Ensure Vector.Sum uses SSE3, rather than SSSE3, for floating-point (#54123)
authorTanner Gooding <tagoo@outlook.com>
Mon, 14 Jun 2021 19:53:57 +0000 (12:53 -0700)
committerGitHub <noreply@github.com>
Mon, 14 Jun 2021 19:53:57 +0000 (12:53 -0700)
commitd95bfea59ed7d19e9b1db096c9d332005989296b
treecd05d1cde6cc1ef0e1c042a07547a6f4f5f59f0b
parentc5708e8cb74fb93a4504f2e455f449990214f4e5
Ensure Vector.Sum uses SSE3, rather than SSSE3, for floating-point (#54123)

* Adding a JIT/SIMD test validating Vector.Sum

* Ensure Vector.Sum uses SSE3, rather than SSSE3, for floating-point

* Ensure we do ISA checks before popping values from the stack

* Applying formatting patch
src/coreclr/jit/simdashwintrinsic.cpp
src/tests/JIT/SIMD/VectorSum.cs [new file with mode: 0644]
src/tests/JIT/SIMD/VectorSum_r.csproj [new file with mode: 0644]
src/tests/JIT/SIMD/VectorSum_ro.csproj [new file with mode: 0644]