발행물
컨퍼런스
MLArchSys
1970
,
Accuracy Boosters: Epoch-Driven Mixed-Mantissa Block Floating Point for DNN Training
SPMA
AstriFlash: An Online Flash-Based Memory Hierarchy
HENND
Accelerating Neural Network with Selective Thread-Level Parallelism Regulation and Cache Bypassing on GPUs
ACM/IEEE International Symposium on Computer Architecture
Avant-Garde: Empowering GPUs with Scaled Numeric Formats
ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems
SSFFT: Energy-Efficient Selective Scaling for Fast Fourier Transform in Embedded GPUs