Forgot your password?
typodupeerror

Comment: Re:Is there anything new here? (Score 3, Informative) 143

by enriquevagu (#47299371) Attached to: Researchers Unveil Experimental 36-Core Chip

Some knowledge about multicore cache coherence here. You are completely right, Slashdot's summary does not introduce any novel idea. In fact, a cache-coherent mesh-based multicore system with one router associated to each core was presented on the market years ago by a startup from MIT, Tilera. Also, the article claims that today's cores are connected by a single shared bus -- that's far outdated, since most processors today employ some form of switched communication (an arbitrated ring, a single crossbar, a mesh of routers, etc).

What the actual ISCA paper presents is a novel mechanism to guarantee total ordering on a distributed network. Essentially, when your network is distributed (i.e., not a single shared bus, basically most current on-chip network) there are several problems with guaranteeing ordering: i) it is really hard to provide a global ordering of messages (like a bus) without making all messages cross a single centralized point which becomes a bottleneck, and ii) if you employ adaptive routing, it is impossible to provide point-to-point ordering of messages.

Coherence messages are divided in different classes in order to prevent deadlock. Depending on the coherence protocol implementation, messages of certain classes need to be delivered in order between the same pair of endpoints, and for this, some of the virtual networks can require static routing (e.g. Dimension-Ordered Routing in a mesh). Note a "virtual network" is a subset of the network resources which is used by the different classes of coherence messages to prevent deadlock. This is a remedy for the second problem. However, a network that provided global ordering would allow for potentially huge simplifications of the coherence mechanisms, since many races would disappear (the devil is in the details), and a snoopy mechanism would be possible -- as they implement. Additionally, this might also impact the consistency model. In fact, their model implements sequential consistency, which is the most restrictive -- yet simple to reason about -- consistency model.

Disclaimer: I am not affiliated with their research group, and in fact, I have not read the paper in detail.

Comment: I doubt it (Score 4, Interesting) 102

by enriquevagu (#46711665) Attached to: Intel and SGI Test Full-Immersion Cooling For Servers

(sorry for the duplicated posting; the previous one was cut because of problems with the html marks)

In order to obtain a 90% reduction in the energy bill, cooling must account for 90% of the power of the DC. This implies a PUE >= 10. As a reference, 5 years ago virtually any DC had a PUE lower than 3. Nowadays, PUE lower than 1.15 can be obtained easily. As a referecence, Facebook publishes the instantaneous PUE of one of its DC in Prineville, which at the moment is 1.05. This implies that any savings in cooling would reduce the bill, at much, in a factor of 1.05 (1/1.05 = 0.9523).

On the other hand, I believe that this is not the first commertial offer for a liquid-cooled server, Intel was already considering two years ago, and the idea has been discussed in other forums for several years. I can't remember right now which company that was actually selling these solutions, but I believe it was already in the market.

Comment: I doubt it (Score 0) 102

by enriquevagu (#46711657) Attached to: Intel and SGI Test Full-Immersion Cooling For Servers

In order to obtain a 90% reduction in the energy bill, cooling must account for 90% of the power of the DC. This implies a PUE >= 10. As a reference, 5 years ago virtually any DC had a PUE instantaneous PUE of one of its DC in Prineville, which at the moment is 1.05. This implies that any savings in cooling would reduce the bill, at much, in a factor of 1.05 (1/1.05 = 0.9523).

On the other hand, I believe that this is not the first commertial offer for a liquid-cooled server, Intel was already considering it two years ago, and the idea has been discussed in other forums for several years. I can't remember right now which company that was actually selling these solutions, but I believe it was already in the market.

