From ccafadb68f5a8132a4ee23f441cf5d6976a4133b Mon Sep 17 00:00:00 2001 From: Bruno Cardoso Lopes Date: Tue, 12 Jul 2011 00:30:27 +0000 Subject: [PATCH] Fix one x86_64 abi issue and the test to actually look for the right thing, which is: { <4 x float>, <4 x float> } should continue to go through memory. git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@134946 91177308-0d34-0410-b5e6-96231b3b80d8 --- lib/CodeGen/TargetInfo.cpp | 9 ++++++++- test/CodeGen/x86_64-arguments.c | 4 ++-- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/lib/CodeGen/TargetInfo.cpp b/lib/CodeGen/TargetInfo.cpp index 0c070a19d8..7c850afbf8 100644 --- a/lib/CodeGen/TargetInfo.cpp +++ b/lib/CodeGen/TargetInfo.cpp @@ -1228,6 +1228,13 @@ void X86_64ABIInfo::classify(QualType Ty, uint64_t OffsetBase, const RecordDecl *RD = RT->getDecl(); + // The only case a 256-bit wide vector could be used is when the struct + // contains a single 256-bit element. Since Lo and Hi logic isn't extended + // to work for sizes wider than 128, early check and fallback to memory. + RecordDecl::field_iterator FirstElt = RD->field_begin(); + if (Size > 128 && getContext().getTypeSize(FirstElt->getType()) != 256) + return; + // Assume variable sized types are passed in memory. if (RD->hasFlexibleArrayMember()) return; @@ -1263,7 +1270,7 @@ void X86_64ABIInfo::classify(QualType Ty, uint64_t OffsetBase, // Classify the fields one at a time, merging the results. unsigned idx = 0; - for (RecordDecl::field_iterator i = RD->field_begin(), e = RD->field_end(); + for (RecordDecl::field_iterator i = FirstElt, e = RD->field_end(); i != e; ++i, ++idx) { uint64_t Offset = OffsetBase + Layout.getFieldOffset(idx); bool BitField = i->isBitField(); diff --git a/test/CodeGen/x86_64-arguments.c b/test/CodeGen/x86_64-arguments.c index 38278f49d8..3d4016db82 100644 --- a/test/CodeGen/x86_64-arguments.c +++ b/test/CodeGen/x86_64-arguments.c @@ -280,9 +280,9 @@ void f39() { f38(x38); f37(x37); } // Make sure that the struct below is passed in the same way // regardless of avx being used // -// CHECK: define void @func41(<2 x double> %s.coerce) +// CHECK: declare void @func40(%struct.t128* byval align 16) typedef float __m128 __attribute__ ((__vector_size__ (16))); -typedef struct { +typedef struct t128 { __m128 m; __m128 n; } two128; -- 2.40.0