"Software rendering went out of the window because the CPU tends to have other things to do besides just multiply 4x4 matrices, which was shifted to the shader cores of GPUs."

Hardware rendering took over because generating a 3D scene is embarrassingly parallel, and the industry quickly learned that you can have thousands of reasonably simple "cores" that can divide and conquer a scene in parallel. There was a no way a general purpose CPU could keep up.

▲

pandaman 3 hours ago | parent [-]

Not so quickly. The shader cores were a breakthrough from early 2000s. First consumer GPUs were built as same as the 1980s GPUs but everything had been integrated in a single chip.

It is the sheer amount of compute and memory bandwidth that mogs a CPU but the parallel processing doesn't help much, at least in realistic 3D: an 8 core AVX-512 march CPU has an order of magnitude more SIMD lanes than something like RSX in PS3 yet it still wouldn't be able to match its performance in rendering textured z-buffered triangles. 3D graphics can really go wide only on wireframe/points, z-buffer forces sequencing between polys so the parallelism there is very limited.

▲

llm_nerd 3 hours ago | parent [-]

Parallel processing was fully in force in the very first GPUs, like the Voodoo. Not like a modern GPU with thousands of more flexible shader cores, but the first iteration had a pipeline architecture that saw multiple blocks operating on rendering separate parts of the pipeline in parallel. This was revolutionary. Especially given that CPUs at the time had a single core.

I'm not sure what the PS3 comparison is for, or why we're comparing a 2026 AVX-512 CPU with a 2006 gaming console. Okay? A modern GPU can obliterate any CPU in SIMD, presuming you conform with the types it wants. Add that it's weird to bring up as AVX and other SIMD techniques are basically the same sort of architecture, parallelizing a problem.

> 3D graphics can really go wide only on wireframe/points, z-buffer forces sequencing between polys so the parallelism there is very limited.

Rendering a 3D is scene is the very definition of embarrassingly parallel. While optimizers can cull the scene, you know that the entire depth within the frustum (there are a variety of optimizing techniques to minimize the overdraw, but it's a part of rendering a scene) is "rendered" and in amalgamation the Z-buffer values are compared and discarded, blended, or whatever? It is an extraordinarily parallel operation.

▲

pandaman 2 hours ago | parent [-]

> the very first GPUs, like the Voodoo

Voodoo Graphics came out in 1995, we had commercial GPUs since early 1980s. Also it's funny that you believe it was "full force" parallel because specifically Voodoo (SST-1) drew a single pixel per clock (and had no geometry processing) so it was not parallel at all, even inside a poly. This statement shows your level of expertise though.

	▲	llm_nerd 2 hours ago \| parent [-]
		How bizarrely hostile. So weird. > Voodoo Graphics came out in 1995, we had commercial GPUs since early 1980s. I mean, if you think you're going to get me in a gotcha, you should know that the first thing we considered a "GPU" came out three years after the Voodoo. The GeForce 256. But since we're talking about gaming, the first real 3D accelerator in that market was the 3dfx Voodoo, and it revolutionized gaming because even though we had graphics cards, their abilities were laughably limited (blitting was a big feature). > so it was not parallel at all You, uh, really should look this up. Are you consulting an LLM or something, because it's like someone who has no idea what they're talking about just randomly saying stuff. PS3! AVX-512! "drew a single pixel" is a funny comment that kind of gives away the game. Do you have any idea what is involved in drawing "a single pixel"? This is rhetorical, because you seem to have no idea at all. I'm just going to ignore you, but Christ you know you don't have to double down on this stuff.