Kostya wrote about it and he asked me to figure out if what's he is missing isn't already available one way or another.
Before we start
For those not used to Multimedia, Rust or Assembly
- Multimedia is all about processing data and serving/rendering it to the user at the right moment.
- That requires to have a good control over latency and use the least amount of cpu.
- This leads to use architecture specific extensions such as
x86_64 AVX2
orARM NEON
. - Higher level languages such as C (or Rust) offer access to those extension via intrinsics, but quite often they are cumbersome enough that writing assembly as-is ends up being more pleasant.
- You may look dav1d and rav1e for examples.
Rust and assembly
Rust had a fairly weak point in supporting assembly:
-
rustc
does not compile.s
or.S
asgcc
andclang
do, and that makes you rely on cc-rs or nasm-rs -
rustc
until recently did not have a stable support for inline-assembly, and right now it has some useful parts still in nightly.
How far are we?
Kostya tried the current stable and he managed to write some assembly for his h264 decoder and get a 20% gain, but he had 3 issues:
- He couldn't figure out how to manage sub-registers and the compiler warning wasn't that helpful for him since it assumes you know the
format!
terminology and you knowasm!
relates to it. this is being addressed -
asm!
operands in stable do not include sym and const. - Kostya couldn't figure out how to deal with templating the assembly using
macro_rules!()
as he is used to do withgcc
.
I asked on zulip since I couldn't think of better ways than munching tokens and usually this means I'm missing something much simpler and obvious.
Luckily Amanieu helped us and this blog post is more or less about keeping notes.
Use cases for inline asm templating
In multimedia software you often write tiny kernels that operate over blocks of pixels, 4x4
, 8x8
, 16x16
and so on and usually the same inner logic is shared across and you ideally would like to not repeat yourself, even more if the very same logic can be shared across the many many extensions x86 has.
Kostya used this as example
fn avg_4(dst: &mut [u8], dstride: usize, src: &[u8], sstride: usize, bh: usize) {
unsafe {
asm!(
"2:",
"movd xmm1, [{src}]",
"movd xmm3, [{src} + {sstride}]",
"movd xmm0, [{dst}]",
"movd xmm2, [{dst} + {dstride}]",
"lea {src}, [{src} + {sstride} * 2]",
"pavgb xmm0, xmm1",
"pavgb xmm2, xmm3",
"movd [{dst}], xmm0",
"movd [{dst} + {dstride}], xmm2",
"lea {dst}, [{dst} + {dstride} * 2]",
"sub {h}, 2",
"jnz 2b",
src = inout(reg) src.as_ptr() => _,
sstride = in(reg) sstride,
dst = inout(reg) dst.as_mut_ptr() => _,
dstride = in(reg) dstride,
h = inout(reg) bh => _,
out("xmm0") _,
out("xmm1") _,
out("xmm2") _,
out("xmm3") _,
);
}
}
fn avg_8(dst: &mut [u8], dstride: usize, src: &[u8], sstride: usize, bh: usize) {
unsafe {
asm!(
"2:",
"movq xmm0, [{src}]",
"movq xmm1, [{src} + {sstride}]",
"movq xmm2, [{dst}]",
"movq xmm3, [{dst} + {dstride}]",
"lea {src}, [{src} + {sstride} * 2]",
"pavgb xmm0, xmm2",
"pavgb xmm1, xmm3",
"movq [{dst}], xmm0",
"movq [{dst} + {dstride}], xmm1",
"lea {dst}, [{dst} + {dstride} * 2]",
"sub {h}, 2",
"jnz 2b",
src = inout(reg) src.as_ptr() => _,
sstride = in(reg) sstride,
dst = inout(reg) dst.as_mut_ptr() => _,
dstride = in(reg) dstride,
h = inout(reg) bh => _,
out("xmm0") _,
out("xmm1") _,
out("xmm2") _,
out("xmm3") _,
);
}
}
fn avg_16(dst: &mut [u8], dstride: usize, src: &[u8], sstride: usize, bh: usize) {
unsafe {
asm!(
"2:",
"movaps xmm0, [{src}]",
"movaps xmm1, [{src} + {sstride}]",
"pavgb xmm0, [{dst}]",
"pavgb xmm1, [{dst} + {dstride}]",
"lea {src}, [{src} + {sstride} * 2]",
"movq [{dst}], xmm0",
"movq [{dst} + {dstride}], xmm1",
"lea {dst}, [{dst} + {dstride} * 2]",
"sub {h}, 2",
"jnz 2b",
src = inout(reg) src.as_ptr() => _,
sstride = in(reg) sstride,
dst = inout(reg) dst.as_mut_ptr() => _,
dstride = in(reg) dstride,
h = inout(reg) bh => _,
out("xmm0") _,
out("xmm1") _,
);
}
}
Between avg_4
and avg_8
there is just a movd
vs movq
and for this Amalieu suggested to use the concat!
