optimize bitcast(trunc(bitcast(x))) where the result is a float and 'x'
is a vector to be a vector element extraction. This allows clang to
compile:
struct S { float A, B, C, D; };
float foo(struct S A) { return A.A + A.B+A.C+A.D; }
into:
_foo: ## @foo
## BB#0: ## %entry
movd %xmm0, %rax
shrq $32, %rax
movd %eax, %xmm2
addss %xmm0, %xmm2
movapd %xmm1, %xmm3
addss %xmm2, %xmm3
movd %xmm1, %rax
shrq $32, %rax
movd %eax, %xmm0
addss %xmm3, %xmm0
ret
instead of:
_foo: ## @foo
## BB#0: ## %entry
movd %xmm0, %rax
movd %eax, %xmm0
shrq $32, %rax
movd %eax, %xmm2
addss %xmm0, %xmm2
movd %xmm1, %rax
movd %eax, %xmm1
addss %xmm2, %xmm1
shrq $32, %rax
movd %eax, %xmm0
addss %xmm1, %xmm0
ret
... eliminating half of the horribleness.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112227 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Transforms/InstCombine/InstCombineCasts.cpp b/lib/Transforms/InstCombine/InstCombineCasts.cpp
index dbe5200..ef5bbc4 100644
--- a/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -1335,6 +1335,35 @@
return new ShuffleVectorInst(InVal, V2, Mask);
}
+/// OptimizeIntToFloatBitCast - See if we can optimize an integer->float/double
+/// bitcast. The various long double bitcasts can't get in here.
+static Instruction *OptimizeIntToFloatBitCast(BitCastInst &CI,InstCombiner &IC) {
+ Value *Src = CI.getOperand(0);
+
+ // If this is a bitcast from int to float, check to see if the int is an
+ // extraction from a vector.
+ Value *VecInput = 0;
+ if (match(Src, m_Trunc(m_BitCast(m_Value(VecInput)))) &&
+ isa<VectorType>(VecInput->getType())) {
+ const VectorType *VecTy = cast<VectorType>(VecInput->getType());
+ const Type *DestTy = CI.getType();
+
+ // If the element type of the vector doesn't match the result type, but the
+ // vector type's size is a multiple of the result type, bitcast it to be a
+ // vector type we can extract from.
+ if (VecTy->getElementType() != DestTy &&
+ VecTy->getPrimitiveSizeInBits() % DestTy->getPrimitiveSizeInBits()==0) {
+ VecTy = VectorType::get(DestTy,
+ VecTy->getPrimitiveSizeInBits() / DestTy->getPrimitiveSizeInBits());
+ VecInput = IC.Builder->CreateBitCast(VecInput, VecTy);
+ }
+
+ if (VecTy->getElementType() == DestTy)
+ return ExtractElementInst::Create(VecInput, IC.Builder->getInt32(0));
+ }
+
+ return 0;
+}
Instruction *InstCombiner::visitBitCast(BitCastInst &CI) {
// If the operands are integer typed then apply the integer transforms,
@@ -1386,6 +1415,11 @@
((Instruction*)NULL));
}
}
+
+ // Try to optimize int -> float bitcasts.
+ if ((DestTy->isFloatTy() || DestTy->isDoubleTy()) && isa<IntegerType>(SrcTy))
+ if (Instruction *I = OptimizeIntToFloatBitCast(CI, *this))
+ return I;
if (const VectorType *DestVTy = dyn_cast<VectorType>(DestTy)) {
if (DestVTy->getNumElements() == 1 && !SrcTy->isVectorTy()) {