Index: clang/lib/CodeGen/TargetInfo.cpp =================================================================== --- clang/lib/CodeGen/TargetInfo.cpp +++ clang/lib/CodeGen/TargetInfo.cpp @@ -2883,6 +2883,7 @@ // Classify the fields one at a time, merging the results. unsigned idx = 0; + const RecordType *IsUnion = RT->getAsUnionType(); for (RecordDecl::field_iterator i = RD->field_begin(), e = RD->field_end(); i != e; ++i, ++idx) { uint64_t Offset = OffsetBase + Layout.getFieldOffset(idx); @@ -2893,14 +2894,16 @@ continue; // AMD64-ABI 3.2.3p2: Rule 1. If the size of an object is larger than - // four eightbytes, or it contains unaligned fields, it has class MEMORY. + // eight eightbytes, or it contains unaligned fields, it has class MEMORY. // - // 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. + // The cases a 256-bit or a 512-bit wide vector could be used is when the + // struct contains a single 256-bit or 512-bit element. Since Lo and Hi + // logic isn't extended to work for sizes wider than 128, early check and + // fallback to memory. // - if (Size > 128 && (Size != getContext().getTypeSize(i->getType()) || - Size > getNativeVectorSizeForAVXABI(AVXLevel))) { + if (Size > 128 && + ((!IsUnion && Size != getContext().getTypeSize(i->getType())) || + Size > getNativeVectorSizeForAVXABI(AVXLevel))) { Lo = Memory; postMerge(Size, Lo, Hi); return; Index: clang/test/CodeGen/passing-union.c =================================================================== --- /dev/null +++ clang/test/CodeGen/passing-union.c @@ -0,0 +1,28 @@ +// RUN: %clang_cc1 -w -fblocks -ffreestanding -triple x86_64-linux-gnu -target-feature +avx -emit-llvm -o %t %s || FileCheck < %t %s --check-prefix=CHECK, AVX +// RUN: %clang_cc1 -w -fblocks -ffreestanding -triple x86_64-linux-gnu -target-feature +avx512f -emit-llvm -o %t %s || FileCheck < %t %s --check-prefix=CHECK, AVX512 +// This test verifies that passing union parameters through register. + +#include + +union M256 { + double d; + __m256 m; +}; + +union M512 { + double d; + __m512 m; +}; + +extern void foo1(union M256 A); +extern void foo2(union M512 A); +union M256 m1; +union M512 m2; +// CHECK-LABEL: define dso_local void @test() +// CHECK: void @foo1(<4 x double> +// AVX: call void @foo2(%union.M512* byval(%union.M512) align 64 +// AVX512: call void @foo2(<8 x double> +void test() { + foo1(m1); + foo2(m2); +}