6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-08-05 13:26:55 +00:00
Code Issues Projects Releases Wiki Activity

Recognize unpckh* masks and match 256-bit versions. The new versions are

Browse Source 
different from the previous 128-bit because they work in lanes.
Update a few comments and add testcases

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@136157 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Bruno Cardoso Lopes
2011-07-26 22:03:40 +00:00
parent c680b92460
commit 4ea496846a
11 changed files with 148 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
lib/Target/X86/Utils/X86ShuffleDecode.cpp
View File

@@ -167,23 +167,22 @@ void DecodeUNPCKLPMask(EVT VT,
SmallVectorImpl<unsigned> &ShuffleMask) {
unsigned NumElts = VT.getVectorNumElements();
// Handle vector lengths > 128 bits. Define a "section" as a set of
// 128 bits. AVX defines UNPCK* to operate independently on 128-bit
// sections.
unsigned NumSections = VT.getSizeInBits() / 128;
if (NumSections == 0 ) NumSections = 1; // Handle MMX
unsigned NumSectionElts = NumElts / NumSections;
// Handle 128 and 256-bit vector lengths. AVX defines UNPCK* to operate
// independently on 128-bit lanes.
unsigned NumLanes = VT.getSizeInBits() / 128;
if (NumLanes == 0 ) NumLanes = 1; // Handle MMX
unsigned NumLaneElts = NumElts / NumLanes;
unsigned Start = 0;
unsigned End = NumSectionElts / 2;
for (unsigned s = 0; s < NumSections; ++s) {
unsigned End = NumLaneElts / 2;
for (unsigned s = 0; s < NumLanes; ++s) {
for (unsigned i = Start; i != End; ++i) {
ShuffleMask.push_back(i); // Reads from dest/src1
ShuffleMask.push_back(i+NumSectionElts); // Reads from src/src2
ShuffleMask.push_back(i+NumLaneElts); // Reads from src/src2
}
// Process the next 128 bits.
Start += NumSectionElts;
End += NumSectionElts;
Start += NumLaneElts;
End += NumLaneElts;
}
}