Comment: Homework are part of the learning process (Score 1) 278

by enriquevagu (#46554047) Attached to: Don't Help Your Kids With Their Homework

Homework is part of the learning process; helping with homework prevents the kid from doing them and, in the process, learning. Solving math problems for homework, as an example, is not because the teacher wants to know the final answer; it's because the teacher wants the student to confront a new type problem and, in the process of confronting it and guessing how to obtain the solution, learn. I give detailed solutions to the class problems to my undergraduate students (they would obtain them anyway, and in many cases with errors), but I always insist that looking at the solution should be the last resort if they don't know how to face the problem (solutions are intended for checking their own's).

The problem with external help (from the parents, typically) is that, in many cases, the parents get involved in excess and actually do the homework for their sons, so the teacher cannot find any error in the child's results. I know a case of a mother who was doing exactly this, because his kid didn't get very good grades (I was even asked for help in some work the child had to do for school with the computer!). The grades started getting worse and, three years later, the kid was in special education. I know this is not the only reason, but I'm confident it affects a lot.

Comment: Classification, first step (Score 1) 983

by enriquevagu (#46463851) Attached to: How Do You Backup 20TB of Data?

The first step is to classify the data in two groups: what you would not want to lose at any cost, and the redundant data (movies, music, etc) that you could survive without. This is the most important step

The second step is to backup the important data using an external 1 TB drive, tape or similar.

Optionally, the third step is to delete the remaining 19 TB.

Comment: Our approach in our research group (Score 1) 189

by enriquevagu (#45750709) Attached to: Scientific Data Disappears At Alarming Rate, 80% Lost In Two Decades

This problem occurs even for people in the same group, who often find problems to repeat the simulations from our own papers, and even as recent as one year ago. The problems typically come from people leaving (PhD finished, grants that expire, people that move to a different job), changes in the simulation tools, etc.

In our Computer Architecture research group we employ Mercurial for versioning the simulator code. Thus, we can know when each change was applied. For each simulation, we store both the configuration file that is used to generate that simulation (which also includes the Mercurial version of the code which is being used) and the simulation results, or at least only the interesting results. Multiple simulators allow for different verbosity levels, and in most cases most of the output is useless, so we typically store the interesting data (such as latency and throughput) because otherwise we would have no disk space.

Even with this setup, we often find problems trying to replicate the exact results of our own previous papers, for example because of poor documentation (this is typical in research, since homebrew simulation tools are not maintained as one would expect from commertial code), changes that introduce subtle effects, code that gets lost when some person leaves or simply large files that get deleted to save disk space (for example, simulation checkpoints or network traces, which are typically very large).

However, you typically do not need to look back and replicate results, so keeping all the data is a useless effort. I completely understand that research data gets lost, but I think that it is largely unavoidable.

Comment: Server description (Score 1) 301

by enriquevagu (#44559805) Attached to: EFF Slams Google Fiber For Banning Servers On Its Network

all ISPs are deliberately vague about what qualifies as a 'server.' ... because TCP clearly specifies it.

The fact that some programs might behave correctly when implementing a server, or not (eg: skype) or the fact that, in some cases, ISPs allow certain services or ports, does not mean that a 'server' is something arcane. It's you that don't know it.

Comment: Comparison to PCM (Score 5, Informative) 69

by enriquevagu (#43987891) Attached to: Computer Memory Can Be Read With a Flash of Light

The link to the actual Nature Communications paper is here: Non-volatile memory based on the ferroelectric photovoltaic effect.

This somehow resembles Phase-Change Memory (PCM). PCM devices are composed of a material which, under a high current, there is a thermal fusion and changes to a different material status, from amorphous to crystalline. This changes two properties: light reflectivity (exploited in CDs and DVDs) and electrical resistance (exploited in emerging non-volatile PCM memories). The paper cites PCM and other types of emerging non-volating memories.

In this case, it is the polarization what changes, without requiring a thermal fusion, therefore increasing the endurance of the device, one of the main shortcomings of PCM. The other main shortcoming of PCM is write speed due to the slow thermal process, in the paper they claim something like 10ns. If this can be manufactured with a large scale of integration and low cost, it will probably be a revolution in computer architecture.

Life is difficult because it is non-linear.

Working...