nyu-mlda / openabc Goto Github PK

Hello. I'm trying to download dataset using link from README:
https://app.globus.org/file-manager?origin_id=ae7b03ad-9e50-472c-9601-ff99054ae47c&origin_path=%2F

I get the following error:

Authentication Required
Identity set contains an identity from an allowed domain, but it does not map to a valid username for this connector

Help me to solve this, please.

The origin full dataset is too huge, we have trouble to download it. Since, we only want the the initial AIG file. We want to know, is there any zip file/link that only have the initial AIG files? Thanks.

Hi,

Is that possible that the original Verilog or VHDL codes can be released?

Thanks,
Min

Hi,

I am working through your paper and code, it appears that you in the QoR prediction task, you use QoR label that is generally between -3 and +3 and it captures the number of nodes in an AIG. However, it is not clear to me how do you get the labels from that information. Could you please clarify.

Thanks,
Nikhil

Hello. I'm trying to use your 'andAIG2Graphml.py' to generate graphml files from bench files.

However, I failed when the line in bench file contains 'DFF'. The alert in line 166 of 'andAIG2Graphml.py' is raised:

Line contains unknown characters. top.fpu_mul+x1_mul.pre_norm_fmul+u2^exp_out~0_FF_NODE = DFF(n742_1)

Please help me to solve it, thanks!

I‘m a follower of your works and do some research based on openABC-D. We want a pre-trained model for downstream works but the model trained by ourselves is slightly worse than the result in the paper. Could you provide the pre-trained QoR prediction model(net3)? Thanks a lot.

Hello,
I found there are some sequential circuits in the dataset. ABC will generally synthesize some latches in the AIG. However, the AIG node types defined in this dataset are only [PI, PO, AND]. Could you tell me how to deal with this problem? Did you simply remove the latches from the AIG?
Best regards

Hi there, I couldn't find the requirements file in your repository, as indicated by the README.

Hello,

It seems that dft_orig.bench and idft_orig.bench are not in ./bench_openabcd/. Do you know where I could find them, or if I missed something?
Thanks!

Hi,

We want to use your dataset to do QoR predictions. We followed your README.md file and downloaded the 19GB dataset for ML. We extracted the .pt files and read them, but are struggling to make sense of the numbers. The excel image shows the data we extracted from synthesisStatistics.pickle. Can you tell us what the numbers for each design indicate?

The snippet below shows the data we got from the 'ac97_ctrl_syn706_step0.pt'. This data is below:
{'and_nodes': tensor(11464), 'desName': ['ac97_ctrl'], 'edge_index': tensor([[ 2339, 2340, 2340, ..., 15938, 15938, 15939], [ 2338, 2, 3, ..., 2336, 15932, 15938]]), 'edge_type': tensor([1, 0, 1, ..., 1, 0, 0]), 'longest_path': tensor(11), 'node_id': ['ys__n0', 'ys__n1', 'ys__n3', 'ys__n4', 'ys__n7', ...], 'node_type': tensor([0, 0, 0, ..., 1, 2, 1]), 'not_edges': tensor(14326), 'num_inverted_predecessors': tensor([0, 0, 0, ..., 1, 1, 0]), 'pi': tensor(2339), 'po': tensor(2137), 'stepID': [0], 'synID': [706], 'synVec': tensor([1, 4, 5, 6, 0, 3, 0, 1, 6, 1, 1, 4, 6, 1, 1, 3, 0, 1, 0, 5])}
Can you explain how do we get the timing numbers from the above?

We were wondering if we need to download the 1.4TB zipped files to generate the ML training and testing datasets, or is there a better way to go about this? Can you guide us on how to use the useful datapoints from the 1.4TB dataset without downloading it all? We are students of UC San Diego and trying to maximize our resource utilization.

Thank you!

Hi,
I follow the tutorial but I can't take the training and evaluation step:
1.the requirements.txt contains many libraries that cannot be installed, so I just use my own env.
2.But the ML-ready dataset is too old, I can't create an environment(pytorch==1.7.0 can't be installed) to use it.
do you have a new ML-ready dataset generated by new version of pyG?
Best regards

Hi,
I downloaded the big dataset. When I merge (cat) the files and I want to unzip the final part I get the following error.
"bad zipfile offset (local header sig):"
I appreciate it if you provide the instruction for reconstructing final dataset. (merging and unzipping it).