pattern he uses in corosensei.
avg_4 and avg_8 would end up being
macro_rules! avg {
($name: ident, $mov:literal) => {
fn $name(dst: &mut [u8], dstride: usize, src: &[u8], sstride: usize, bh: usize) {
unsafe {
asm!(
"2:",
concat!($mov, " xmm1, [{src}]"),
concat!($mov, " xmm3, [{src} + {sstride}]"),
concat!($mov, " xmm0, [{dst}]"),
concat!($mov, " xmm2, [{dst} + {dstride}]"),
"lea {src}, [{src} + {sstride} * 2]",
"pavgb xmm0, xmm1",
"pavgb xmm2, xmm3",
concat!($mov, " [{dst}], xmm0"),
concat!($mov, " [{dst} + {dstride}], xmm2"),
"lea {dst}, [{dst} + {dstride} * 2]",
"sub {h}, 2",
"jnz 2b",
src = inout(reg) src.as_ptr() => _,
sstride = in(reg) sstride,
dst = inout(reg) dst.as_mut_ptr() => _,
dstride = in(reg) dstride,
h = inout(reg) bh => _,
out("xmm0") _,
out("xmm1") _,
out("xmm2") _,
out("xmm3") _,
);
}
}
}
}
avg!{avg_4};
avg!{avg_8};
To factorize away avg_8 and avg_16, you need a way to deal with the operands
and while the asm statements are literals
, the operands
can be only expressed as tt
in a macro_rules!
.
The normal way to deal with this use-case is to rely on the preprocessor #if
directives, using macro_rules you have to be a bit more creative.
Amalieu gave me another example and I ended up crafting:
macro_rules! avg_common {
($name:ident { $($load:literal),* } { $($store:literal),* } $($out:tt)*) => {
fn $name(dst: &mut [u8], dstride: usize, src: &[u8], sstride: usize, bh: usize) {
unsafe {
asm!(
"2:",
$($load),*,
"lea {src}, [{src} + {sstride} * 2]",
"pavgb xmm0, xmm2",
"pavgb xmm1, xmm3",
$($store),*,
"lea {dst}, [{dst} + {dstride} * 2]",
"sub {h}, 2",
"jnz 2b",
src = inout(reg) src.as_ptr() => _,
sstride = in(reg) sstride,
dst = inout(reg) dst.as_mut_ptr() => _,
dstride = in(reg) dstride,
h = inout(reg) bh => _,
$($out)*
)
}
}
}
}
macro_rules! avg {
(avg_8) => {
avg_common!{avg_8 {
"movq xmm0, [{src}]",
"movq xmm1, [{src} + {sstride}]",
"movq xmm2, [{dst}]",
"movq xmm3, [{dst} + {dstride}]"
}
{
"movq [{dst}], xmm0",
"movq [{dst} + {dstride}], xmm1"
}
out("xmm0") _,
out("xmm1") _,
out("xmm2") _,
out("xmm3") _,
}
};
(avg_16) => {
avg_common!{avg_16 {
"movaps xmm0, [{src}]",
"movaps xmm1, [{src} + {sstride}]",
"pavgb xmm0, [{dst}]",
"pavgb xmm1, [{dst} + {dstride}]"
}
{
"movq [{dst}], xmm0",
"movq [{dst} + {dstride}], xmm1"
}
out("xmm0") _,
out("xmm1") _,
}
};
}
More or less solving Kostya problem even if supporting multiple blocks of operands would require extra care.
Coming next
I had been quite busy with the SIFIS-Home project in particular writing a new implementation of WebOfThings in Rust, soon we'll release the first version supporting wot-1.1 and probably I'll write a bit about it.
Top comments (0)