fix the BuildVector -> unpcklps logic to not do pointless shuffles
when the top elements of a vector are undefined. This happens all
the time for X86-64 ABI stuff because only the low 2 elements of
a 4 element vector are defined. For example, on:
_Complex float f32(_Complex float A, _Complex float B) {
return A+B;
}
We used to produce (with SSE2, SSE4.1+ uses insertps):
_f32: ## @f32
movdqa %xmm0, %xmm2
addss %xmm1, %xmm2
pshufd $16, %xmm2, %xmm2
pshufd $1, %xmm1, %xmm1
pshufd $1, %xmm0, %xmm0
addss %xmm1, %xmm0
pshufd $16, %xmm0, %xmm1
movdqa %xmm2, %xmm0
unpcklps %xmm1, %xmm0
ret
We now produce:
_f32: ## @f32
movdqa %xmm0, %xmm2
addss %xmm1, %xmm2
pshufd $1, %xmm1, %xmm1
pshufd $1, %xmm0, %xmm3
addss %xmm1, %xmm3
movaps %xmm2, %xmm0
unpcklps %xmm3, %xmm0
ret
This implements rdar://8368414
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112378 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 91fc26c..8141634 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -4304,8 +4304,18 @@
// Step 2: unpcklps X, Y ==> <3, 2, 1, 0>
unsigned EltStride = NumElems >> 1;
while (EltStride != 0) {
- for (unsigned i = 0; i < EltStride; ++i)
+ for (unsigned i = 0; i < EltStride; ++i) {
+ // If V[i+EltStride] is undef and this is the first round of mixing,
+ // then it is safe to just drop this shuffle: V[i] is already in the
+ // right place, the one element (since it's the first round) being
+ // inserted as undef can be dropped. This isn't safe for successive
+ // rounds because they will permute elements within both vectors.
+ if (V[i+EltStride].getOpcode() == ISD::UNDEF &&
+ EltStride == NumElems/2)
+ continue;
+
V[i] = getUnpackl(DAG, dl, VT, V[i], V[i + EltStride]);
+ }
EltStride >>= 1;
}
return V[0];