Hi,
Could we introduce special attribute for struct definitions to
make function ABI look like it accepts all fields as separate
data (recursively)?
Its application should be constrained because alignment and etc.
Reasons:
1. clean unified _and_ hight level ABI with existing C libraries
in both export from D and import to D directions.
2. Speed. For example LAPACK routine for small size matrixes
would be 5-10% slower if we implement them using ndslices API.
3. Code size. Many LAPACK routines only call a lot of BLAS
functions and do not compute anything itself. If we use ndslices
for GLAS ABI, then code size will grow.
Note that BLAS/GLAS routines are not and should not be inlined.
2 and 3 are not jokes, please see code examples below.
Thanks,
Ilya
ldc2 -betterC -output-s -O -release -boundscheck=off testcc.d
-----
pragma(inline, false)
ref back(size_t length, sizediff_t stride, double* ptr)
{
return ptr[(length - 1) * stride];
}
auto foo(size_t length, sizediff_t stride, double* ptr)
{
return back(length, stride, ptr);
}
///////////
struct Slice
{
size_t length;
sizediff_t stride;
double* ptr;
}
pragma(inline, false)
ref back(Slice slice)
{
with(slice)
return ptr[(length - 1) * stride];
}
auto foo(Slice slice)
{
return back(slice);
}
-----
-----
// back 1 (desired)
decq %rdx
imulq %rsi, %rdx
leaq (%rdi,%rdx,8), %rax
retq
// foo 1 (desired)
pushq %rax
Lcfi0:
callq __D6testcc4backFNaNbNcNimlPdZd
movsd (%rax), %xmm0
popq %rax
retq
///////////
// back 1 (current)
movq 8(%rsp), %rax
decq %rax
imulq 16(%rsp), %rax
shlq $3, %rax
addq 24(%rsp), %rax
retq
// foo 1 (current)
subq $24, %rsp
Lcfi1:
movq 48(%rsp), %rax
movq %rax, 16(%rsp)
movq 32(%rsp), %rax
movq 40(%rsp), %rcx
movq %rcx, 8(%rsp)
movq %rax, (%rsp)
callq __D6testcc4backFNaNbNcNiS6testcc5SliceZd
movsd (%rax), %xmm0
addq $24, %rsp
retq
-----
