[flagged]
What every developer should know about GPU computing
71–80 of 186 posts
Re: What every developer should know about GPU computing
#72Earlier quoted context omitted.
Vector Processing Unit would be more appropriate.
Why stop there? Matrix Processing Unit or Tensor Processing Unit if you want to trigger the physicists or are a fan of the google cloud.
Those things actually exists and are called NPU (Neural Processing Unit). Many recent ARM CPU have them (Apple, Qualcomm, etc.) and even new RISC-V CPU. They're different from GPU in being even more constrained in programming requiring usage of a fixed function vendor-supplied library.
Re: What every developer should know about GPU computing
#73Never really needed to know this stuff because compiler does all the translation, but low level programming like training AI would be useful. Is that a correct assumption?
Re: What every developer should know about GPU computing
#74TL;DR most developers don't need to know any of this.
Re: What every developer should know about GPU computing
#75>> Most programmers have an intimate understanding of CPUs
I'd say the mental model for most programmers is: lines of text, in their language of choice, zipping by really fast.
Re: What every developer should know about GPU computing
#76> Most programmers have an intimate understanding of CPUs and sequential programming because they grow up writing code for the CPU Maybe it’s just where I work, but I feel like even this isn’t true. A lot of the newer/young employees don’t even seem to have a lot of OS/system understanding. A lot of the higher-level languages abstract the immediate need of having any “intimate understanding” of CPUs.
> A lot of the newer/young employees don’t even seem to have a lot of OS/system understanding.
This is largely irrelevant to the concept of sequential programming.
Re: What every developer should know about GPU computing
#77>Most programmers have an intimate understanding of CPUs maybe this article is brilliant, but when the first line is something so blatantly untrue it really makes it hard to take the rest seriously
And this is the most insightful thing you had to say about this?! Pfft.
Re: What every developer should know about GPU computing
#78>> Most programmers have an intimate understanding of CPUs I'd say the mental model for most programmers is: lines of text, in their language of choice, zipping by really fast.
Like an interpreted language I suppose
Re: What every developer should know about GPU computing
#79>Most programmers have an intimate understanding of CPUs maybe this article is brilliant, but when the first line is something so blatantly untrue it really makes it hard to take the rest seriously
Definitely not true about most programmers, but maybe the author meant CS educated engineers. Going through a formal CS program will give you an intimate understanding of CPUs, especially when compared to the very light coverage of GPUs.
Are most programmers self trained now? I can see if someone self trains for fe or even full stack with an eye on compensation, they wouldn't understand program counters and the like. But so many people seem motivated by video games to get into the industry that I'd expect them to be reading about things like the fast inverse square root or similar.
Re: What every developer should know about GPU computing
#80Let's assume I have an array of 10.000 lat/lng-pairs. I want to compute the length of the track. I duplicate the array and remove the first item in the duplicated array, append the last entry of the original array to the duplicate in order for them to be equal in length.
Then I use a vectorized haversine algorithm on these arrays to obtain a third one with the distances between each "row" of the two arrays.
With NumPy this is fast, but I guess that a GPU could also perform this and likely do it much faster. Would it be worth it if one has to consider that the data needs to be moved to the GPU and the result be retrieved?