nsight-compute

This is my 🔥 100 Days of GPU — a wild, hands-on journey through CUDA/CUTLASS kernels, Triton spells, and PTX sorcery.

Profiling with NVIDIA Nsight Tools Bootcamp

Evidence-driven CUDA, CUTLASS, Triton and GPU workload optimization for ChatGPT · 使用 ChatGPT 驱动 GPU workload 性能优化

Query every CUDA device attribute without profiling, and benchmark kernels against your hardware's theoretical peak.

A comprehensive, hardware-agnostic GPU benchmarking suite that compares CUDA, OpenCL, and DirectCompute performance using identical workloads. Built from scratch with professional architecture, extensive documentation, and production-ready GUI.

CACAO is an open-source LLM agentic system that automatically generates, validates, profiles, and optimizes CUDA kernels using real GPU performance feedback and KTT-based autotuning.

References content from the OLCF CUDA Training Series. (https://github.com/olcf/cuda-training-series)

CUDA Samples and Nsight Guided Profiling Samples

A CUDA kernel playground for GEMM, Tensor Cores, Softmax, LayerNorm, validation, profiling, and performance benchmarking.

GPU-accelerated Number-Theoretic Transform for ZK-Proof generation. Targets the NTT bottleneck (91% of Groth16 prover time) via two CUDA optimizations: async double-buffered pipeline eliminating CPU-GPU transfer overhead, and IADD3-path Montgomery multiplication reducing finite-field instruction latency. BLS12-381, Ampere sm_86, Nsight-profiled.

Kernel-only profiling workflow for CUDA and Triton kernels with Nsight Compute, standardized reports, visual analysis, and vendor-portable adapters.

CUDA FP32 GEMM optimization with loop unrolling, shared memory tiling, register tiling, benchmarking, and Nsight profiling.

Hand-written CUDA linear algebra library. A GEMM driven from a naive baseline to a compute-bound tensor-core kernel at ~90% of cuBLAS on an RTX 5070, profiled with Nsight Compute, plus GEMV, TRSM, CSR SpMV, cuSOLVER, a measured roofline, and NVML telemetry.

Learning CUDA GEMM optimization and profiling for AI infrastructure.

Three hand-written Triton kernels for LLM inference (fused RMSNorm plus residual, online softmax, INT4 g128 GEMV) benchmarked on NVIDIA Blackwell against PyTorch eager and torch.compile, with every raw CUDA-event sample, measured device ceiling, and Nsight Compute report committed and CI-verified.

CUDA reduction primitive using warp shuffles, grid-stride loading, and memory-bandwidth profiling with Nsight Compute.

Nsight-driven CUDA kernel profiling studies for GEMM, Tensor Core GEMM, reductions, softmax, and attention against vendor baselines.

Single-head CUDA attention kernel: naive SDPA --> fused softmax --> occupancy-tuned variants, benchmarked against cuDNN SDPA with Nsight Compute profiling.

Qwen3.5-2B BF16 Roofline and Nsight profiling on Jetson Orin Nano

libHPC is a high-performance computing library focused on Linux and Windows environments. It provides SIMD-optimized kernels, concurrent data structures, GPU utilities, and HPC-oriented memory management components.