mirror of
https://github.com/amd/blis.git
synced 2026-05-11 09:39:59 +00:00
873b4f93fd
Add test in top-level GEMM BLAS layer for alpha = zero. Scale C appropriately if true and return. This ensures that A and B are not referenced, and thus that any Inf or NaN values in A or B are not propagated to C. This was tested in some lower level code paths, but not consistently. Solution throughout GEMM codebase assumes scalm handles scale value (beta from GEMM) equal to 0 without propagating inf/NaNs in C matrix. Also call AOCL_DTL exits and bli_finalize_auto() in a more consistent way. AMD-Internal: [CPUPL-3053] Change-Id: I4009f311951eb1ce9416cf846e9fa93b7c9219cc