mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-22 04:22:57 +02:00
db2b7a7592
Before this patch, the backend sub-optimally expanded the non-constant shift
count of a v8i16 shift into a sequence of two 'movd' plus 'movzwl'.
With this patch the backend checks if the target features sse4.1. If so, then
it lets the shuffle legalizer deal with the expansion of the shift amount.
Example:
;;
define <8 x i16> @test(<8 x i16> %A, <8 x i16> %B) {
%shamt = shufflevector <8 x i16> %B, <8 x i16> undef, <8 x i32> zeroinitializer
%shl = shl <8 x i16> %A, %shamt
ret <8 x i16> %shl
}
;;
Before (with -mattr=+avx):
vmovd %xmm1, %eax
movzwl %ax, %eax
vmovd %eax, %xmm1
vpsllw %xmm1, %xmm0, %xmm0
retq
Now:
vpxor %xmm2, %xmm2, %xmm2
vpblendw $1, %xmm1, %xmm2, %xmm1
vpsllw %xmm1, %xmm0, %xmm0
retq
llvm-svn: 223660
|
||
|---|---|---|
| .. | ||
| Analysis | ||
| Assembler | ||
| Bindings | ||
| Bitcode | ||
| BugPoint | ||
| CodeGen | ||
| DebugInfo | ||
| ExecutionEngine | ||
| Feature | ||
| FileCheck | ||
| Instrumentation | ||
| Integer | ||
| JitListener | ||
| Linker | ||
| LTO | ||
| MC | ||
| Object | ||
| Other | ||
| SymbolRewriter | ||
| TableGen | ||
| tools | ||
| Transforms | ||
| Unit | ||
| Verifier | ||
| YAMLParser | ||
| .clang-format | ||
| CMakeLists.txt | ||
| lit.cfg | ||
| lit.site.cfg.in | ||
| Makefile | ||
| Makefile.tests | ||
| TestRunner.sh | ||