Microsoft, Intel to team on new parallel, multicore research efforts

Microsoft, Intel to team on new parallel, multicore research efforts

Summary: In what has become a not-so-secret secret, Microsoft and Intel are set to unveil on March 18 their joint funding of more parallel-processing research work, according to various industry reports.

SHARE:
TOPICS: CXO, Intel, Microsoft
41

In what has become a not-so-secret secret, Microsoft and Intel are set to unveil on March 18 their joint funding of more parallel-processing research work, according to various industry reports.

EETimes says the Wintel couple will announce it is helping fund the new Parallel Computing Lab at the University of California at Berkeley. While Microsoft officials are not publicly confirming that report, the announcement tomorrow does involve Microsoft's ongoing interest in multicore research, a company spokeswoman confirmed.

Update on March 18: The reports were correct. Not only is UC Berkeley one of the participants in the new Parallel Computing Research Centers announced today by Microsoft and Intel, but so is the University of Illinois at Urbana-Champaign. According to the press release: "Microsoft and Intel have committed a combined $20 million to the Berkeley and UIUC research centers over the next five years. An additional $8 million will come from UIUC, and UC Berkeley has applied for $7 million in funds from a state-supported program to match industry grants." Microsoft and Intel are billing this as the first joint industry-university collaboration "of this magnitude" that is focused on "mainstream" -- not just scientific/high-end parallel-computing research.

Microsoft has a number of its own research and commercial initiatives underway in the multicore/parallel-processing arenas. The company released in late 2007 a test build of Parallel FX, which is a set of parallel extensions to Visual Studio. The Microsoft Research folks are working on the MS-ManiC (Memory Systems for Many Cores) project, which is focused on designing scalable memory-system architectures for many-core processors.

The Research team also has a request for proposal (RFP) out that will fund three-year research projects in multicore computing. The Safe and Scalable Multicore Computing RFP is for $1.5 million, which MSR anticipates making available in nine awards averageing $166,000. Proposals for that RFP were due last week, and recipients are st to be notified on April 23, 2008.

One of Microsoft's parallel projects I've been following quite closely is Dryad, which is its distributed-computing infrastructure for large-scale (thousands of servers) parallel applications. Dryad is Microsoft's answer to Google's MapReduce technology. Dryad can scale from multicore single computers, to small clusters of computers, to data centers with thousands of computers, according to Microsoft.

On the Microsoft Research site, there's a new research paper on Dryad which Microsoft's researchers are set to present at the European Conference on Computer Systems (EuroSys) in Portugal next week.

Dryad is not pure research; Microsoft's adCenter online advertising team is using the technology today. From the research paper:

"SQL Server Integration Services (SSIS) [6] supports workflow-based application programming on a single instance of SQLServer. The AdCenter team in MSN has developed a system that embeds local SSIS computations in a larger, distributed graph with communication, scheduling and fault tolerance provided by Dryad."

The Windows Live Search team seems to be making use of Dryad, too. Again, from the paper:

"We would like to thank all the members of the Cosmos team in Windows Live Search for their support and collaboration."

(Cosmos, as I confirmed recently, is the distributed storage layer underlying Live Search.)

One more update from March 18:  Microsoft's Tony Hey, corporate vice president of External Research at Microsoft Research, itemized during a call with press and analysts about the new industry-research collaboration several additional multicore/parallel efforts Microsoft has undertaken. These include:

Topics: CXO, Intel, Microsoft

About

Mary Jo has covered the tech industry for 30 years for a variety of publications and Web sites, and is a frequent guest on radio, TV and podcasts, speaking about all things Microsoft-related. She is the author of Microsoft 2.0: How Microsoft plans to stay relevant in the post-Gates era (John Wiley & Sons, 2008).

Kick off your day with ZDNet's daily email newsletter. It's the freshest tech news and opinion, served hot. Get it.

Talkback

41 comments
Log in or register to join the discussion
  • Joint effort to monopolize the next 20 years

    ...
    fr0thy@...
    • Dude, you need a new recording

      This one is worn out and plain BORING.
      No_Ax_to_Grind
      • LOL

        You don't agree with the suggestion then ;-)
        fr0thy@...
        • Seriously frothy

          There are times you actually present a point with knowledge and effective delivery. In fact I've found myself reconsidering my own thoughts once or twice after reading your posts.

          But when the post is nothing more than rant, rant, rant, bash, bash, bash I just turn your volume down to 1 or less and pretty much ignore anything of value you did have to say.

          Truth is, I know that you are capable of far better discussion, it's just sad you don't step up to that plate more often.
          No_Ax_to_Grind
          • Seriously No_Ax

            We all rant at times, it's human nature.

