mikros/rust
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add more SIMD

Browse Source
This commit is contained in:
Antoni Boucher 2022-06-05 18:53:30 -04:00
parent b55bd956dc
commit 13fa30c6c3
1 changed files with 19 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
src/intrinsic/llvm.rs
View File

@ -171,10 +171,7 @@ pub fn adjust_intrinsic_arguments<'a, 'b, 'gcc, 'tcx>(builder: &Builder<'a, 'gcc
new_args.push(last_arg);
args = new_args.into();
},
"__builtin_ia32_vfmaddsubps512_mask" | "__builtin_ia32_vfmaddsubpd512_mask" | "__builtin_ia32_vpmadd52huq512_mask"
| "__builtin_ia32_vpmadd52luq512_mask" | "__builtin_ia32_vpmadd52huq256_mask" | "__builtin_ia32_vpmadd52luq256_mask"
| "__builtin_ia32_vpmadd52huq128_mask"
=> {
"__builtin_ia32_vfmaddsubps512_mask" | "__builtin_ia32_vfmaddsubpd512_mask" => {
let mut new_args = args.to_vec();
let last_arg = new_args.pop().expect("last arg");
let arg4_type = gcc_func.get_param_type(3);
@ -188,7 +185,10 @@ pub fn adjust_intrinsic_arguments<'a, 'b, 'gcc, 'tcx>(builder: &Builder<'a, 'gcc
| "__builtin_ia32_vpermi2varq256_mask" | "__builtin_ia32_vpermi2varq128_mask"
| "__builtin_ia32_vpermi2varps512_mask" | "__builtin_ia32_vpermi2varps256_mask"
| "__builtin_ia32_vpermi2varps128_mask" | "__builtin_ia32_vpermi2varpd512_mask"
| "__builtin_ia32_vpermi2varpd256_mask" | "__builtin_ia32_vpermi2varpd128_mask" => {
| "__builtin_ia32_vpermi2varpd256_mask" | "__builtin_ia32_vpermi2varpd128_mask" | "__builtin_ia32_vpmadd52huq512_mask"
| "__builtin_ia32_vpmadd52luq512_mask" | "__builtin_ia32_vpmadd52huq256_mask" | "__builtin_ia32_vpmadd52luq256_mask"
| "__builtin_ia32_vpmadd52huq128_mask"
=> {
let mut new_args = args.to_vec();
let arg4_type = gcc_func.get_param_type(3);
let minus_one = builder.context.new_rvalue_from_int(arg4_type, -1);
@ -513,10 +513,10 @@ pub fn intrinsic<'gcc, 'tcx>(name: &str, cx: &CodegenCx<'gcc, 'tcx>) -> Function
"llvm.x86.avx512.mask.compress.store.b.512" => "__builtin_ia32_compressstoreuqi512_mask",
"llvm.x86.avx512.mask.compress.store.b.256" => "__builtin_ia32_compressstoreuqi256_mask",
"llvm.x86.avx512.mask.compress.store.b.128" => "__builtin_ia32_compressstoreuqi128_mask",
"llvm.x86.avx512.mask.compress.w.512" => "__builtin_ia32_compressstoreuhi512_mask",
"llvm.x86.avx512.mask.compress.w.512" => "__builtin_ia32_compresshi512_mask",
"llvm.x86.avx512.mask.compress.w.256" => "__builtin_ia32_compresshi256_mask",
"llvm.x86.avx512.mask.compress.w.128" => "__builtin_ia32_compresshi128_mask",
"llvm.x86.avx512.mask.compress.b.512" => "__builtin_ia32_compressstoreuqi512_mask",
"llvm.x86.avx512.mask.compress.b.512" => "__builtin_ia32_compressqi512_mask",
"llvm.x86.avx512.mask.compress.b.256" => "__builtin_ia32_compressqi256_mask",
"llvm.x86.avx512.mask.compress.b.128" => "__builtin_ia32_compressqi128_mask",
"llvm.x86.avx512.mask.expand.w.512" => "__builtin_ia32_expandhi512_mask",
@ -674,6 +674,18 @@ pub fn intrinsic<'gcc, 'tcx>(name: &str, cx: &CodegenCx<'gcc, 'tcx>) -> Function
"llvm.x86.avx512.vpmadd52h.uq.256" => "__builtin_ia32_vpmadd52huq256_mask",
"llvm.x86.avx512.vpmadd52l.uq.256" => "__builtin_ia32_vpmadd52luq256_mask",
"llvm.x86.avx512.vpmadd52h.uq.128" => "__builtin_ia32_vpmadd52huq128_mask",
"llvm.x86.avx512.vpdpwssd.512" => "__builtin_ia32_vpdpwssd_v16si",
"llvm.x86.avx512.vpdpwssd.256" => "__builtin_ia32_vpdpwssd_v8si",
"llvm.x86.avx512.vpdpwssd.128" => "__builtin_ia32_vpdpwssd_v4si",
"llvm.x86.avx512.vpdpwssds.512" => "__builtin_ia32_vpdpwssds_v16si",
"llvm.x86.avx512.vpdpwssds.256" => "__builtin_ia32_vpdpwssds_v8si",
"llvm.x86.avx512.vpdpwssds.128" => "__builtin_ia32_vpdpwssds_v4si",
"llvm.x86.avx512.vpdpbusd.512" => "__builtin_ia32_vpdpbusd_v16si",
"llvm.x86.avx512.vpdpbusd.256" => "__builtin_ia32_vpdpbusd_v8si",
"llvm.x86.avx512.vpdpbusd.128" => "__builtin_ia32_vpdpbusd_v4si",
"llvm.x86.avx512.vpdpbusds.512" => "__builtin_ia32_vpdpbusds_v16si",
"llvm.x86.avx512.vpdpbusds.256" => "__builtin_ia32_vpdpbusds_v8si",
"llvm.x86.avx512.vpdpbusds.128" => "__builtin_ia32_vpdpbusds_v4si",
// NOTE: this file is generated by https://github.com/GuillaumeGomez/llvmint/blob/master/generate_list.py
_ => include!("archs.rs"),