Long synthesis time on Vitis

[KevinSmild]

Hi, It seems that synthesis time is really long, specially because the interval requirements for the pipelining are not met and Vitis needs to guess the right parameters (which it does badly). I have been trying to use this tool to compile a GBDT based on XGBoost with 700 trees, 40 features - 1000000 data points - and the following parameters:

{
            'objective': 'binary:logistic',
            'grow_policy': 'lossguide',
            'eval_metric': 'rmse',
            'eta': 1,
            'gamma': 1,
            'alpha': 1,
            'max_leaves': 7,
            'max_depth': 3,
            'seed': 0,
            'nthread': 16
 }

Trying to compile the resulting HLS code without modifying it fails because of the optimizations. After adjusting the optimizations, synthesis time takes hours. The same happened with a similar GBDT with only 50 trees and without modifying the HLS code.

Is there something I might be doing wrong? Is this library recommended for such "big" models?

[thesps]

Hi, in this case I would recommend using the VHDL backend, if possible. The long synthesis time with the HLS is an issue that we don't have a solution for yet. You can see a comparison of the synthesis time as a function of the number of estimators (with depth fixed at 3), from our paper:

(Blue x is HLS C Synthesis, blue + is Logic Synthesis of HLS C Synthesis results, orange circle is Logic Synthesis of VHDL backend code)

[KevinSmild]

Hi, Thanks for the reply. VHDL will make things a little bit more complicated since I am trying to use this as part of Vitis Design Flow, but I'll try.

I still wonder why Vitis compilation takes so long tho. Compilation time is ridiculously long.

Cheers.