http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50819
Bug #: 50819
Summary: missed SLP vectorization
Classification: Unclassified
Product: gcc
Version: 4.7.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
AssignedTo: unassig...@gcc.gnu.org
ReportedBy: vincenzo.innoce...@cern.ch
in this example sum2 vectorize sum1 does not.
As you may suspect all current code looks more like sum1…
typedef float Value;
struct LorentzVector
{
LorentzVector(Value x=0, Value y=0, Value z=0, Value t=0) :
theX(x),theY(y),theZ(z),theT(t){}
LorentzVector & operator+=(const LorentzVector & a) {
theX += a.theX;
theY += a.theY;
theZ += a.theZ;
theT += a.theT;
return *this;
}
Value theX;
Value theY;
Value theZ;
Value theT;
} __attribute__ ((aligned(16)));
inline LorentzVector
operator+(LorentzVector const & a, LorentzVector const & b) {
return
LorentzVector(a.theX+b.theX,a.theY+b.theY,a.theZ+b.theZ,a.theT+b.theT);
}
inline LorentzVector
operator*(LorentzVector const & a, Value s) {
return LorentzVector(a.theX*s,a.theY*s,a.theZ*s,a.theT*s);
}
inline LorentzVector
operator*(Value s, LorentzVector const & a) {
return a*s;
}
void sum1(LorentzVector & res, Value s, LorentzVector const & v1, LorentzVector
const & v2) {
res += s*(v1+v2);
}
void sum2(LorentzVector & res, Value s, LorentzVector const & v1, LorentzVector
const & v2) {
res = res + s*(v1+v2);
}
c++ -O3 -c FourVec.cc
Vincenzos-MacBook-Pro:ctest innocent$ otool -V -t -v -X FourVec.o | c++filt
sum1(LorentzVector&, float, LorentzVector const&, LorentzVector const&):
movss 0x0c(%rsi),%xmm1
movss 0x08(%rsi),%xmm2
movss 0x04(%rsi),%xmm3
movss (%rsi),%xmm4
addss 0x0c(%rdx),%xmm1
addss 0x08(%rdx),%xmm2
addss 0x04(%rdx),%xmm3
addss (%rdx),%xmm4
mulss %xmm0,%xmm1
mulss %xmm0,%xmm2
mulss %xmm0,%xmm3
mulss %xmm0,%xmm4
addss 0x0c(%rdi),%xmm1
addss 0x08(%rdi),%xmm2
addss 0x04(%rdi),%xmm3
addss (%rdi),%xmm4
movss %xmm1,0x0c(%rdi)
movss %xmm2,0x08(%rdi)
movss %xmm3,0x04(%rdi)
movss %xmm4,(%rdi)
ret
nopl (%rax)
sum2(LorentzVector&, float, LorentzVector const&, LorentzVector const&):
movaps (%rsi),%xmm1
shufps $0x0,%xmm0,%xmm0
addps (%rdx),%xmm1
mulps %xmm1,%xmm0
addps (%rdi),%xmm0
movaps %xmm0,(%rdi)
ret
