mirror of
https://github.com/RPCS3/llvm.git
synced 2025-02-11 05:17:36 +00:00
![Mark Heffernan](/assets/img/avatar_default.png)
For NVPTX, try to use 32-bit division instead of 64-bit division when the dividend and divisor fit in 32 bits. This speeds up some internal benchmarks significantly. The underlying reason is that many index computations are carried out in 64-bits but never actually exceed the capacity of a 32-bit word. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@244684 91177308-0d34-0410-b5e6-96231b3b80d8