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

Fix some vfmaddsub intrinsics

Browse Source
This commit is contained in:
Antoni Boucher 2022-10-08 14:37:36 -04:00
parent 23a1a86835
commit c573621812
3 changed files with 26 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/builder.rs
View File

@ -280,7 +280,11 @@ fn function_ptr_call(&mut self, func_ptr: RValue<'gcc>, args: &[RValue<'gcc>], _
let func_name = format!("{:?}", func_ptr);
let previous_arg_count = args.len();
let orig_args = args;
let args = llvm::adjust_intrinsic_arguments(&self, gcc_func, args.into(), &func_name);
let args = {
let function_address_names = self.function_address_names.borrow();
let original_function_name = function_address_names.get(&func_ptr);
llvm::adjust_intrinsic_arguments(&self, gcc_func, args.into(), &func_name, original_function_name)
};
let args_adjusted = args.len() != previous_arg_count;
let args = self.check_ptr_call("call", func_ptr, &*args);

3
src/context.rs
View File

@ -33,6 +33,7 @@ pub struct CodegenCx<'gcc, 'tcx> {
// TODO(bjorn3): Can this field be removed?
pub current_func: RefCell<Option<Function<'gcc>>>,
pub normal_function_addresses: RefCell<FxHashSet<RValue<'gcc>>>,
pub function_address_names: RefCell<FxHashMap<RValue<'gcc>, String>>,
pub functions: RefCell<FxHashMap<String, Function<'gcc>>>,
pub intrinsics: RefCell<FxHashMap<String, Function<'gcc>>>,
@ -192,6 +193,7 @@ pub fn new(context: &'gcc Context<'gcc>, codegen_unit: &'tcx CodegenUnit<'tcx>,
context,
current_func: RefCell::new(None),
normal_function_addresses: Default::default(),
function_address_names: Default::default(),
functions: RefCell::new(functions),
intrinsics: RefCell::new(FxHashMap::default()),
@ -345,6 +347,7 @@ fn get_fn_addr(&self, instance: Instance<'tcx>) -> RValue<'gcc> {
// FIXME(antoyo): the rustc API seems to call get_fn_addr() when not needed (e.g. for FFI).
self.normal_function_addresses.borrow_mut().insert(ptr);
self.function_address_names.borrow_mut().insert(ptr, func_name.to_string());
ptr
}

24
src/intrinsic/llvm.rs
View File

@ -5,7 +5,7 @@
use crate::{context::CodegenCx, builder::Builder};
pub fn adjust_intrinsic_arguments<'a, 'b, 'gcc, 'tcx>(builder: &Builder<'a, 'gcc, 'tcx>, gcc_func: FunctionPtrType<'gcc>, mut args: Cow<'b, [RValue<'gcc>]>, func_name: &str) -> Cow<'b, [RValue<'gcc>]> {
pub fn adjust_intrinsic_arguments<'a, 'b, 'gcc, 'tcx>(builder: &Builder<'a, 'gcc, 'tcx>, gcc_func: FunctionPtrType<'gcc>, mut args: Cow<'b, [RValue<'gcc>]>, func_name: &str, original_function_name: Option<&String>) -> Cow<'b, [RValue<'gcc>]> {
// Some LLVM intrinsics do not map 1-to-1 to GCC intrinsics, so we add the missing
// arguments here.
if gcc_func.get_param_count() != args.len() {
@ -277,11 +277,23 @@ pub fn adjust_intrinsic_arguments<'a, 'b, 'gcc, 'tcx>(builder: &Builder<'a, 'gcc
let c = builder.context.new_rvalue_from_vector(None, arg3_type, &[new_args[2]; 2]);
args = vec![a, b, c, new_args[3]].into();
},
"__builtin_ia32_vfmaddsubpd256" | "__builtin_ia32_vfmaddsubps" | "__builtin_ia32_vfmaddsubps256" => {
let mut new_args = args.to_vec();
let arg3 = &mut new_args[2];
*arg3 = builder.context.new_unary_op(None, UnaryOp::Minus, arg3.get_type(), *arg3);
args = new_args.into();
"__builtin_ia32_vfmaddsubpd256" | "__builtin_ia32_vfmaddsubps" | "__builtin_ia32_vfmaddsubps256"
| "__builtin_ia32_vfmaddsubpd" => {
if let Some(original_function_name) = original_function_name {
match &**original_function_name {
"llvm.x86.fma.vfmsubadd.pd.256" | "llvm.x86.fma.vfmsubadd.ps" | "llvm.x86.fma.vfmsubadd.ps.256"
| "llvm.x86.fma.vfmsubadd.pd" => {
// NOTE: since both llvm.x86.fma.vfmsubadd.ps and llvm.x86.fma.vfmaddsub.ps maps to
// __builtin_ia32_vfmaddsubps, only add minus if this comes from a
// subadd LLVM intrinsic, e.g. _mm256_fmsubadd_pd.
let mut new_args = args.to_vec();
let arg3 = &mut new_args[2];
*arg3 = builder.context.new_unary_op(None, UnaryOp::Minus, arg3.get_type(), *arg3);
args = new_args.into();
},
_ => (),
}
}
},
"__builtin_ia32_ldmxcsr" => {
// The builtin __builtin_ia32_ldmxcsr takes an integer value while llvm.x86.sse.ldmxcsr takes a pointer,