mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-21 03:53:04 +02:00
38de0c92c6
This patch improves the folding of vector AND nodes into blend operations for
targets that feature SSE4.1. A vector AND node where one of the operands is
a constant build_vector with elements that are either zero or all-ones can be
converted into a blend.
This allows for example to simplify the following code:
define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) {
%1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1>
%2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
Before this patch llc (-mcpu=corei7) generated:
andps LCPI1_0(%rip), %xmm0, %xmm0
andps LCPI1_1(%rip), %xmm1, %xmm1
orps %xmm1, %xmm0, %xmm0
retq
With this patch we generate a single 'vpblendw'.
llvm-svn: 221343
|
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| DAGCombiner.cpp | ||
| FastISel.cpp | ||
| FunctionLoweringInfo.cpp | ||
| InstrEmitter.cpp | ||
| InstrEmitter.h | ||
| LegalizeDAG.cpp | ||
| LegalizeFloatTypes.cpp | ||
| LegalizeIntegerTypes.cpp | ||
| LegalizeTypes.cpp | ||
| LegalizeTypes.h | ||
| LegalizeTypesGeneric.cpp | ||
| LegalizeVectorOps.cpp | ||
| LegalizeVectorTypes.cpp | ||
| LLVMBuild.txt | ||
| Makefile | ||
| ResourcePriorityQueue.cpp | ||
| ScheduleDAGFast.cpp | ||
| ScheduleDAGRRList.cpp | ||
| ScheduleDAGSDNodes.cpp | ||
| ScheduleDAGSDNodes.h | ||
| ScheduleDAGVLIW.cpp | ||
| SDNodeDbgValue.h | ||
| SelectionDAG.cpp | ||
| SelectionDAGBuilder.cpp | ||
| SelectionDAGBuilder.h | ||
| SelectionDAGDumper.cpp | ||
| SelectionDAGISel.cpp | ||
| SelectionDAGPrinter.cpp | ||
| TargetLowering.cpp | ||
| TargetSelectionDAGInfo.cpp | ||