{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:14:33Z","timestamp":1772694873026,"version":"3.50.1"},"reference-count":100,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4500304"],"award-info":[{"award-number":["2022YFB4500304"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332021,62304257,62472058"],"award-info":[{"award-number":["62332021,62304257,62472058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408611","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-16","source":"Crossref","is-referenced-by-count":0,"title":["Cohet: A CXL-Driven Coherent Heterogeneous Computing Framework with Hardware-Calibrated Full-System Simulation"],"prefix":"10.1109","author":[{"given":"Yanjing","family":"Wang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhou","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunfeng","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibo","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhui","family":"Luo","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zicong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ou","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dezun","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nong","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingche","family":"Lai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1109\/ISCA59077.2024.00066","article-title":"Intel accelerators ecosystem: An soc-oriented perspective: Industry product","volume-title":"2024 ACM\/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)","author":"Yuan","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref3","first-page":"1","article-title":"Nvidia data center processing unit (DPU) architecture","volume-title":"2021 IEEE Hot Chips 33 Symposium (HCS), 2021","author":"Burstein"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/HCS52781.2021.9567455","article-title":"Intel\u2019s hyperscaleready infrastructure processing unit (IPU)","volume-title":"2021 IEEE Hot Chips 33 Symposium (HCS)","author":"Burres","year":"2021"},{"key":"ref5","first-page":"83","article-title":"Apunet: revitalizing GPU as packet processing accelerator","volume-title":"Proceedings of the 14th USENIX Conference on Networked Systems Design and Implementation (NSDI)","author":"Go","year":"2017"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ISCA.2018.00012","article-title":"A configurable cloud-scale DNN processor for real-time ai","volume-title":"2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA)","author":"Fowers","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901323"},{"key":"ref8","first-page":"51","article-title":"Azure accelerated networking: SmartNICs in the public cloud","volume-title":"Proceedings of the 15th USENIX Conference on Networked Systems Design and Implementation (NSDI)","author":"Firestone","year":"2018"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.1109\/MICRO61859.2024.00110","article-title":"Demystifying a CXL type-2 device: A heterogeneous cooperative computing perspective","volume-title":"2024 57th IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Ji","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3656019.3676896"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624868"},{"key":"ref12","article-title":"An introduction to the compute express link (CXL) interconnect","author":"Sharma","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"ref13","year":"2025","journal-title":"Unified Memory for CUDA Beginners"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673110"},{"key":"ref15","year":"2025","journal-title":"NVLink-C2C"},{"key":"ref16","year":"2025","journal-title":"amd-cdna-3-white-paper"},{"key":"ref17","author":"Gupta","year":"2025","journal-title":"Accelerating datacenter workloads"},{"key":"ref18","author":"Consortium","year":"2025","journal-title":"Compute Express Link Specification"},{"key":"ref19","year":"2025","journal-title":"OpenCAPI Specification Archive - Compute Express Link"},{"key":"ref20","year":"2025","journal-title":"Gen-Z Specification Archive - Compute Express Link"},{"key":"ref21","year":"2025","journal-title":"CCIX Specification Archive - Compute Express Link"},{"key":"ref22","year":"2025","journal-title":"Integrators list - Compute Express Link"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614256"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3650061"},{"key":"ref25","volume-title":"Performance characterizations and usage guidelines of Samsung CXL memory module hybrid prototype","author":"Zeng","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582063"},{"key":"ref27","first-page":"574","article-title":"Pond: CXL-based memory pooling systems for cloud platforms","volume":"2","author":"Li","year":"2023","journal-title":"in ASPLOS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731092"},{"key":"ref29","year":"2025","journal-title":"CMM-D CXL memory Samsung semiconductor global"},{"key":"ref30","year":"2025","journal-title":"CXL memory initiative"},{"key":"ref31","volume-title":"World\u2019s First CXL 2.0 and PCIe Gen 5.0 Switch Chip"},{"key":"ref32","year":"2025","journal-title":"SK hynix secures CXL 2.0-based CMM-DDR5 customer validation"},{"key":"ref33","year":"2025","journal-title":"Montage MXC"},{"key":"ref34","year":"2025","journal-title":"Agilex TM 7 FPGA i-series development kit (2x r-tile and 1x f-tile)"},{"key":"ref35","year":"2025","journal-title":"Compute express link (CXL) 2.0\/1.1 FPGA IP"},{"key":"ref36","year":"2025","journal-title":"Compute express link subsystem maturity map - the linux kernel documentation"},{"key":"ref37","year":"2025","journal-title":"OpenCL - the open standard for parallel programming of heterogeneous systems"},{"key":"ref38","year":"2025","journal-title":"oneAPI programming model"},{"key":"ref39","first-page":"613","article-title":"HAL: Hardware-assisted Load Balancing for Energy-efficient SNIC-Host Cooperative Computing","volume-title":"2024 ACM\/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)","author":"Huang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651325"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3422575.3422789"},{"key":"ref42","first-page":"1","article-title":"Remote atomic extension (rae) for scalable high performance computing","volume-title":"2020 57th ACM\/IEEE Design Automation Conference (DAC)","author":"Wang","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901349"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1109\/Cluster48925.2021.00033","article-title":"Thinking more about RDMA memory semantics","volume-title":"2021 IEEE International Conference on Cluster Computing (CLUSTER)","author":"Ma","year":"2021"},{"key":"ref45","first-page":"437","article-title":"Design guidelines for high performance RDMA systems","volume-title":"Proceedings of the 2016 USENIX Conference on Usenix Annual Technical Conference (ATC)","author":"Kalia","year":"2016"},{"key":"ref46","first-page":"583","article-title":"High