Having read or at least skimmed most of those books, I think the best intro is 'CUDA Programming: A Developer's Guide to Parallel Computing with GPUs'
Massively Parallel Processors: A Hands-on Approach is not really good in my opinion, many small mistakes and confusing sentences (even when you know cuda).
CUDA by Example: An Introduction to General-Purpose GPU Programming is too simple and abstract too much the architecture.
Next year I'm planning to start writing a cuda book that starts by engineering the hardware, and goes up to the optimization part on that harware (which is basically a nvidia card) including all the main algorithms (except for graphs).
I'm already teaching the course in this way at uni, and it is quite successful among students.
I really wish there were better options to PMPP... It's by far the most up-to-date book, but I totally agree the writing is sort of bad and some of the code examples are straight up incorrect.
So tl;dr, you have at least one person who would pay for a better book :-)
Not really, Hardware didn't really change that much, of course you'll not find Tensor or raytracing cores, but you will have a very solid grasp of gpu programming and the cuda language (that didn't change that much either), and then you can easily learn those more modern things with blog posts or even, at worst, chatgpt.
Regarding the section on Python and high-level CUDA, anyone interested should maybe first take a peek at Warp, which I’m guessing is too new to have a book yet. Warp lets you write CUDA kernels directly in Python, and it’s a breeze to get started. https://github.com/nvidia/warp
Probably worth noting that writing performant kernels for modern Nvidia hardware looks almost nothing like what the books from 2012 are going to teach you. You can read them for fun if you'd like but they're basically irrelevant.
Increasingly (for instance ADSP podcast [1]) those in nvidia's inner circle are advocating against writing your own CUDA kernels. (Unless that's your full time job at nvidia, that is).
That would be cool but nvidia released blackwell and still have not released unbroken kernels for sm120. Sm120 is not the data center gpu, so it doesn't get its love. So we can't depend on nvidia to do the right thing is my point unfortunately
That advice seems like nonsense. It's like saying avoid C because you can use Python, or avoid writing a graphics engine because you can license Unreal.
It’s not about whether you work at Nvidia. Avoid writing CUDA kernels if there are higher level libraries that do what you need. Do write CUDA kernels if you want to learn how, or if you need the low level control, or to micro-optimize. Being able to fuse kernels to avoid memory traffic or get better specialization is also a reason to reach for raw CUDA. Just consider what’s the right tool for the job…
can very much agree about not writing stuff like reductions yourself, unless you have good reason to.
but this sort of feels like another "implement everything with <nvidia stuff> and you'll have a great time!! (but also coincidentally get locked in even more to Nvidia hardware)"
I started learning about GPU and CUDA from this book recently, and I agree the writing is confusing, and code examples have errors. However, it is still a nice reference about many types of algorithms for heterogeneous memory devices, it helped me understand better some patterns for CPUs.
In an age when your company mandates you to raise your productivity right now with hundreds of percentage points using LLMs, how do you find an excuse to sit down and read a book?