Matt Arsenault f303d037f2 R600: Fix LowerSDIV24
Use ComputeNumSignBits instead of checking for i8 / i16 which only
worked when AMDIL was lying about having legal i8 / i16.

If an integer is known to fit in 24-bits, we can
do division faster with float ops.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213843 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-24 06:59:20 +00:00
..
2014-06-23 18:00:26 +00:00
2014-06-23 18:00:31 +00:00
2014-07-24 06:59:20 +00:00
2014-06-23 18:00:31 +00:00
2014-07-20 06:31:06 +00:00
2014-07-20 06:31:06 +00:00
2014-07-17 17:50:22 +00:00
2014-07-21 17:52:00 +00:00