News / Design & IP / Chimera: A Configurable LLM Decode Accelerator Architecture with Compute-Memory-Floorplan Co-Design for HBM-Equipped Multi-Die FPGAs
Chimera: A Configurable LLM Decode Accelerator Architecture with Compute-Memory-Floorplan Co-Design for HBM-Equipped Multi-Die FPGAs
By The Semiconductor Hub news desk ·
Link post
GPUs are widely used for LLM inference, but single-request decoding is memory-bound, leaving their compute underutilized while they draw substantial power. HBM-equipped FPGAs are well suited to LLM decoding: their customizable datapaths use memory bandwidth more energy-efficiently than GPUs. However, high memory bandwidth alone does not ensure high decode performance: exploiting it requires parallel compute and memory interfaces, whose resource costs and placement on the chip can limit the thro…
Read at arXiv cs.AR (Hardware Architecture)Source: arXiv cs.AR (Hardware Architecture), published . The summary is the Hub's own; the full story is at the source. Report a rights or accuracy concern