On PowerPC, a bitcast of <16 x i8> to i128 may run through a code
path in ExpandRes_BITCAST that attempts to do an intermediate
bitcast to a <4 x i32> vector, and then construct the Hi and Lo parts
of the resulting i128 by pairing up two of those i32 vector elements
each. The code already recognizes that on a big-endian system, the
first two vector elements form the Hi part, and the final two vector
elements form the Lo part (vice-versa from the little-endian situation).
However, we also need to take endianness into account when forming each
of those separate pairs: on a big-endian system, vector element 0 is
the *high* part of the pair making up the Hi part of the result, and
vector element 1 is the low part of the pair. The code currently always
uses vector element 0 as the low part and vector element 1 as the high
part, as is appropriate for little-endian platforms only.
This patch fixes this by swapping the vector elements as they are
paired up as appropriate.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@165802
91177308-0d34-0410-b5e6-
96231b3b80d8
// there are only two nodes left, i.e. Lo and Hi.
SDValue LHS = Vals[Slot];
SDValue RHS = Vals[Slot + 1];
+
+ if (TLI.isBigEndian())
+ std::swap(LHS, RHS);
+
Vals.push_back(DAG.getNode(ISD::BUILD_PAIR, dl,
EVT::getIntegerVT(
*DAG.getContext(),
--- /dev/null
+; RUN: llc < %s | FileCheck %s
+target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32:64"
+target triple = "powerpc64-unknown-linux-gnu"
+
+define i32 @test(<16 x i8> %v) nounwind {
+entry:
+ %0 = bitcast <16 x i8> %v to i128
+ %1 = lshr i128 %0, 96
+ %2 = trunc i128 %1 to i32
+ ret i32 %2
+}
+
+; Verify that bitcast handles big-endian platforms correctly
+; by checking we load the result from the correct offset
+
+; CHECK: addi [[REGISTER:[0-9]+]], 1, -16
+; CHECK: stvx 2, 0, [[REGISTER]]
+; CHECK: lwz 3, -16(1)
+; CHECK: blr
+