mirror of
https://github.com/RPCS3/llvm.git
synced 2025-04-12 19:18:48 +00:00

Skipping 'bitcast' in this case allows to vectorize load: %arrayidx = getelementptr inbounds double*, double** %in, i64 %indvars.iv %tmp53 = bitcast double** %arrayidx to i64* %tmp54 = load i64, i64* %tmp53, align 8 Differential Revision http://reviews.llvm.org/D14112 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@251907 91177308-0d34-0410-b5e6-96231b3b80d8