SIMD < SIMT < SMT: Parallelism in Nvidia GPUs (2011)

> How many register sets does a typical SMT processor have? Er, 2, sometimes 4

Way more of them. Pipelines are deep, and different in-flight instructions need different versions of the same registers.

For example, my laptop has AMD Zen3 processor. Each core has 192 scalar physical registers, while only ~16 general-purpose scalar registers defined in the ISA. This gives 12 register sets; they are shared by both threads running on the core.

Similar with SIMD vector registers. Apparently each core has 160 32-byte vector registers. Because AVX2 ISA defines 16 vector register, this gives 10 register sets per core, again shared by 2 threads.

I believe the author is referring to how many logical threads/hyperthreads can a core run (for AMD and Intel, two. I believe POWER can do 8, Sparc 4).

The extra physical registers are there for superscalar execution, not for SMT/hyperthreading.

I meant register sets visible to software. The fact that there's even more hardware not visible to software that you need for a thread to run fast just means that the cost of adding another thread is even higher

Depends on whether that hardware is shared between threads or not. Physical registers are usually shared.