Yuzong Chen

About running COFFE with local optimization instead of global

13

Hi, I am currently using coffe to run automatic sizing for a full adder. I only care about the area and delay trade-off for this subcircuit without considering the global...

About employing diffusion sharing for multi-input gates like nand2 nor2.

1

Hi, I am currently using COFFE to run simulations for a modified BRAM and I am using many nand gates, nor gates, sense amplifiers and write drivers as in Aman's...

About wordlinedriver area calculation in fpga.py

6

In coffe/fpga.py, line 3593 when calculating and updating the area for wordline drivers. At line 4529, the calculation only considers the areafac which equals to 2**self.row_decoder_bits. However, should this area...

Obtained different PPL for Wikitext and C4 compared to results reported in the paper

2

Hi, thank you so much for the amazing paper and repo. I am trying to reproduce the Wikitext and C4 perplexity in the OmniQuant paper. I downloaded the repo and...