Discussion

Search code, repositories, users, issues, pull requests...

bob1029: A fun experiment but I wonder how many out there seriously think we could ever completely rid ourselves of the CPU. It seems to be a rising sentiment.The cost of communicating information through space is dealt with in fundamentally different ways here. On the CPU it is addressed directly. The actual latency is minimized as much as possible, usually by predicting the future in various ways and keeping the spatial extent of each device (core complex) as small as possible. The GPU hides latency with massive parallelism. That's why we can put them across relatively slow networks and still see excellent performance.Latency hiding cannot deal well in workloads that are branchy and serialized because you can only have one logical thread throughout. The CPU dominates this area because it doesn't cheat. It directly targets the objective. Making efficient, accurate control flow decisions tends to be more valuable than being able to process data in large volumes. It just happens that there are a few exceptions to this rule that are incredibly popular.

spot5010: I don't think we get rid of the CPU. But the relationship will be inverted. Instead of the CPU calling the GPU, it might be that the GPU becomes the central controller and builds programs and calls the CPU to execute tasks.

treyd: This will never without completely reimagining how process isolation works and rewriting any OS you'd want to run on that architecture.

Nevermark: Time to benchmark Doom.Now we know future genius models won't even need CPUs, just their tensor/rectifying circuits. If they need a CPU, they will just imagine one.

GeertB: I don't quite understand how multiply doesn't require addition as well to combine the various partial products.

robertcprice1: Hey everyone thank you taking a look at my project. This was purely just a “can I do it” type deal, but ultimately my goal is to make a running OS purely on GPU, or one composed of learned systems.

yjftsjthsd-h: This is hilarious and profoundly in the spirit of hacker news. Thanks for posting:)

nicman23: can i run linux on a nvidia card though?

micw: Linux runs everywhere

volemo: Except on my stupid iPad “Pro”. :(

mghackerlady: iirc theres an app on the app store that's basically a small alpine container

low_tech_punk: Saw the DOOM raycast demo at bottom of page.Can't wait for someone to build a DOOM that runs entirely on GPU!

jhuber6: Depends entirely on your definition of 'entirely', but https://github.com/jhuber6/doomgeneric is pretty much a direct compilation of the DOOM C source for GPU compute. The CPU is necessary to read keyboard input and present frame data to the screen, but all the logic runs on the GPU.

DonThomasitos: I don‘t understand why you would train a NN for an operation like sqrt that the GPU supports in silicon.

nine_k: I see it as a practical joke or a fun hack, like CPUs implemented in the Game of Life, or in Minecraft.

mihaitodor: It’s been done already. Have a look at Quest for Tetris: https://codegolf.stackexchange.com/questions/11880/build-a-w...

himata4113: I was always wondering what would happen if you trained a model to emulate a cpu in the most efficient way possible, this is definitely not what I expected, but also shows promise on how much more efficient models can become.

artemonster: Every clueless person who suggest that we move to GPUs entirely have zero idea how things work and basically are suggesting using lambos to plow fields and tractors to race in nascar

madwolf: Bad comparison. Lambos are regularly plowing fields and they're quite good at it. https://www.lamborghini-tractors.com/en-eu/

artemonster: I remembered that labos used to make tractors after I posted the comment. Nice catch!

volemo: I see us not getting rid of CPU, but CPU and GPU being eventually consolidated in one system of heterogeneous computing units.

jagged-chisel: Agreed. Much like “RISC is gonna replace everything” - it didn’t. Because the CPU makers incorporated lessons from RISC into their designs.I can see the same happening to the CPU. It will just take on the appropriate functionality to keep all the compute in the same chip.It’s gonna take awhile because Nvidia et al like their moats.

StilesCrisis: CISC only survived because CPUs now dedicate a ton of silicon to decoding the CISC stream into RISC-y microcode. RISC CPUs can avoid this completely, but it turns out backwards compatibility was important to the market and the transistor cost of "instruction decode" just adds like +1 pipeline depth or something.

ndiddy: > CISC only survived because CPUs now dedicate a ton of silicon to decoding the CISC stream into RISC-y microcode.For Intel CPUs, this was somewhat true starting from the Pentium Pro (1995). The Pentium M (2004) introduced a technique called "micro-op fusion" that would bind multiple micro-ops together so you'd get combined micro-ops for things like "add a value from memory to a register". From that point onward, the Intel micro-ops got less and less RISCy until by Sandy Bridge (2011) they pretty much stopped resembling a RISC instruction set altogether. Other x86 implementations like K7/K8/K10 and Zen never had micro-ops that resembled RISC instructions.

jdlyga: I'll do you one better, imagine a CPU that runs entirely in an LLM.You’re absolutely right! I made an arithmetic mistake there — 3 * 3 is 9, not 8. Let’s correct that: Before: EAX = 3 After imul eax, eax: EAX = 9 Thanks for catching that — the correct return value is 9.

FartyMcFarter: What an amazing multiplication request! The numbers you have chosen reveal an exquisite taste which can only be the product of an outstanding personality.

andreadev: The bit about multiplication being ~12x faster than addition is worth pausing on. In silicon, addition is the "easy" operation — but here the complexity hierarchy completely inverts. Makes sense once you think about it: multiplication decomposes into parallel byte-pair lookups (which neural nets handle trivially as table approximation), while addition has a sequential carry chain you can't fully parallelize away.Funny enough, analog computing had the same inversion — a Gilbert cell does multiplication cheaply, while addition needs more complex summing circuits. Completely different path to the same result.What I haven't seen discussed: if the whole CPU is neural nets, the execution pipeline is differentiable end-to-end. You could backprop through program execution. Useless for booting Linux, but potentially interesting for program synthesis — learning instruction sequences via gradient descent instead of search. Feels like that's the more promising research direction here than trying to make it fast.

zephen: > CPUs now dedicate a ton of silicon to decoding the CISC stream into RISC-y microcode.In absolute terms, this is true. But in relative terms, you're talking less than 1% of the die area on a modern, heavily cached, heavily speculative, heavily predictive CPU.

FartyMcFarter: Didn't there use to be a joke about Intel being the biggest RAM manufacturer (given the amount of physical space caches take on a CPU)?

zephen: I hadn't heard that, but certainly, there must have been many times when Intel held the crown of "biggest working hunk of silicon area devoted to RAM."