April 06, 2022|新聞報導
MLPerf Results Show Advances in Machine Learning Inference Performance and Efficiency
MLCommons’ latest benchmarks illustrate focus on energy efficiency and up to 3.3X performance gains
了解更多
December 16, 2021|新聞報導
HarDNet進軍智慧醫療 協助自動化診斷醫學影像判讀
人工智慧(AI)浪潮不斷推動關鍵技術的發展，全面啟動產、官、學、研界合作共建研發平台，開創全新的應用領域，科技部半導體射月計畫的「HarDNet」專案，是由清華大學資工系林永隆教授領導的團隊，研究高效率CNN骨幹網路架構，並改良傳統AI網路的架構，藉由減少DenseNet架構中的捷徑連結與重新設計層級間的權重數，降低資料在記憶體搬運次數，藉此達到提升運算速度的效果，同時維持高辨識準確率。
了解更多
October 24, 2021|新聞報導
MLCommons™ Releases MLPerf™ Inference v1.1 Results
Submissions this round included software and hardware innovations from Alibaba, Centaur Technology, cTuning, Dell, EdgeCortix, Fujitsu, FuriosaAI, Gigabyte, HPE, Inspur, Intel, Krai, Lenovo, LTechKorea, Nettrix, Neuchips, NVIDIA, OctoML, Qualcomm Technologies, Inc., and Supermicro
了解更多
October 17, 2021|新聞報導
MLCommons™ Releases MLPerf™ Inference v1.0 Results with First Power Measurements
Today, MLCommons, an open engineering consortium, released results for MLPerf Inference v1.0, the organization's machine learning inference performance benchmark
了解更多
October 02, 2021|新聞稿
RecAccel-World's 1st DLRM DSA solution
NEUCHIPS successfully submitted results of its RecAccel system in MLPerf v0.7. Announced early this year, RecAccel is the world’s 1st Hardwired DLRM accelerator and is the only non-GPU/CPU entry
了解更多
May 12, 2021|新聞稿
NEUCHIPS Announces World's First Deep Learning Recommendation Model (DLRM) Accelerator: RecAccel
NEUCHIPS Corp., an AI compute company specializing in domain-specific accelerator solutions, announced the world's first recommendation engine - RecAccelTM - that can perform 500,000 inferences per second. Running open-source PyTorch DLRM, RecAccelTM outperforms server-class CPU and inference GPU by 28X and 65X, respectively. It is equipped with an ultra-high-capacity, high-bandwidth memory subsystem for embedding table lookup and a massively parallel compute FPGA for neural network inference. Via a PCIe Gen3 host interface, RecAccelTM is ready for data center adaptation.
了解更多
