{"adoption": {"forks": 187, "observed_at": "2026-08-28T04:04:28.107109+00:00", "stars": 1350}, "canonical_url": "https://ross.abutalabs.com/products/how_to_optimize_in_gpu", "card": {"archived": false, "artifact_type": "learning-resource", "description": "This is a series of GPU optimization topics. Here we will introduce  how to optimize the CUDA kernel in detail.  I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.", "domain": ["gpu-computing", "performance", "tutorials", "developer-tools"], "enriched": true, "function": ["gpu-computing", "benchmarking", "developer-tools"], "health_score": 20, "homepage": null, "language": "Cuda", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["Liu-xiandong/How_to_optimize_in_GPU"], "name": "Liu-xiandong/How_to_optimize_in_GPU", "platform": [], "pushed_at": "2023-07-29T05:52:37+00:00", "repo": "Liu-xiandong/How_to_optimize_in_GPU", "stars": 1350, "tags": ["cuda-kernels", "high-performance-computing", "sgemm", "sgemv", "kernel-optimization", "nsight", "v100", "gpu", "cuda", "linux"], "topics": ["gpu-acceleration", "elementwise", "reduce", "sgemm", "sgemv", "high-performance-computing", "hpc"], "urls": [], "use_cases": ["learn how to optimize CUDA kernels", "understand vectorized memory access in CUDA", "write a high-performance sgemm kernel", "optimize reduce operations on GPU", "compare my kernel performance against cuBLAS", "learn SASS-level tuning with register remapping"], "what_it_is": "A tutorial series repository teaching CUDA kernel optimization with detailed walkthroughs of elementwise, reduce, sgemv, and sgemm kernels. The kernels achieve near-theoretical-limit performance on V100 GPUs, benchmarked with Nsight against cuBLAS.", "when_to_avoid": ["you need a production linear algebra library - use cuBLAS or CUTLASS instead", "you want a maintained framework rather than educational code", "you target GPUs other than NVIDIA V100-class hardware without adapting the tuning"], "when_to_choose": ["you want to learn GPU kernel optimization from worked examples", "you need reference implementations of near-peak elementwise, reduce, sgemv, or sgemm kernels", "you are studying HPC or preparing for GPU performance engineering work"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/how_to_optimize_in_gpu", "repo": "Liu-xiandong/How_to_optimize_in_GPU", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:28.107109+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:42:15.494960+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "071694161be4a0004d224cacbdd40184efe18e165c21f1fa56b2839a72a412eb", "fetched_at": "2026-08-28T04:04:28.107109+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Liu-xiandong/How_to_optimize_in_GPU"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1781, "days_push": 1131, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}