llvm-project

783b050f - [LMI] Support non-power-of-2 types for the matmul remainder (#163987)

[LMI] Support non-power-of-2 types for the matmul remainder (#163987) In the inner loop of matmul, instead of continuously halving the HW vector register width, I just use the remainder vector directly if it's legal. We don't have in-tree targets that have this so I opted for adding a hidden flag to simulate this for testing purposes: -matrix-split-matmul-remainder-over-threshold The tests are the vectorization-friendly 3x3x1 matrix-vector and 1x3x3 vector-matrix multiplies for CM, RM respectively.