idoeestuff

omg running ref spec on gem5 fs mode...

i think this is just anecdotal; this person is clearly in the community.

i'm not sure this data is useful, because we'd disagree on "people with the right connections".

1. torellas student (now at mit) release code for spectre defense. yeah maybe it was to help her job hunt, but at least it proves (to me) that torellas isn't just pushing crap in the past. i understand you have issues with torellas handling of this incident (as do I), but taking issue with his isca papers seems to be overreach.

2. i dont understand how you can pick on "cycle accurate" simulation when every simulator in our community has problems. at least in gem5 (one of torellas isca2020 paper), we as reviewers can look at the code. how about the famous "in house x86 pin based simulator"? most pin based simulators performance numbers should rightfully be joke, but we use them anyway, because we aren't going to rewrite them.

3. at the end of the day, most of our work is unverifiable, because we make so many approximations anyway. one young faculty told me "we just need to see the idea and determine if it makes sense". i just do not know if this is the right thing to do, or if its a lie we tell ourselves.

seems you wanted reply to another person

what dept are you in where faculty wouldn't support each other? surely the powerful faculty usually are the ones with the grants coming in, sometimes funding the other faculty (at least the dept/university).

can you expand? i know the clique, but at least for the specific work i follow, the work isn't bad recently.

of course, nothing surprises me.

i would like add some discussions. when i say "i", you can either read "i" as i am a pc or external reviewer, or maybe im a grad student.

1. i dont want say anything which gets me trouble, but hotcrp was set up wrong by the chair in that year ISCA. i know pc members were able to download the whole paper submission list. i personally saw _all_ papers and _all_ reviewer comments on anything i did not submit. it is likely that everyone had access to this, because i am not a "big players" in this field. i really doubt i had some special access because i have no relationship to the chair that year.

i still have all the papers from isca19. i should not have these, but i just got them from a normal download (no enumeration or guessing urls).

2. point 1 does not excuse leaking, just made easier. instead of calling all pc friends and asking them to call their pc friends, you just need to call one pc friend not on your submission. he could see it.

3. good luck getting tao li. hint: did he fund anyone in the past who was investigating him? did he fund anyone who reviews his papers?

4. the tao li story is deeper. a) there's race issue. because it's easier to manipulate people if your business is being a chinese -> usa faculty pipeline. and once people go through your pipeline, they are even more likely to keep it going! b) if you think the paper push is bad, wait until the details of how he actually treated his students come to life. hint: some things advisors do to students in china is immoral, but tolerated. those things are illegal in usa.

5. this is bigger than tao li. you will never get rid of the cliques, but it's at point that i don't even want read the papers anymore. why sell my integrity for grants, when i could get industry money where at least the product shows the work is not crap?

6. if you want to know some worst players, i heard they are upset they are not in micro2020 reviewer list :p. of course it's not a completely good reviewer list, our community is too small!

7. i hope one day we can honestly talk this out. i would like to tell pressuring stories :)