forked from OSchip/llvm-project
8c81678dfa
Demonstrates some shortfalls in subvector(cvt(x)) compared to cvt(subvector(x)) patterns - especially on AVX/AVX2 targets. llvm-svn: 242614 |
||
---|---|---|
clang | ||
clang-tools-extra | ||
compiler-rt | ||
debuginfo-tests | ||
libclc | ||
libcxx | ||
libcxxabi | ||
libunwind | ||
lld | ||
lldb | ||
llgo | ||
llvm | ||
openmp | ||
polly |