Processing-in-Memory Development Strategy for AI Computing Using Main-Path and Doc2Vec Analyses

Round 1

Reviewer 1 Report

This manuscript utilized Main Path Analysis (MPA) to identify the core technology of PiM. The result is then analyzed to determine the potential partners for technical cooperation required for PiM technology development. This manuscript can be considered for publication if the following comments can be replied:

1. In 16, “analyzed b using Document.....”, analyzed by?

2. In figure 1, If central processing unit has connection with memory device in (b), since it has connection with memory device in (a)? Also, the subtitle (a) and (b) are overlap with the figure.

3. Line 127, ”In relation to technological partnership, many studies have been conducted on defining and discovering technological partners, types of cooperation, and effect of performances”, corresponding literature should be cited here.

4. Font was not unified, such as in line 244, “related”.

5. The conclusion part should be more concise.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors have proposed a Strategy for AI Computing using Main-Path and Doc2Vec. In their manuscript, I have following concerns:

1. Abstract of the article is written more generically. It must address the introduction, problem statement and then connect the proposed technique with problem statement.

2. Figure 2 needs to be redrawn to adjust the legends.

3. What is the novelity of this article?

4. Section 3 and section 4 are weak. Authors need to enrich both these sections with more details about the methods used, experiments performed and so on.

5. Section 5 needs improvements.

6. Authors need to validate their methodology by comparing it with sota.

7. Authors need to carry out an ablation study to prove the authenticity of their methodology.

8. Authors need to present mathematical modeling for their methodology.

 

English of the article in adequate. 

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

1. the first and second challenge have no references at all. please justify both scientifically.

2. please provide the reasoning what is stated in line 178-179. 

3. in 3.2 please provide why technically key-route and global search do not match with the goal.

4. please scientifically justify the weight in line 224, 318, and 319. why only one combination of values? simulation needs more combination for validation.

5. why intel is very outstanding in table 2 compared to other candidates? is it as expected from beginning?

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

This manuscript can be accepted in present form

Reviewer 2 Report

Paper can be accepted in its current form