Add bilinear interpolation benchmark (#566)
authorCarol Eidt <carol.eidt@microsoft.com>
Thu, 5 Dec 2019 20:10:12 +0000 (12:10 -0800)
committerGitHub <noreply@github.com>
Thu, 5 Dec 2019 20:10:12 +0000 (12:10 -0800)
commit249d6d8c96e45ec2c8e9a1bc8cd07e4c1f88373b
tree951fae747886ef9b08fb1f60129cb99548ac9f32
parentf2390f0ff562caaeaf1582e2d591a9893881fdc8
Add bilinear interpolation benchmark (#566)

This is also checked in to the performance repo. Adding it here makes it easier to include in diffs and other code analysis. Also, it exposed a correctness bug in the Arm64 `Vector<T>` implementation; the convert from floating point to integer needs to truncate.
src/coreclr/src/jit/codegenarm64.cpp
src/coreclr/tests/src/JIT/Performance/CodeQuality/BilinearInterpol/BilinearInterpol.cs [new file with mode: 0644]
src/coreclr/tests/src/JIT/Performance/CodeQuality/BilinearInterpol/BilinearInterpol.csproj [new file with mode: 0644]