search for: conv13

Hello. My target architecture supports natively 16 bit integers (i16). Whenever I write in C programs using only short types, clang compiles the program to LLVM and converts the i16 data to i32 to perform arithmetic operations and then truncates the results to i16. Then, the InstructionCombining (INSTCOMBINE or IC) pass removes these conversions back and forth from i16, except for

....i, 13 br i1 %exitcond.i, label %eshdn1.exit, label %for.body.i eshdn1.exit: ; preds = %if.end12.i %arrayidx6 = getelementptr inbounds i16* %den, i32 3 %3 = load i16* %arrayidx6, align 2, !tbaa !5 %arrayidx11 = getelementptr inbounds i16* %num, i32 3 %conv13 = zext i16 %3 to i32 %mul = mul i32 %conv13, 65535 %arraydecay18 = getelementptr inbounds [14 x i16]* %tprod, i32 0, i32 0 %4 = bitcast [13 x i16]* %p.i to i8* %arrayidx.i = getelementptr inbounds [13 x i16]* %p.i, i32 0, i32 11 %incdec.ptr.i103 = getelementptr inbounds [13 x i16]* %p.i,...