Live data from Hacker News

Viewing profile — shihab

shihab

HN member
Joined
Wed, Sep 19, 2018, 5:52 AM UTC
HN karma
1,715
Public activity
281 items

About shihab

PhD student, Computer Science & Engineering

Recent public activity

  1. comment
    Comment #49048704

    US burnt almost entire latin american down last century because "can't have communism in our backyard", even though these countries are quite far geographically than Bahrain is to …

  2. comment
    Comment #47197913

    I brought up Israeli-American donors because that’s what is relevant in the context of the story we’re discussing. We are talking about a war many right wing Israelis wanted for de…

  3. comment
    Comment #47193411

    Exactly what part of my statement was dog whistling? Can you stop throwing around this serious accusation of antisemitism without any attempt to substantiate your claim?

  4. comment
    Comment #47192462

    Citizens United is an existential threat for USA. You cannot have Israeli-American dual citizens pouring $200 million dollars in elections. and that’s just her alone. This is simpl…

  5. comment
    Comment #47192332

    Another mid east war entirely on Israel’s behalf, another war Americans will pay tax for, die for- just so Israel can keep grabbing few parcels of lands from Palestine.

  6. comment
    Comment #46915327

    I think there are two steps here: converting video to sensor data input, and using that sensor data to drive. Only the second step will be handled by cars on road, first one is pur…

  7. comment
    Comment #46901995

    The article strictly talks about people who were pals with him _after_ his Pedophilia conviction. And please don't do this strawman "evil person eating babies", nobody sane is clai…

  8. comment
    Comment #46791687

    I work with GPUs and I'm also trying to understand the motivations here. Side note & a hot take: that sort of abstraction never really existed for GPU and it's going to be even har…

  9. comment
    Comment #46791591

    To the author (or anyone from vectorware team), can you please give me, admittedly a skeptic, a motivating example of a "GPU-native" application? That is, where does it truly make …

  10. comment
    Comment #46713179

    > For example, NEON ... can hold up to 32 128-bit vectors to perform your operations without having to touch the "slow" memory. Something I recently learnt: the actual number of ph…

  11. comment
    Comment #46706520

    I'm not asking an academic program first published 8 year ago (e3nn) to beat actively developed CuEquivariance library. An academic proposing new algorithms doesn't need to worry t…

  12. comment
    Comment #46706133

    I should note PETSc is a big piece of software that does a lot of things. It also wraps many libraries, and those might ultimately dictate actual performance depending on what you …

  13. comment
    Comment #46705935

    To be practically useful, we don't need to beat vendors, just getting close would be enough, by the virtue of being open-source (and often portable). But I found, as an example, PE…

  14. comment
    Comment #46705109

    Hi, I just wanted to note that e3nn is more of an academic software that's a bit high-level by design. A better baseline for comparison would be Nvidia's cuEquivariance, which does…

  15. comment
    Comment #46682013

    Hi, I actually mentioned ISPC several times there. And although I strenuously avoided crowning one approach "better" over the other, it is worth pointing out that 1) Many of these …

  16. comment
    Comment #46681706

    No. Assuming `k` is small enough, which in practice often is, the arithmetic intensity of this kernel is 25-90 Flops/Byte, way above the roofline knee of any modern CPU.

  17. comment
    Comment #46681674

    Hi, thanks for reading. Re (b) I'm curious what that middle ground is. Is there any simple refactor to help GCC to get rid of this `if`? (Note, ISPC did fine here) (c) Just to be c…

  18. comment
    Comment #46615095

    Yeah N is big enough that entire data isn't in the cache, but the memory access pattern here is the next best thing: totally linear, predictable access. I remember seeing around 94…

  19. story
  20. comment
    Comment #46593391

    For SIMD at least, the {mins[3], maxs[3]} representation aligns more naturally with actual instructions on x86. To compute a new bounding box: new_box.mins = _mm_min_ps(a.mins[3], …

  21. comment
    Comment #46548826

    If you are from ML/Data science world, the analogy that finally unlocked FFT for me is feature size reduction using Principal Component Analysis. In both cases, you project data to…

  22. comment
    Comment #46517721

    I'd love to see a breakdown of what exactly worked here, or better yet, PR to upstream Abseil that implements those ideas. AI is always good at going from 0 to 80%, it's the last 2…

  23. comment
    Comment #46509891

    I was surprised by that defiant tone there in an official page. But it's missing actual numbers, which makes it all pretty strange.

  24. comment
    Comment #45792255

    I'm curious what you did with the "active sorting range" after a push/pop event. Since it's a vector underneath, I don't see any option other than to sort the entire range after ea…

  25. comment
    Comment #45564912

    > To Koreans, they looked more like sauce bowls, leading them to conclude that the Japanese had starved themselves to stretch out the siege. As a Bengali man, that's exactly how I …