mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
d98e321d12
When we pass a AArch64 Homogeneous Floating-Point
Aggregate (HFA) argument with increased alignment
requirements, for example
struct S {
__attribute__ ((__aligned__(16))) double v[4];
};
Clang uses `[4 x double]` for the parameter, which is passed
on the stack at alignment 8, whereas it should be at
alignment 16, following Rule C.4 in
AAPCS (https://github.com/ARM-software/abi-aa/blob/master/aapcs64/aapcs64.rst#642parameter-passing-rules)
Currently we don't have a way to express in LLVM IR the
alignment requirements of the function arguments. The align
attribute is applicable to pointers only, and only for some
special ways of passing arguments (e..g byval). When
implementing AAPCS32/AAPCS64, clang resorts to dubious hacks
of coercing to types, which naturally have the needed
alignment. We don't have enough types to cover all the
cases, though.
This patch introduces a new use of the stackalign attribute
to control stack slot alignment, when and if an argument is
passed in memory.
The attribute align is left as an optimizer hint - it still
applies to pointer types only and pertains to the content of
the pointer, whereas the alignment of the pointer itself is
determined by the stackalign attribute.
For byval arguments, the stackalign attribute assumes the
role, previously perfomed by align, falling back to align if
stackalign` is absent.
On the clang side, when passing arguments using the "direct"
style (cf. `ABIArgInfo::Kind`), now we can optionally
specify an alignment, which is emitted as the new
`stackalign` attribute.
Patch by Momchil Velikov and Lucas Prates.
Differential Revision: https://reviews.llvm.org/D98794
34 lines
1.3 KiB
LLVM
34 lines
1.3 KiB
LLVM
; RUN: llc < %s -mtriple=arm64-none-eabi | FileCheck %s
|
|
|
|
; Over-aligned HFA argument placed on register - one element per register
|
|
define double @test_hfa_align_arg_reg([2 x double] alignstack(16) %h.coerce) local_unnamed_addr #0 {
|
|
entry:
|
|
; CHECK-LABEL: test_hfa_align_arg_reg:
|
|
; CHECK-NOT: mov
|
|
; CHECK-NOT: ld
|
|
; CHECK: ret
|
|
%h.coerce.fca.0.extract = extractvalue [2 x double] %h.coerce, 0
|
|
ret double %h.coerce.fca.0.extract
|
|
}
|
|
|
|
; Call with over-aligned HFA argument placed on register - one element per register
|
|
define double @test_hfa_align_call_reg() local_unnamed_addr #0 {
|
|
entry:
|
|
; CHECK-LABEL: test_hfa_align_call_reg:
|
|
; CHECK-DAG: fmov d0, #1.00000000
|
|
; CHECK-DAG: fmov d1, #2.00000000
|
|
; CHECK: bl test_hfa_align_arg_reg
|
|
%call = call double @test_hfa_align_arg_reg([2 x double] alignstack(16) [double 1.000000e+00, double 2.000000e+00])
|
|
ret double %call
|
|
}
|
|
|
|
; Over-aligned HFA argument placed on stack - stack round up to alignment
|
|
define double @test_hfa_align_arg_stack(double %d0, double %d1, double %d2, double %d3, double %d4, double %d5, double %d6, double %d7, float %f, [2 x double] alignstack(16) %h.coerce) local_unnamed_addr #0 {
|
|
entry:
|
|
; CHECK-LABEL: test_hfa_align_arg_stack:
|
|
; CHECK: ldr d0, [sp, #16]
|
|
; CHECK-NEXT: ret
|
|
%h.coerce.fca.0.extract = extractvalue [2 x double] %h.coerce, 0
|
|
ret double %h.coerce.fca.0.extract
|
|
}
|