification)
Debugging the Interfaces in the Boards(HDMI, CVBS, SPDIF, Ethernet, UART).
Creation of Bill of Materials.
Procurement of Components as per bill of material.
Vendor Interaction.
Board bring up Activity and Debugging of Proto Boards.
Soldering (except BGA).
Board Bring Up and BSP for Set-Top Box.
Boot loaders (U-Boot, CFE and customized boot loader) and Customization.
Linux Kernel Image Creation, Customization and porting onto the Target Machines

Hardware DesignSchematic DesignPCB Layout VerificationDebuggingLinux Kernel CustomizationHardware Design Engineering

Sap labs india pvt. ltd.

Project Intern

Aug 2013 – Dec 2013 · 4 mos · Bangalore

Project: START Review Process Automation.
This project has involve automating the review process of START templates saving the enormous amount of time we spend on manually checking the adherence to guidelines.Worked on the automation of the tool in ABAP(Advanced Business Application Programming)

ABAPProcess Automation