.png){kind=icon}
.png){kind=icon}
Return
FastTrackGPU: Static-AnalysisGuided Analytical Modeling for Softcore GPUs
.png){kind=icon}
PRE
AI
DOI：10.1109/LCA.2026.3677349.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
SoftGPUs make FPGA platforms practical data-parallel accelerators by providing a GPU-like programming model on top of an open RTL-to-software stack. However, their high configurability creates a large configuration space, making it difficult to identify workload-optimal designs under FPGA resource constraints. We address this challenge by proposing the first analytical model for softGPUs and four decision policies that aggressively prune the design space. Implemented in our FastTrackGPU framework, our lightweight analytical model driven by static analysis enables orders-of-magnitude faster configuration selection than Bayesian optimization while boosting kernel throughput by 1.55 & times; (geomean) over area-greedy baselines.
Keywords:
Field programmable gate arrays
Throughput
Kernel
Instruction sets
Graphics processing units
Static analysis
Analytical models
Table lookup
Sockets
Optimization
Softcore GPU
FPGA
DSE
analytical model
Journal
I
IF:
1.4
Papers:
42
Citations:
781