[PATCH] D39575: [X86] Add subtarget features prefer-avx256 and prefer-avx128 and use them to limit vector width presented by TTI

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

Should we be looking at this from a cost model POV? Possibly introducing the concept of a cost for "first use" of a vector type (in this case for 512-bit vectors),  increasing the cost of 512-bit ops and making the cost models more 'state aware' (use of a 512-bit vector causes a cost multiplier effect on ALL vector ops).

Having said that the vectorizers don't seem to do a good job of comparing costs of different vector widths - AVX1 (Jaguar/Bulldozer/SandyBridge etc.) often end up with 256-bit integer vector code despite the fact that the costs already flag the x4 cost compared to 128-bit integer equivalents (and cause nasty register spill issues).


https://reviews.llvm.org/D39575