Closed Olivier-Dopeli closed 3 years ago
The CSV files in the Aladdin plug-in records the energy and area for 32-bit int adder and multipliers, so in aladdin_table.py
, we perform interpolations to get the energy and area for these units of different data widths. For multipliers with data width d
, the values in the CSV files are scaled by 32/d
^2 and for adders, it is just a linear scale, e.g., as implemented here: https://github.com/Accelergy-Project/accelergy-aladdin-plug-in/blob/master/aladdin_table.py#L305
For the specific example, the data width is 8 bits, so we have 179/4+4600/16 = 332.25 for mac area.
Can you support on this related issue?
https://github.com/NVlabs/timeloop/issues/199#issuecomment-1461866785
Please see the reply in the timeloop repo.
Hello,
I'm looking at the different exercises in the tutorial to understand the Timeloop and Accelergy frameworks.
In example 05-mapper-conv1d+oc-3level of Timeloop , the architecture is composed of a single PE containing 1 integer MAC. The command
timeloop-mapper arch/3level.arch.yaml prob/conv1d+oc.prob.yaml mapper/exhaustive.mapper.yaml constraints/null.constraints.yaml -o output
generates the filetimeloop-mapper.ART_summary.yaml
which contains the following MAC area data:I have seen that it is script
aladdin_table.py
that collects the area data of a multiplier and an adder in the corresponding .csv files. By default, the data corresponding to a latency of 5ns are collected. Then the area of the multiplier and the adder are added to estimate the area of the MAC. In this case, I think I can manually estimate the area :Adder area : 1.79E+02
+mult. area : 4.60E+03
=MAC area : 4 779 um^2
But, the manually calculated MAC area doesn't correspond to the MAC area obtained in the file
timeloop-mapper.ART_summary.yaml
Can you explain to me why I have this difference, please?
Thank you in advance.