Abstract is missing.
- Range Extension with Supernormals for Mixed-Precision 8-bit DNN TrainingShing Wai Pun, Bozhang Bao, Silviu-Ioan Filip, Guy Lemieux, John V. Kim, Nazar Misyats, Nirvik Pande, Victor Ravain, Robert Sherrick. 1-4 [doi]
- An Empirical Study of Microscaling Formats for Low-Precision LLM TrainingHanmei Yang, Summer Deng, Amit Nagpal, Maxim Naumov, Mohammad Janani, Tongping Liu, Hui Guan 0001. 1-8 [doi]
- Hardware-Aware Training for Multiplierless Convolutional Neural NetworksRémi Garcia 0001, Léo Pradels, Silviu-Ioan Filip, Olivier Sentieys. 9-16 [doi]
- Trailing-Ones Anticipation for Reducing the Latency of the Rounding Incrementer in FP FMA UnitsToru Koizumi 0001, Ryota Shioya, Takuya Yamauchi, Tomoya Adachi, Ken Namura, Jun Makino. 21-28 [doi]
- Hardware Fixed-Point 2D and 3D normsRomain Bouarah, Florent de Dinechin. 29-36 [doi]
- VEXP: A Low-Cost RISC-V ISA Extension for Accelerated Softmax Computation in TransformersRun Wang, Gamze Islamoglu, Andrea Belano, Viviane Potocnik, Francesco Conti 0001, Angelo Garofalo, Luca Benini. 37-44 [doi]
- On the Flop and Flap Counts of the 2, 8-Split-Radix FFTPaul Caprioli. 45-52 [doi]
- Fast Basecases for Arbitrary-Size MultiplicationAlbin Ahlback, Fredrik Johansson. 53-60 [doi]
- Evaluation of Bfloat16, Posit, and Takum Arithmetics in Sparse Linear SolversLaslo Hunhold, James Quinlan. 61-68 [doi]
- Experimental Software and Hardware Evaluation of Ad-Hoc Constant Division RoutinesFrédéric Pétrot. 69-72 [doi]
- Double-Word Decomposition in a Combined FP16, BF16 and FP32 Dot Product Add OperatorOrégane Desrentes, Benoît Dupont de Dinechin, Florent de Dinechin. 73-80 [doi]
- Implementation Evaluation of Fixed-Point Multipliers for Complex NumbersPer Larsson-Edefors, Erik Börjeson. 81-84 [doi]
- n±δ) Addition Algorithm via Two-Valued Digit EncodingSaeid Gorgin 0001, Amirhossein Sadr, Dara Rahmati, Jungrae Kim. 85-92 [doi]
- Rounding Error Statistics as Numerics SignaturePing Tak Peter Tang. 93-100 [doi]
- Mixing Condition Numbers and Oracles for Accurate Floating-point DebuggingBhargav Kulkarni, Pavel Panchekha. 101-108 [doi]
- Excvate: Spoofing Exceptions and Solving Constraints to Test Exception Handling in Numerical LibrariesJackson Vanover, James Demmel, Xiaoye Sherry Li, Cindy Rubio-González. 109-116 [doi]
- Correct Rounding in Double Extended PrecisionSélène Corbineau, Paul Zimmermann. 117-124 [doi]
- Rigorous Error Analysis for Logarithmic Number SystemsThanh Son Nguyen, Alexey Solovyev, Mark G. Arnold, Ganesh Gopalakrishnan. 125-132 [doi]
- On Stochastic Rounding with Few Random BitsAndrew Fitzgibbon, Stephen Felix. 133-140 [doi]
- FastTwoSum revisitedClaude-Pierre Jeannerod, Paul Zimmermann. 141-148 [doi]
- Robust, End-to-end Correctness Proofs of Industrial Divide and Square Root RTL DesignsSol Swords, Cuong Chau. 149-156 [doi]
- Formal Verification of the IEEE P3109 Standard for Binary Floating-Point Formats for Machine LearningChristoph M. Wintersteiger. 157-160 [doi]