Go to file
Simon Pilgrim 1d181bc992 [X86][AVX] Use extract_subvector to reduce vector op widths (PR36761)
We have a number of cases where we fail to reduce vector op widths, performing the op in a larger vector and then extracting a subvector. This is often because by default it would create illegal types.

This peephole patch attempts to handle a few common cases detailed in PR36761, which typically involved extension+conversion to vX2f64 types.

Differential Revision: https://reviews.llvm.org/D49556

llvm-svn: 337500
2018-07-19 21:52:06 +00:00
clang [CStringSyntaxChecker] Check strlcpy sizeof syntax 2018-07-19 21:50:03 +00:00
clang-tools-extra [clangd] Also get scope for RK_pattern completion results. 2018-07-18 15:31:14 +00:00
compiler-rt [profile] Fix typo in test 2018-07-19 20:18:37 +00:00
debuginfo-tests Revert "[CMake] Sort dependency list and add safestack to it" 2018-07-18 20:10:43 +00:00
libclc atom: Use volatile pointers for cl_khr_{global,local}_int32_{base,extended}_atomics 2018-06-21 19:27:39 +00:00
libcxx [libc++] Allow running ABI list tests with different ABI versions 2018-07-19 18:02:50 +00:00
libcxxabi [CMake] Set per-runtime library directory suffix in runtimes build 2018-07-10 19:13:33 +00:00
libunwind The semantics of DW_CFA_GNU_args_size have changed subtile over the 2018-07-17 19:00:51 +00:00
lld [ELF][HEXAGON] Add support for R_HEX_B15_PCREL 2018-07-19 20:27:43 +00:00
lldb Added unit tests for Flags 2018-07-19 17:45:51 +00:00
llgo Update copyright year to 2018. 2018-06-18 12:22:17 +00:00
llvm [X86][AVX] Use extract_subvector to reduce vector op widths (PR36761) 2018-07-19 21:52:06 +00:00
openmp Block library shutdown until unreaped threads finish spin-waiting 2018-07-19 19:17:00 +00:00
parallel-libs Update copyright year to 2018. 2018-06-18 12:22:17 +00:00
polly [DependenceInfo] Use isl++ to replace foreach_set with for loop 2018-07-17 07:08:06 +00:00
README.md

README.md

Low Level Virtual Machine (LLVM)

This directory and its subdirectories contain source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and runtime environments.