forked from OSchip/llvm-project
[CodeGen] Combine concat_vector of trunc'd scalar to scalar_to_vector.
We already do: concat_vectors(scalar, undef) -> scalar_to_vector(scalar) When the scalar is legal. When it's not, but is a truncated legal scalar, we can also do: concat_vectors(trunc(scalar), undef) -> scalar_to_vector(scalar) Which is equivalent, since the upper lanes are undef anyway. While there, teach the combine to look at more than 2 operands. Differential Revision: http://reviews.llvm.org/D8883 llvm-svn: 234530
This commit is contained in:
parent
bd0c7eb4dc
commit
df43737782
|
@ -11514,9 +11514,10 @@ SDValue DAGCombiner::visitCONCAT_VECTORS(SDNode *N) {
|
|||
if (ISD::allOperandsUndef(N))
|
||||
return DAG.getUNDEF(VT);
|
||||
|
||||
// Optimize concat_vectors where one of the vectors is undef.
|
||||
if (N->getNumOperands() == 2 &&
|
||||
N->getOperand(1)->getOpcode() == ISD::UNDEF) {
|
||||
// Optimize concat_vectors where all but the first of the vectors are undef.
|
||||
if (std::all_of(std::next(N->op_begin()), N->op_end(), [](const SDValue &Op) {
|
||||
return Op.getOpcode() == ISD::UNDEF;
|
||||
})) {
|
||||
SDValue In = N->getOperand(0);
|
||||
assert(In.getValueType().isVector() && "Must concat vectors");
|
||||
|
||||
|
@ -11524,6 +11525,15 @@ SDValue DAGCombiner::visitCONCAT_VECTORS(SDNode *N) {
|
|||
if (In->getOpcode() == ISD::BITCAST &&
|
||||
!In->getOperand(0)->getValueType(0).isVector()) {
|
||||
SDValue Scalar = In->getOperand(0);
|
||||
|
||||
// If the bitcast type isn't legal, it might be a trunc of a legal type;
|
||||
// look through the trunc so we can still do the transform:
|
||||
// concat_vectors(trunc(scalar), undef) -> scalar_to_vector(scalar)
|
||||
if (Scalar->getOpcode() == ISD::TRUNCATE &&
|
||||
!TLI.isTypeLegal(Scalar.getValueType()) &&
|
||||
TLI.isTypeLegal(Scalar->getOperand(0).getValueType()))
|
||||
Scalar = Scalar->getOperand(0);
|
||||
|
||||
EVT SclTy = Scalar->getValueType(0);
|
||||
|
||||
if (!SclTy.isFloatingPoint() && !SclTy.isInteger())
|
||||
|
|
|
@ -2,6 +2,8 @@
|
|||
|
||||
target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
|
||||
|
||||
; Test the (concat_vectors (trunc), (trunc)) pattern.
|
||||
|
||||
define <4 x i16> @test_concat_truncate_v2i64_to_v4i16(<2 x i64> %a, <2 x i64> %b) #0 {
|
||||
entry:
|
||||
; CHECK-LABEL: test_concat_truncate_v2i64_to_v4i16:
|
||||
|
|
|
@ -0,0 +1,18 @@
|
|||
; RUN: llc < %s -mtriple aarch64-unknown-unknown -asm-verbose=false | FileCheck %s
|
||||
|
||||
target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
|
||||
|
||||
; Test the (concat_vectors (bitcast (trunc (scalar))), undef..) pattern.
|
||||
|
||||
define <8 x i8> @test_concat_from_truncated_scalar(i32 %x) #0 {
|
||||
entry:
|
||||
; CHECK-LABEL: test_concat_from_truncated_scalar:
|
||||
; CHECK-NEXT: fmov s0, w0
|
||||
; CHECK-NEXT: ret
|
||||
%t = trunc i32 %x to i16
|
||||
%0 = bitcast i16 %t to <2 x i8>
|
||||
%1 = shufflevector <2 x i8> %0, <2 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 2, i32 2, i32 2, i32 2, i32 2>
|
||||
ret <8 x i8> %1
|
||||
}
|
||||
|
||||
attributes #0 = { nounwind }
|
Loading…
Reference in New Issue