![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
Intrinsics and compiler smarts
Jul. 29th, 2019 10:17 amRecently I was wondering why relatively simple and short SIMD/SSE intrinsics code is ~1.5 slower when compiled by ICC, than when compiled with CLANG.
When one uses intrinsics, it is supposed to be almost assembly, compiler should only do [optimal] register allocations and deal with input and output variables. However, compilers now do much more than that, especially the optimizations they perform on top of intrinsics are often very non-obvious.
In case of the code I examined, ICC produced ~20% faster code for a scalar part, and ~10% faster code for one vector basic block, but ~2x slower for another vector basic block. When combined, these resulted in ~1.5x difference.
It is not the first time I noticed the compiler optimizations significantly alter SIMD intrinsics flow, but before it was always something small, like fusing 2 instructions when a SIMD equivalent exists, etc. In this case it just produced 2x+ instructions! Alas, just changing to -O0 won't make it back to the planned flow, as O0 adds too many intermediates... So if I am certain that my instruction flow is better than compilers, I'll have to do inline asm rather than intrinsics.
When one uses intrinsics, it is supposed to be almost assembly, compiler should only do [optimal] register allocations and deal with input and output variables. However, compilers now do much more than that, especially the optimizations they perform on top of intrinsics are often very non-obvious.
In case of the code I examined, ICC produced ~20% faster code for a scalar part, and ~10% faster code for one vector basic block, but ~2x slower for another vector basic block. When combined, these resulted in ~1.5x difference.
It is not the first time I noticed the compiler optimizations significantly alter SIMD intrinsics flow, but before it was always something small, like fusing 2 instructions when a SIMD equivalent exists, etc. In this case it just produced 2x+ instructions! Alas, just changing to -O0 won't make it back to the planned flow, as O0 adds too many intermediates... So if I am certain that my instruction flow is better than compilers, I'll have to do inline asm rather than intrinsics.
