This is a great list but I would rather look at the most cited papers from that conference (say 10 years later). As an example, MapReduce did not win the best paper in OSDI 2004. However, it has impacted the industry like no other paper in that conference.
I cannot come up with any correlation except bigger screens help you avoid ads better? All my ad clicks(or taps) on facebook on my phone have been accidental.
I do not fully agree with no-innovation comment. Many of their products, such as the iphone were indeed innovative.
I however, do agree with the latter that it has no footprint of its contributions. Research, and computing in general, builds on others work and in that sense apple comes as across as a douchebag - no white papers, publications or even blogs from employees. Only public documentation is usually served by an army of lawyers.
Until a year ago, they had steve jobs to justify this selfish behavior. And now there is no steve jobs and such behavior will create a huge PR hit for apple. Unless they can create a fantastic product record pre-jobs, it will be very hard. For example, the first feature sans jobs was Siri and it wasn't an universal success by any means. Good time to buy microsoft stock.
also the bit about publications - "it only matters if there are very few or none". Considering the author is a PhD himself, it is some what self-deprecating. And he works at google interviewing PhDs. sigh
I believe that quality of publications matters a lot. I've seen many passionate hackers move into industry after Phd and some of them have authored seminal papers. I am positive that most industry positions recognize these contributions.
I'm mostly convinced that current form of interviewing process of asking trick programming questions is little random. And this post has many red flags to confirm this. All the best google!
i am not able to fully understand what it is shooting for. The README, says it avoids the VM layer (which seems impossible in a pure software solution). The code suggests its merely doing a kmem_cache_zalloc. am i missing something?
its true that vm is an overhead now, with infinite/very large memory, the concept of virtual memory is outdated. TLB misses are too high and huge pages just don't cut it. this has been repeated over and over but we need to re-design the VM/hardware to support TLBless access for a portion of memory of the working set size of your primary application.