Hi,
Given a function like x < 0 ? 0 : x
We can lower it to bic x, x, asr 31 because we can test if CC==LT && RHS==TrueVal==0 && LHS==FalseVal
Further, give a function x > 255 ? 255 : (x < 0 ? 0 :x), we should lower it to: usat x, #8
However, things become more complicated if we have
((x < 0 ? 0 :x) << n ) & mask …
Because it will first be converted to
x < 0 ? 0 : ((x << n) & mask)
Now, it’s hard to match the pattern. (Doable but nasty)
Any suggestions?
Thanks in advance.
Weiming
Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation