![]() In r369429, I hoisted a floating point computation to a variable in order to remove a warning. However, it turns out this doesn't play well with floating point arithmetic. This commit reverts r369429 and instead casts the result of the floating point computation to remove the warning. Whether hoisting the computaiton to a variable should give the same result can be investigated independently. llvm-svn: 369693 |
||
---|---|---|
.. | ||
rand.util.canonical | ||
rand.util.seedseq | ||
nothing_to_do.pass.cpp |