forked from OSchip/llvm-project
[X86] Passing union type through register
For example: union M256 { double d; __m256 m; }; extern void foo1(union M256 A); union M256 m1; void test() { foo1(m1); } clang will pass m1 through stack which does not follow the ABI. Differential Revision: https://reviews.llvm.org/D78699
This commit is contained in:
parent
c1489ee5a7
commit
26cfb6e562
|
@ -3061,6 +3061,7 @@ void X86_64ABIInfo::classify(QualType Ty, uint64_t OffsetBase,
|
||||||
|
|
||||||
// Classify the fields one at a time, merging the results.
|
// Classify the fields one at a time, merging the results.
|
||||||
unsigned idx = 0;
|
unsigned idx = 0;
|
||||||
|
bool IsUnion = RT->isUnionType();
|
||||||
for (RecordDecl::field_iterator i = RD->field_begin(), e = RD->field_end();
|
for (RecordDecl::field_iterator i = RD->field_begin(), e = RD->field_end();
|
||||||
i != e; ++i, ++idx) {
|
i != e; ++i, ++idx) {
|
||||||
uint64_t Offset = OffsetBase + Layout.getFieldOffset(idx);
|
uint64_t Offset = OffsetBase + Layout.getFieldOffset(idx);
|
||||||
|
@ -3071,13 +3072,16 @@ void X86_64ABIInfo::classify(QualType Ty, uint64_t OffsetBase,
|
||||||
continue;
|
continue;
|
||||||
|
|
||||||
// AMD64-ABI 3.2.3p2: Rule 1. If the size of an object is larger than
|
// 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
|
// The only case a 256-bit or a 512-bit wide vector could be used is when
|
||||||
// contains a single 256-bit element. Since Lo and Hi logic isn't extended
|
// the struct contains a single 256-bit or 512-bit element. Early check
|
||||||
// to work for sizes wider than 128, early check and fallback to memory.
|
// and fallback to memory.
|
||||||
//
|
//
|
||||||
if (Size > 128 && (Size != getContext().getTypeSize(i->getType()) ||
|
// FIXME: Extended the Lo and Hi logic properly to work for size wider
|
||||||
|
// than 128.
|
||||||
|
if (Size > 128 &&
|
||||||
|
((!IsUnion && Size != getContext().getTypeSize(i->getType())) ||
|
||||||
Size > getNativeVectorSizeForAVXABI(AVXLevel))) {
|
Size > getNativeVectorSizeForAVXABI(AVXLevel))) {
|
||||||
Lo = Memory;
|
Lo = Memory;
|
||||||
postMerge(Size, Lo, Hi);
|
postMerge(Size, Lo, Hi);
|
||||||
|
|
|
@ -0,0 +1,29 @@
|
||||||
|
// RUN: %clang_cc1 -w -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 -ffreestanding -triple x86_64-linux-gnu -target-feature +avx512f -emit-llvm -o %t %s || FileCheck < %t %s --check-prefix=CHECK, AVX512
|
||||||
|
// This tests verifies that a union parameter should pass by a vector regitster whose first eightbyte is SSE and the other eightbytes are SSEUP.
|
||||||
|
|
||||||
|
typedef int __m256 __attribute__ ((__vector_size__ (32)));
|
||||||
|
typedef int __m512 __attribute__ ((__vector_size__ (64)));
|
||||||
|
|
||||||
|
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);
|
||||||
|
}
|
Loading…
Reference in New Issue