Raja KoduriVerified account

@Rajaontheedge

some times ice some times water but mostly human. exa pixelated. interests: all math and any moving imagery.

32°F
Joined December 2009
361 Photos and videos Photos and videos

Tweets

You blocked @Rajaontheedge

Are you sure you want to view these Tweets? Viewing Tweets won't unblock @Rajaontheedge

  1. Apr 17

    In the link above Rich Sutton talks about brute force and AI..Moore’s law could also be viewed as “brute force” or our collective will (or ego) to stubbornly pursue exponential trajectories as a daily routines

    Replying to @Peter_shirley
    To be fair, they mention ray tracing and the z-buffer (but call them "brute-force object space" and "brute-force image space") and dismiss them as impractical, which they pretty much were in 1974. It's ironic that when it all shook out those were the only two left standing.
    2 replies 3 retweets 20 likes
    Undo
  2. Apr 14

    Congrats Pete and Makuta team - what a journey! Your contributions ushered golden age of VFX in Indian cinema - looking forward to the next chapter as the creative world embraces real-time virtual production

    turns 11 years old today!! Thanks to everyone who have supported us over the years!!
    2 replies 5 retweets 30 likes
    Undo
  3. Retweeted
    Apr 1

    Intel’s founders were motivated by the love of problem-solving, the possibilities of science, and their vision that silicon technology could make people’s lives better. That sense of purpose is very much alive today. More in our annual report

    1 reply 12 retweets 103 likes
    Undo
  4. Retweeted
    Mar 26
    Replying to

    Nice one, . You know you are always top of mind for me!

    7 replies 2 retweets 181 likes
    Undo
  5. Mar 26

    ~100 Billion Neurons plus >100 Billion Transistors....chief geek unleashed

    20 replies 53 retweets 643 likes
    Undo
  6. Mar 24

    Software is harder than hardware - collectively we are making great progress though. But it's very important for all (parallel) code to be portable to all architectures

    This is a great post on how we're working with software developers, Intel and the oneAPI initiative to prepare a wide range of software for Intel's upcoming GPUs, XPUs. This is all using the SYCL standard, so it isn't just about Intel hardware.
    Show this thread
    5 replies 18 retweets 124 likes
    Undo
  7. Mar 24

    Early days. so you may see us mixing up both terminologies for a bit.

    3 replies 52 likes
    Show this thread
    Show this thread
    Undo
  8. Mar 24

    Internally we also are switching to "tile" nomenclature to differentiate silicon that needs to be packaged with advanced high density packaging (55 micron bump pitches and below) v/s silicon "chiplets" that can be packaged with standard packaging

    2 replies 5 retweets 75 likes
    Show this thread
    Show this thread
    Undo
  9. Mar 24

    Andreas, in Jan we didn't account the HBM's as individual tiles. That's the main difference. 16 Xe HPC (internal/external) 8 Rambo (internal) 2 Xe Base (internal) 11 EMIB (internal) 2 Xe Link (external) 8 HBM (external)

    Hey ! In January you mentioned 41 chiplets for Ponte Vecchio, yesterday Intel talked about 47. Can you explain the discrepancy? Or is that simple the magic of alchemy? 😉
    12 replies 35 retweets 219 likes
    Show this thread
    Show this thread
    Undo
  10. Mar 23

    CPR😀

    Replying to @Rajaontheedge
    OMG Tick Tock is back, IDF is back, new fabs, foundry model......this session was like CPR for my inner nerd. As said is Back !
    1 reply 2 retweets 42 likes
    Undo
  11. Mar 23

    Like this?

    6 replies 16 retweets 192 likes
    Undo
  12. Mar 23

    Peta-flops in your palm. An ambitious dream. silicon engineers along with our packaging alchemists made it come true in just 2 years! 's infectious energy for technology is a great accelerant for our march onwards to bring this magic to a cloud near you

    16 replies 80 retweets 366 likes
    Undo
  13. Mar 23

    I..D..F is back 💪👍😀 Intel ON

    15 replies 40 retweets 386 likes
    Undo
  14. Mar 23

    Pat unleashed!

    . shows off Ponte Vecchio using new package technologies.
    Show this thread
    4 replies 12 retweets 163 likes
    Undo
  15. Retweeted
    Mar 18

    Create high-fidelity game graphics with Intel Rendering Toolkit. Identify bottlenecks, improve frame rates & tune performance for smoother gameplay with and Intel Profiler. See these technologies in action:

    8 retweets 25 likes
    Undo
  16. Mar 17

    Real world, real workloads, real users - kudos to and Xe software teams lead by and . Built from scratch in 2 years! There's a particular joy in shipping solutions

    More streams. More subscribers. The Intel® Server GPU is helping our customers like deliver high-density, low-latency services.
    3 replies 7 retweets 97 likes
    Undo
  17. Retweeted
    Mar 17

    Exciting things are happening on 3.23.21! Please join me for a business update and webcast address on the new era of innovation and leadership .

    51 replies 207 retweets 715 likes
    Undo
  18. Retweeted
    Mar 16

    Hear how is embracing the Intel Rendering Toolkit to create highest-fidelity utilizing current, scalable infrastructure, integrated with . Register now:

    1 reply 2 retweets 14 likes
    Undo
  19. Mar 15

    What and why matter way more than where and when

    Replying to @okarthik42
    It's what you learn, not where you learn it!
    3 replies 2 retweets 57 likes
    Undo
  20. Mar 11

    From 2012 to 2021 - same Intel Folsom lab, many of the same engineers with more grey hair , I was at Apple back then, getting hands on with pre-production crystalwell, 9 years later playing with a GPU that’s >20x faster!

    29 replies 53 retweets 607 likes
    Undo

@Rajaontheedge hasn't Tweeted yet.

Loading seems to be taking a while.

Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.

    You may also like

    ·