Rasterization could be simulated in software with some driver trickery, but apparently it has less fp32 performance than the 5090 so it would be significantly slower
Still, a RISC-V based GPU is very weird, normally I hear RISC-V being slower and less power efficient than even a CPU.
I expect it to be bottlenecked by complex brdfs and shaders in actual path tracing workloads, but I guess we’ll see what happens.
In theory it should be able to be more power efficient. In practice, less development has been put into RISC-V CPU designs so they are still less power efficient than Arm (and maybe x86 even)
Rasterization could be simulated in software with some driver trickery, but apparently it has less fp32 performance than the 5090 so it would be significantly slower
Still, a RISC-V based GPU is very weird, normally I hear RISC-V being slower and less power efficient than even a CPU.
I expect it to be bottlenecked by complex brdfs and shaders in actual path tracing workloads, but I guess we’ll see what happens.
Isn’t the whole point of RISC that its more power efficient?
In theory it should be able to be more power efficient. In practice, less development has been put into RISC-V CPU designs so they are still less power efficient than Arm (and maybe x86 even)
Arm are RISC processors, I’m lead to believe x86-64 might even be something similar under the microcode.
Yea I edited to say RISC-V specifically, thx