{"id":"W4415702056","doi":"10.1145/3774327","title":"HiSpMM: High Performance High Bandwidth Sparse-Dense Matrix Multiplication on HBM-equipped FPGAs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Reconfigurable Technology and Systems","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Scalability; Bottleneck; Field-programmable gate array; Workload; Speedup; Matrix multiplication; Design space exploration; Bandwidth (computing); Robustness (evolution)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003183065,0.0007959934,0.0002991853,0.000417985,0.0002612573,0.0005763631,0.001038103,0.0003296627,0.0148724],"category_scores_gemma":[0.0007459742,0.0002690953,0.000288133,0.0003934336,0.0002309269,0.0006814298,0.0006062773,0.0005639776,0.002718589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004415679,"about_ca_system_score_gemma":0.0005622989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001319964,"about_ca_topic_score_gemma":0.002925445,"domain_scores_codex":[0.9997438,0.00004676498,0.00001247994,0.00003391816,0.000116349,0.00004673797],"domain_scores_gemma":[0.9997521,0.00006524075,0.0000299285,0.00005712593,0.0000645675,0.00003099229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001831952,0.0004165903,0.00764455,0.001333206,0.0002883974,0.001422872,0.0004122592,0.1080187,0.1361129,0.03050437,0.1483199,0.5636943],"study_design_scores_gemma":[0.0007240495,0.0017133,0.004415118,0.0001501986,0.00008896021,0.0007989601,0.000177532,0.7489702,0.1187444,0.009772125,0.1143559,0.00008922087],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2213916,0.002688859,0.656239,0.0008873942,0.0005214399,0.0004327073,0.002120207,0.05919831,0.0565205],"genre_scores_gemma":[0.6556373,0.0004446335,0.325801,0.0004570523,0.00007438374,0.0002893486,0.002597592,0.0009257962,0.01377295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0148724,"threshold_uncertainty_score":0.04975313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01360890834303751,"score_gpt":0.2504642010922213,"score_spread":0.2368552927491838,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}