performance distributed lock management services using network-based remote atomic operations","volume-title":"Seventh IEEE International Symposium on Cluster Computing and the Grid (CCGrid \u201907)","author":"Narravula","year":"2007"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/pact.2015.24"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480055"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1109\/HPCA61900.2025.00104","article-title":"Rpcnic: Enabling efficient datacenter RPC offloading on PCIeattached SmartNICs","volume-title":"2025 IEEE International Symposium on High Performance Computer Architecture (HPCA)","author":"Zhang","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446696"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613156"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480051"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378450"},{"key":"ref54","first-page":"1","article-title":"Understanding routable PCIe performance for composable infrastructures","volume-title":"Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Hou","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387517"},{"key":"ref56","year":"2025","journal-title":"Heterogeneous Memory Management (HMM) - The Linux Kernel documentation"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378529"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2024716.2024718"},{"key":"ref59","article-title":"The gem5 simulator: Version 20.0+","author":"Lowe-Power","year":"2020","journal-title":"ArXiv"},{"key":"ref60","year":"2025","journal-title":"Ruby"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589065"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378511"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/micro61859.2024.00056"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3448418"},{"key":"ref65","year":"2025","journal-title":"Introduction to infiniband"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527385"},{"key":"ref67","first-page":"457","article-title":"Graphpim: Enabling instruction-level PIM offloading in graph computing frameworks","volume-title":"2017 IEEE International Symposium on High Performance Computer Architecture (HPCA)","author":"Nai"},{"key":"ref68","first-page":"519","article-title":"When cloud storage meets RDMA","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Gao"},{"key":"ref69","first-page":"561","article-title":"Ray: a distributed framework for emerging ai applications","volume-title":"Proceedings of the 13th USENIX Conference on Operating Systems Design and Implementation (OSDI)","author":"Moritz"},{"key":"ref71","author":"Slee","year":"2025","journal-title":"Thrift: Scalable crosslanguage services implementation"},{"key":"ref72","year":"2025","journal-title":"Protocol Buffers"},{"key":"ref73","year":"2025","journal-title":"Cap\u2019n proto: Introduction"},{"key":"ref74","year":"2025","journal-title":"FlatBuffers docs"},{"key":"ref75","year":"2025","journal-title":"4th gen intel xeon processor scalable family, sapphire rapids"},{"key":"ref76","year":"2025","journal-title":"Multichannel DMA FPGA IP for PCI express altera"},{"key":"ref77","year":"2025","journal-title":"CLDEMOTE - cache line demote"},{"key":"ref78","year":"2025","journal-title":"CLFLUSH - flush cache line"},{"key":"ref79","volume-title":"CXLMemSim","author":"Yang","year":"2025"},{"key":"ref80","first-page":"1","article-title":"CXL-DMSim: A full-system CXL disaggregated memory simulator with comprehensive silicon validation","author":"Wang","year":"2025","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"ref81","first-page":"1","article-title":"A mess of memory system benchmarking, simulation and application profiling","author":"Esmaili-Dokht","year":"2024","journal-title":"in MICRO"},{"key":"ref82","author":"Developers","year":"2025","journal-title":"QEMU"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00291"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624175"},{"key":"ref85","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/MCHPC56545.2022.00007","article-title":"Evaluating emerging CXL-enabled memory pooling for HPC systems","volume-title":"2022 IEEE\/ACM Workshop on Memory Centric High Performance Computing (MCHPC)","author":"Wahlgren","year":"2022"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3715987"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3711999"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695968"},{"key":"ref89","first-page":"1","article-title":"Nomad: non-exclusive memory tiering via transactional page migration","volume-title":"Proceedings of the 18th USENIX Conference on Operating Systems Design and Implementation (OSDI)","author":"Xiang"},{"key":"ref90","doi-asserted-by":"crossref","first-page":"1518","DOI":"10.1109\/MICRO61859.2024.00111","article-title":"Neomem: Hardware\/software co-design for CXL-native memory tiering","volume-title":"2024 57th IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Zhou","year":"2024"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685809"},{"key":"ref92","first-page":"382","article-title":"Enabling efficient large recommendation model training with near CXL memory processing","volume-title":"2024 ACM\/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)","author":"Liu"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624173"},{"key":"ref94","first-page":"1","article-title":"Efficient Tensor Offloading for Large Deep-Learning Model Training based on Compute Express Link","volume-title":"SC24: International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Xu","year":"2024"},{"key":"ref95","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1109\/HPCA56546.2023.10071127","article-title":"Rambda: RDMA-driven acceleration framework for memory-intensive $\\mu$ s-scale datacenter applications","volume-title":"2023 IEEE International Symposium on HighPerformance Computer Architecture (HPCA)","author":"Yuan","year":"2023"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707264"},{"key":"ref97","year":"2025","journal-title":"Why does Intel Agilex\u00ae 7 R-Tile Compute Express Link (CXL) 1.1\/2.0 FPGA IP not include the ATS capability?"},{"key":"ref98","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/FCCM53951.2022.9786103","article-title":"An evaluation of using CCIX for cache-coherent Host-FPGA interfacing","volume-title":"2022 IEEE 30th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","author":"Tamimi","year":"2022"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544253"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00055"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00023"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408611.pdf?arnumber=11408611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:36:30Z","timestamp":1772692590000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408611","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}