            What I do like about Zdnet is that there are a number of posters that we all get familiar with, have our say, and enjoy reading all of the differing perspectives.

            I do appreciate your comment. It's good to know that, over time, we are all heading towards a better direction.

            I will admit, in response to your comment, that I have experienced, personally, immediate family tragedy as a rezult of the pathetic blind greed that is, in this industry, Microsoft.

            That is doubled by the fact that following the aforementioned, I got on with life and really love computing, but there it is again, greed greed greed, pretending to give a **** and trying to dictate the reason why we are even born.

            I'll leave it at that, but MS ain't technology.
            fr0thy@...
      • No_Ax calling someone a broken record , now thats ripe - NT

        NT
        raycote
        • (Over)ripe......... tripe

          Not much difference. Either way it
          provokes only one sentiment......
          pheeeyooooo!
          Ole Man
      • Pot, Kettle, Black - no_axe

        Arrange as you see fit
        deaf_e_kate
      • Or, perhaps...

        ...a medication adjustment.
        MalumRegnat\
  • It's about time...

    Somebody put money into CS research, especially parallel stuff. Maybe this money will spur others to do likewise. Maybe CS departments will now be able to "rise from the ashes" of the .gone era and do what they should have been doing - research and teaching!

    Disclaimer: I've about had it with people who tell me that multi-core is better/faster but can't tell the difference between sequential and parallel algorithms, and for that matter didn't even know there might be a difference. And don't get me started on those who are at best confused by program, process, and thread.
    zkiwi
    • Actually, been going on for some time.

      I remembr the original "guesstimates" for the Longhorn platform and it was for a Quad (or more) and MS was working with both Intel and IBM at the time.
      No_Ax_to_Grind
      • Research versus Research

        Parallel has been around a while and has been used in server and supercomputing realms. But there's a huge difference in researchers improving the performance of a database search algorithm on a multiprocessor server versus getting the most out of numerous everyday apps on a multicore PC. But given the explosion in multicore processors (I'm guessing, but we may see more multicore processors manufactured in 2007 and 2008 than in all previous years combined), there's plenty of research to do and breakthroughs to be discovered. I'm sure the tempo of research has been ratcheted up from the Longhorn platform development days.
        Rodney Davis
        • I agree completely

          Lots remains to be done.
          No_Ax_to_Grind
      • Which clearly explains why...

        Now there's a dearth of knowledge and experience in this area?
        zkiwi
        • Ever moving target

          I am certain the tech for multi-core has changed a lot in the last 5 years.
          No_Ax_to_Grind
          • However...

            The theory behind it hasn't and it hasn't been taught well/at all in colleges (as of yet).
            zkiwi
          • Oh I agree, but I think you underestimate

            I think you underestimate multi-core or paralle processing and the changes it will require in how we go about building and using software. Personally, I think in the next 5 to 10 years paralle multi processors will cahnge the landscape completely.

            Honestly, people haven't even scratched the surface of theis technology so teaching it effectively is going to take some time. The "teachers" need to figure out where they are headed first.
            No_Ax_to_Grind
          • "need to figure out where they are headed first"

            A fine example of "parallel"... the
            blind leading the blind.

            You won't learn much if they teach
            you what they DON'T know, eh? Once
            upon a time, long ago, research was
            conducted in the lab, until they
            could produce a certified reliable
            product....... not so nowadays....
            the public gets to participate (AND
            PAY FOR!) all research..........
            Ole Man
        • He won't get it ... he still doesn't get FOSS ...

          I expect that you remember the burying of massively multi-parallel stuff a couple of decades ago. Conversations at that time likened it to the everlasting light bulb scenario, in that the markets always tend back to a controlled ongoing drip drip drip. Some likened Intel's promoting of the MHz of chips as another example of this - the consumer would relate to 25 being "better" than 20.

          We can only surmise where we could be by now. As is well documented here on ZDNet, I feel exactly the same way about Windows - in fact, Windows is an anti-research device because to get involved and learn, you had to be eligible to work for Microsoft. Why else has FOSS been so massively embraced ....

          The continents that embrace FOSS mentality the most will be laughing at all the others, and yet the others just can't see .....
          fr0thy@...
          • My theory on OSS's success...

            Is more along the lines of, "Hey, there's all that stuff that we teach the theory of sitting there, and we get it for free, and to contribute to it for free as well."

            And I would add to that, the bleeding edge of putting theories into practice seems to be tipping more and more towards OSS for the above reasoning.

            That's not to say it's not nice that Microsoft's pumping money into research at the university level, I just have my suspicions as to the encumbering of it, and that Microsoft is aiming at limited use, free to them but not others kind of research. I could be wrong, but...
            zkiwi