I just realized part of the confusion here may be where the savings come from. When forward shading the savings comes in the final pixel shading....
I don't know the specifics of the Gears screenspace GI, but it really depends on the algorithm using the G-buffer. If you need the full...
Worded another way... what I understood DegustatoR to be saying, and I agree with, is you rasterize the G-buffer using VRS. Then it doesn't...
This isn't true. VRS can be applied dynamically. If the developer chooses to only apply it below a target frame rate they can do that.
You can't just enable Mesh Shaders, provide it with the same content, and expect improved performance. For static content that can have vertex...
The GE prefix came about because some things were moved around and it was decided to group multiple blocks under the Geometry Engine register...
Also, the hardware VS (Primitive Shader in newer hardware) is what feeds the rasterizer. So it goes last, providing consistency in naming from a...
Nvidia does have a higher culling rate than rasterization so there must be something about the workload that drops the 3090 from its peak rate.
VRS replicates the color values to the pixels.
The answer I gave you is crystal clear and not a guess.
Navi21 has 4.
Well, there was this rumor today. I see ME3 multiplayer won't be included in the remaster. This would keep me from buying it but I don't think I...
I've never heard engineering decisions be driven by fear of patents. Architects shouldn't be reading patents in the first place so they don't...
It depends on what you consider to be the IA. I was referring to hardware that reads the index buffer, forms primitives, and performs vertex...
Primitive shaders have a hardware assisted mode that uses the input assembler and a fast launch mode that looks like compute. Mesh Shaders use the...
Everything doesn't shrink the same with each new process node so that could have something to do with it. For example, wires don't shrink the same...
That version of RGP isn't showing PrimS. Maybe it was dropped to only show the API shaders.
What do you mean? Ray tracing uses compute.
My understanding is transparency is accomplished using the graphics pipeline rather than compute. I haven't seen any speculation about objects in...
That's an interesting patent, but I wasn't referencing it. Coarse rasterization before fine rasterization is not a new concept. For example, you...
I've provided answers to your questions already. Maybe I was too vague before. It's not unbalanced to have a primitive rasterizer perform coarse...
32-bit color should be fast on any architecture so that sounds good.
Yes, that's consistent with what I wrote. It means the back end (pixel output) of the scan converters total 128 pixels. The diagram is correct,...
4 triangles per clock at up to 128 pixels/clock. A triangle can touch a single pixel or up to 32 and theoretically maintain peak geometry rate....
There are 4 scan converters as per the diagram. The driver settings don't mean what you think they mean or they are incorrect.
I suspect there's some subtlety with those defines. The front end of the scan converter matters for triangle throughput, but in order to scale...
Digidi, don't look at Navi10. There are some inconsistencies in performance there that will only confuse things. The quoted rates for Navi21 are...
I hadn't realized an entire SE was harvested for the 6800. That would reduce the triangle rasterization rate, but Navi21 has enough pre-cull...
Navi21 can rasterize 4 primitives/clock as can XSX and PS5. Navi21 will be better at tessellation and some other circumstances though, such as...
I loved the entire trilogy and unexpectedly had a ton of fun with ME3 multiplayer. There was a lot of variety with the playable characters. Though...
APIs don't specify vertex shaders must be run a specific number of times. This allows each IHV to implement their own vertex reuse algorithms....
Nanite is not REYES nor is Lumen ray tracing based on everything I've read. Nanite is rendering small triangles, but that's where the similarity...
I don't know what that means. I suppose it's someone's username so no.
There's no way DRAM latency is lower than a cache hit since you need to check the cache before going to DRAM.
I'm not an expert in this area, but my understanding is developer input is necessary to get rid of quads and perform well. It's been a discussion...
I can't explain what you saw in the shader. RDNA can have multiple draw instances in the same VS wave. This was sometimes true for previous...
It seems this thread has gone off topic so I'll continue the trend. :) On AMD hardware multiple primitives can contribute to a PS wave. Up to...
I interpreted the quote to say they can call two primitives per clock meaning they likely rasterize one that survives culling.
They do share the instruction cache just not the vector L0. Yes
I'm far from an expert, but have been reading about this some recently thanks to links posted here. Apparently you get less aliasing with texture...
Sampler feedback can improve the performance of texture space shading but it's not required for texture space shading. It can be used to reduce...
Each CU has 2 SIMD32, so 64 SPs, 2 SFU, 2 scalar ALU, 2 instruction dispatch units
AMD has an ES stage when GS is used.
Based on the prior tweets I think GS meant Geometry Shader though when used while discussing PS2 I can see your interpretation.
Did the vector unit operate on work groups and have local memory?
When you let the hardware cull rather than compute all parts are faster. That says you can't conclude anything about primitive shader culling...
Yes, every AMD architecture has been able to vary these numbers. That's why the 5700 works, not just the 5700 XT.
What was the curious data for Vega64? It performs pretty close to 4 prims/clk.
There are sync points like maintaining raster order so if one SE runs ahead it won't get to far. IPC means better performance per clock given the...
It's not BS. Workstation sales pay for driver optimizations for professional apps. These optimizations are the main thing you're paying for in...