6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2026-04-20 16:17:38 +00:00
Code Issues Projects Releases Wiki Activity

Allow vectorization of bit intrinsics in BB Vectorizer.

Browse Source 
This patch adds support for vectorization of  bit intrinsics such as bswap,ctpop,ctlz,cttz.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207174 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Karthik Bhat
2014-04-25 03:33:48 +00:00
parent 38ac7e92d8
commit ac16f0e024
3 changed files with 181 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/Transforms/Vectorize/BBVectorize.cpp
+21 -8
View File
@@ -122,6 +122,10 @@ static cl::opt<bool>
NoMath("bb-vectorize-no-math", cl::init(false), cl::Hidden,
cl::desc("Don't try to vectorize floating-point math intrinsics"));
static cl::opt<bool>
NoBitManipulation("bb-vectorize-no-bitmanip", cl::init(false), cl::Hidden,
cl::desc("Don't try to vectorize BitManipulation intrinsics"));
static cl::opt<bool>
NoFMA("bb-vectorize-no-fma", cl::init(false), cl::Hidden,
cl::desc("Don't try to vectorize the fused-multiply-add intrinsic"));
@@ -684,6 +688,11 @@ namespace {
case Intrinsic::floor:
case Intrinsic::fabs:
return Config.VectorizeMath;
case Intrinsic::bswap:
case Intrinsic::ctpop:
case Intrinsic::ctlz:
case Intrinsic::cttz:
return Config.VectorizeBitManipulations;
case Intrinsic::fma:
case Intrinsic::fmuladd:
return Config.VectorizeFMA;
@@ -1088,13 +1097,14 @@ namespace {
CostSavings = ICost + JCost - VCost;
}
// The powi intrinsic is special because only the first argument is
// vectorized, the second arguments must be equal.
// The powi,ctlz,cttz intrinsics are special because only the first
// argument is vectorized, the second arguments must be equal.
CallInst *CI = dyn_cast<CallInst>(I);
Function *FI;
if (CI && (FI = CI->getCalledFunction())) {
Intrinsic::ID IID = (Intrinsic::ID) FI->getIntrinsicID();
if (IID == Intrinsic::powi) {
if (IID == Intrinsic::powi || IID == Intrinsic::ctlz ||
IID == Intrinsic::cttz) {
Value *A1I = CI->getArgOperand(1),
*A1J = cast<CallInst>(J)->getArgOperand(1);
const SCEV *A1ISCEV = SE->getSCEV(A1I),
@@ -1118,7 +1128,8 @@ namespace {
assert(CI->getNumArgOperands() == CJ->getNumArgOperands() &&
"Intrinsic argument counts differ");
for (unsigned i = 0, ie = CI->getNumArgOperands(); i != ie; ++i) {
if (IID == Intrinsic::powi && i == 1)
if ((IID == Intrinsic::powi || IID == Intrinsic::ctlz ||
IID == Intrinsic::cttz) && i == 1)
Tys.push_back(CI->getArgOperand(i)->getType());
else
Tys.push_back(getVecTypeForPair(CI->getArgOperand(i)->getType(),
@@ -2773,10 +2784,11 @@ namespace {
ReplacedOperands[o] = Intrinsic::getDeclaration(M, IID, VArgType);
continue;
} else if (IID == Intrinsic::powi && o == 1) {
// The second argument of powi is a single integer and we've already
// checked that both arguments are equal. As a result, we just keep
// I's second argument.
} else if ((IID == Intrinsic::powi || IID == Intrinsic::ctlz ||
IID == Intrinsic::cttz) && o == 1) {
// The second argument of powi/ctlz/cttz is a single integer/constant
// and we've already checked that both arguments are equal.
// As a result, we just keep I's second argument.
ReplacedOperands[o] = I->getOperand(o);
continue;
}
@@ -3222,6 +3234,7 @@ VectorizeConfig::VectorizeConfig() {
VectorizePointers = !::NoPointers;
VectorizeCasts = !::NoCasts;
VectorizeMath = !::NoMath;
VectorizeBitManipulations = !::NoBitManipulation;
VectorizeFMA = !::NoFMA;
VectorizeSelect = !::NoSelect;
VectorizeCmp = !::NoCmp;