{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4ATR7EVAVAIZTXMBSSQFN5Z6NA","short_pith_number":"pith:4ATR7EVA","schema_version":"1.0","canonical_sha256":"e0271f92a0a81199dd8194a056f73e682394a8483a6b65794c1550627ea40644","source":{"kind":"arxiv","id":"1804.06826","version":1},"attestation_state":"computed","paper":{"title":"Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Benjamin Staiger, Daniele P. Scarpazza, Marco Maggioni, Zhe Jia","submitted_at":"2018-04-18T17:25:13Z","abstract_excerpt":"Every year, novel NVIDIA GPU designs are introduced. This rapid architectural and technological progression, coupled with a reluctance by manufacturers to disclose low-level details, makes it difficult for even the most proficient GPU software designers to remain up-to-date with the technological advances at a microarchitectural level. To address this dearth of public, microarchitectural-level information on the novel NVIDIA GPUs, independent researchers have resorted to microbenchmarks-based dissection and discovery. This has led to a prolific line of publications that shed light on instructi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1804.06826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-04-18T17:25:13Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"d42e93a734ec7bff725461f0dd5e1fa48d70838d86929cec23760f551b0ba54e","abstract_canon_sha256":"40a3b5cd84b167d600fe7fc55666972f0d53961e4c896a02b5a14f0772d21389"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:05.651893Z","signature_b64":"LKRnXXdKq9xazy/yEywBfI9/0NmheJcKQeO+Po7wxcJHODFQxK4hh5OeGVznAmCAaNS6/uD91155D44BZsJfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0271f92a0a81199dd8194a056f73e682394a8483a6b65794c1550627ea40644","last_reissued_at":"2026-05-18T00:18:05.651366Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:05.651366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dissecting the NVIDIA Volta GPU Architecture via Microbenchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Benjamin Staiger, Daniele P. Scarpazza, Marco Maggioni, Zhe Jia","submitted_at":"2018-04-18T17:25:13Z","abstract_excerpt":"Every year, novel NVIDIA GPU designs are introduced. This rapid architectural and technological progression, coupled with a reluctance by manufacturers to disclose low-level details, makes it difficult for even the most proficient GPU software designers to remain up-to-date with the technological advances at a microarchitectural level. To address this dearth of public, microarchitectural-level information on the novel NVIDIA GPUs, independent researchers have resorted to microbenchmarks-based dissection and discovery. This has led to a prolific line of publications that shed light on instructi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06826","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.06826","created_at":"2026-05-18T00:18:05.651446+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06826v1","created_at":"2026-05-18T00:18:05.651446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06826","created_at":"2026-05-18T00:18:05.651446+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ATR7EVAVAIZ","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ATR7EVAVAIZTXMB","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ATR7EVA","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1907.02894","citing_title":"RegDem: Increasing GPU Performance via Shared Memory Register Spilling","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17031","citing_title":"Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2512.00053","citing_title":"Ten-Four: An Open-Source Fused Dot Product Unit for Mixed-Precision GPGPU Tensor Cores","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2512.22168","citing_title":"TileLoom: Automatic Dataflow Planning for Tile-Based Languages on Spatial Dataflow Accelerators","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02473","citing_title":"Analyzing Reverse Address Translation Overheads in Multi-GPU Scale-Up Pods","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2205.14135","citing_title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27808","citing_title":"AME-PIM: Can Memory be Your Next Tensor Accelerator?","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25422","citing_title":"CUDA Kernel Optimization and Counter-Free Performance Analysis for Depthwise Convolution in Cloud Environments","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2307.08691","citing_title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15180","citing_title":"AdaSplash-2: Faster Differentiable Sparse Attention","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17862","citing_title":"M100: An Orchestrated Dataflow Architecture Powering General AI Computing","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19004","citing_title":"Ocean: Fast Estimation-Based Sparse General Matrix-Matrix Multiplication on GPU","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04178","citing_title":"Microbenchmark-Driven Analytical Performance Modeling Across Modern GPU Architectures","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ATR7EVAVAIZTXMBSSQFN5Z6NA","json":"https://pith.science/pith/4ATR7EVAVAIZTXMBSSQFN5Z6NA.json","graph_json":"https://pith.science/api/pith-number/4ATR7EVAVAIZTXMBSSQFN5Z6NA/graph.json","events_json":"https://pith.science/api/pith-number/4ATR7EVAVAIZTXMBSSQFN5Z6NA/events.json","paper":"https://pith.science/paper/4ATR7EVA"},"agent_actions":{"view_html":"https://pith.science/pith/4ATR7EVAVAIZTXMBSSQFN5Z6NA","download_json":"https://pith.science/pith/4ATR7EVAVAIZTXMBSSQFN5Z6NA.json","view_paper":"https://pith.science/paper/4ATR7EVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06826&json=true","fetch_graph":"https://pith.science/api/pith-number/4ATR7EVAVAIZTXMBSSQFN5Z6NA/graph.json","fetch_events":"https://pith.science/api/pith-number/4ATR7EVAVAIZTXMBSSQFN5Z6NA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ATR7EVAVAIZTXMBSSQFN5Z6NA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ATR7EVAVAIZTXMBSSQFN5Z6NA/action/storage_attestation","attest_author":"https://pith.science/pith/4ATR7EVAVAIZTXMBSSQFN5Z6NA/action/author_attestation","sign_citation":"https://pith.science/pith/4ATR7EVAVAIZTXMBSSQFN5Z6NA/action/citation_signature","submit_replication":"https://pith.science/pith/4ATR7EVAVAIZTXMBSSQFN5Z6NA/action/replication_record"}},"created_at":"2026-05-18T00:18:05.651446+00:00","updated_at":"2026-05-18T00:18:05.651446+00:00"}