2 Commits

Author	SHA1	Message	Date
Stanislav Mekhanoshin	cf74ef134c	[AMDGPU] Limit promote alloca max size in functions ... Non-entry functions have 32 caller saved VGPRs available. If we promote alloca to consume more registers we will have to spill CSRs. There is no reason to eliminate scratch access to get another scratch access instead. Differential Revision: https://reviews.llvm.org/D110372	2021-09-24 13:38:39 -07:00
Stanislav Mekhanoshin	54e2dc7537	[AMDGPU] Limit promote alloca to vector with VGPR budget ... Allow only up to 1/4 of available VGPRs for the vectorization of any given alloca. Differential Revision: https://reviews.llvm.org/D82990	2020-07-01 15:57:24 -07:00