The Dlang SIMD library
intel-intrinsics
is the SIMD library for D.
intel-intrinsics
lets you use SIMD in D with support for LDC / DMD / GDC with a single syntax and API: the x86 Intel Intrinsics API that is also used within the C, C++, and Rust communities.
intel-intrinsics
is most similar to simd-everywhere, it can target AArch64 for full-speed with Apple Silicon without code change.
"dependencies":
{
"intel-intrinsics": "~>1.0"
}
_mm_
prefixDMD x86/x86_64 | LDC x86/x86_64 | LDC arm64 | GDC x86_64 | |
---|---|---|---|---|
MMX | Yes but (#42) | Yes | Yes | Yes |
SSE | Yes | Yes | Yes | Yes |
SSE2 | Yes but (#42) | Yes | Yes | Yes |
SSE3 | Yes but (#42) | Yes (-mattr=+sse3 ) |
Yes | Yes (-msse3 ) |
SSSE3 | Yes (-mcpu ) |
Yes (-mattr=+ssse3 ) |
Yes | Yes (-mssse3 ) |
SSE4.1 | Yes but (#42) | Yes (-mattr=+sse4.1 ) |
Yes | Yes (-msse4.1 ) |
SSE4.2 | Yes but (#42) | Yes (-mattr=+sse4.2 ) |
Yes (-mattr=+crc ) |
Yes (-msse4.2 ) |
BMI2 | Yes but (#42) | Yes (-mattr=+bmi2 ) |
Yes | Yes (-mbmi2 ) |
AVX | Yes but (#42) | Yes (-mattr=+avx ) |
Yes | Yes (-mavx ) |
AVX2 | WIP and (#42) | WIP (-mattr=+avx2 ) |
WIP | WIP (-mavx2 ) |
The intrinsics implemented follow the syntax and semantics at: https://software.intel.com/sites/landingpage/IntrinsicsGuide/
The philosophy (and guarantee) of intel-intrinsics
is:
intel-intrinsics
generates optimal code else it's a bug.intel-intrinsics
define the following types whatever the compiler and target:
long1
, int2
, short4
, byte8
, float2
,
long2
, int4
, short8
, byte16
, float4
, double2
long4
, int8
, short16
, byte32
, float8
, double4
though most of the time you will deal with:
alias __m128 = float4;
alias __m128i = int4;
alias __m128d = double2;
alias __m64 = long1;
alias __m256 = float8;
alias __m256i = long4;
alias __m256d = double4;
This type erasure of integers vectors is a defining point of the Intel API.
intel-intrinsics
implements Vector Operators for compilers that don't have __vector
support (DMD with 32-bit x86 target, 256-bit vectors with GDC without -mavx
...). It doesn't provide unsigned vectors though.
Example:
__m128 add_4x_floats(__m128 a, __m128 b)
{
return a + b;
}
is the same as:
__m128 add_4x_floats(__m128 a, __m128 b)
{
return _mm_add_ps(a, b);
}
One exception to this is
int4
*int4
. Older GDC and current DMD do not have this operator. Instead, do use_mm_mullo_epi32
frominteli.smmintrin
module.
It is recommended to do it in that way for maximum portability:
__m128i A;
// recommended portable way to set a single SIMD element
A.ptr[0] = 42;
// recommended portable way to get a single SIMD element
int elem = A.array[0];
intel-intrinsics
?Portability
It just works the same for DMD, LDC, and GDC.
When using LDC, intel-intrinsics
allows to target AArch64 and 32-bit ARM with the same semantics.
Capabilities
Some instructions just aren't accessible using core.simd
and ldc.simd
capabilities. For example: pmaddwd
which is so important in digital video. Some instructions need an almost exact sequence of LLVM IR to get generated. ldc.intrinsics
is a moving target and you need a layer on top of it.
Familiarity Intel intrinsic syntax is more familiar to C and C++ programmers. The Intel intrinsics names aren't good, but they are known identifiers. The problem with introducing new names is that you need hundreds of new identifiers.
Documentation There is a convenient online guide provided by Intel: https://software.intel.com/sites/landingpage/IntrinsicsGuide/ Without that Intel documentation, it's impractical to write sizeable SIMD code.
dg2d
is a very fast 2D renderer, twice as fast as Cairointel-intrinsics
AArch64 and 32-bit ARM respects floating-point rounding through MXCSR emulation. This works using FPCR as thread-local store for rounding mode.
Some features of MXCSR are absent:
32-bit ARM has a different nearest rounding mode as compared to AArch64 and x86. Numbers with a 0.5 fractional part (such as -4.5
) may not round in the same direction. This shouldn't affect you.
Some ARM architecture do not represent the sign bit for NaN. Just writing -float.nan
or -double.nan
will loose the sign bit! This isn't related to intel-intrinsics
.
intel-intrinsics
semanticsIn this DConf 2019 talk, Auburn Sounds:
intel-intrinsics
came to be,See the talk: intel-intrinsics: Not intrinsically about intrinsics