Full
Paper |
25 min |
|
|
Short
Paper |
10 min |
|
|
|
|
DAY 1 |
|
|
|
10:30--11:45 |
|
|
|
Main-A |
|
Distributed Systems
and Networking Frontiers |
|
46 |
10:30 |
A Novel Multi-Winner
Auction-based Transaction Mechanism for Blockchain Storage Networks |
|
143 |
10:55 |
FractalSync:
Lightweight Scalable Global Synchronization of Massive Bulk Synchronous
Parallel AI Accelerators |
|
41 |
11:05 |
NeurDORA:
Neural-Aided Decentralized Offloading Based on Resource Auction |
|
84 |
11:15 |
Enabling the Proxy
Computing Paradigm on DPU-based FPGA Acceleration |
|
70 |
11:25 |
Flex8: A Flexible
Precision Co-design for 8-bit Neural Network |
|
|
|
|
|
11:45--13:00 |
|
|
|
Main-B |
|
Pushing the
Boundaries of Cross-cutting Computing Challenges |
|
73 |
11:45 |
Accordion: A
malleable pipeline scheduling approach for adaptive SLO-aware inference
serving |
|
32 |
12:10 |
PowerSecBench: reveal
microarchitectural power leakages using generic RISC-V microbenchmarks |
|
18 |
12:35 |
FERIVer: An
FPGA-assisted Emulated Framework for RTL Verification of RISC-V Processors |
|
56 |
12:45 |
Charactering and
Mitigating Performance Variability in Parallel Applications on Modern HPC
Clusters |
|
|
|
|
|
14:00-15:15 |
|
|
|
Main-C |
|
System Software and
Runtime Frontiers |
|
110 |
14:00 |
Pattern Matching,
Transformation and Code Replacement on a Polyhedral Representation of Nested
Loops |
|
123 |
14:25 |
Multi-GPU Greedy
Scheduling Through a Polyglot Runtime |
|
55 |
14:50 |
SRBB-based Quantum
State Preparation |
|
1 |
15:00 |
RapidChiplet: A
Toolchain for Rapid Design Space Exploration of Inter-Chiplet Interconnects |
|
|
|
|
|
15:30--16:45 |
|
|
|
Main-D |
|
Hardware Frontiers |
|
3 |
15:30 |
AdaTP: Enhancing
Temporal Prefetching with Adaptive Metadata Filtering |
|
27 |
15:55 |
Combination of
Storage and Accumulation for Synchronous SpMV Acceleration on FPGAs with HBM |
|
99 |
16:20 |
Computing Efficiency
Improvement for Multi-PEA CGRA with Built-in Control Design |
|
|
|
|
|
|
|
|
|
DAY 2 |
|
|
|
10:00--11:15 |
|
|
|
Main-F |
|
Best Papers |
|
66 |
10:00 |
Ramping Up
Open-Source RISC-V Cores: Assessing the Energy Efficiency of Superscalar,
Out-of-Order Execution |
|
48 |
10:25 |
Register Dispersion:
Reducing the Footprint of the Vector Register File in Vector Engines of
Low-Cost RISC-V CPUs |
|
129 |
10:50 |
Solution of
Backtracking Problems on Tile-Centric AI Accelerators |
|
|
|
|
|
11:15--12:30 |
|
|
|
Main-G |
|
Systems
for AI |
|
44 |
11:15 |
Logic Gate Network
Inference Acceleration with RISC-V Custom Instruction Set |
|
104 |
11:40 |
A Custom RISC-V ISA
with Scalable Processing Units for Efficient Neural Network Inference |
|
17 |
12:05 |
FastSpMM: Leveraging
Tensor Cores for Sparse Matrix Multiplication |
|
|
|
|
|
14:00--15:15 |
|
|
|
Special Session |
|
Analog
Computing / ChipsAct |
|
|
14:00 |
Solving
Partial Differential Equations on an Analog, Optical Platform |
Chene
Tradonsky, Omri Wolf, Talya Vaknin, Dan Glück, Dov Furman |
|
14:25 |
Photonic
computing with Lithium Niobate integrated Photonics – from Concepts to
Products |
Victor
Brasch |
|
14:50 |
The
U.S. Microelectronics Research Programs and Where They Lower Barriers to
Co-Design |
James
A. Ang, Antonino Tumeo, Nicolas Bohm Agostini, Ankur Limaye |
|
|
|
|
15:30--16:45 |
|
|
|
Special Session |
|
CompSpace |
|
|
15:30 |
Coordinating
Instruments for Multi-Messenger Astrophysics |
Daisy
Wang, Ye Htet, Marion Sudvarg, Roger Chamberlain, Jeremy Buhler, James
Buckley |
|
15:55 |
Mitigating
Cross-Domain SEU Corruption in FPGA-Based AI Accelerators for Space
Applications |
Sarah
Azimi, Eleonora Vacca, Corrado De Sio, Luca Sterpone |
|
16:20 |
Cutting-Edge
Strategies for Radiation Effect Estimation on Asteroids Space Mission |
Eleonora
Vacca, Sarah Azimi, Luca Sterpone |
|
|
|
|
|
|
|
|
DAY 3 |
|
|
|
10:30--11:30 |
|
|
|
Main-H |
|
Memory
Frontiers |
|
11 |
10:30 |
CVA6-VMRT: A Modular
Approach Towards Time-Predictable Virtual Memory in a 64-bit Application
Class RISC-V Processor |
|
81 |
10:55 |
Corrosion Hammer: A
Self-Activated Bit-Flip Attack to the Processing-In-Memory Accelerator |
|
52 |
11:20 |
Enhancing
Practicality of Memory Compression for GPUs with High-Throughput
Simplifications |
|
|
|
|
|
11:30--13:00 |
|
|
|
Main-I |
|
Crosscutting
Developments and Hardware Frontiers |
|
72 |
11:30 |
Multi-Task
Collaborative Learning for Robust Diabetic Retinopathy Grading on Low-Quality
Fundus Images |
|
97 |
11:55 |
MCCNet: Multi-Scale
Context Cross-Attention Network for Diabetic Retinopathy classification |
|
67 |
12:20 |
Unleashing
Optimization in Dynamic Circuits through Branch Expansion |
|
124 |
12:45 |
Quantum Circuit
Design for Finding k-Cliques via Quantum Amplitude Amplification Strategies |
|
|
|
|
|