Skip to content

Fix LLVM 23 compatibility: replace removed NoNaNsFPMath/NoInfsFPMath TargetOptions fields #9029

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
alexreinking merged 3 commits into from
Mar 15, 2026
+19 −1
Merged

Fix LLVM 23 compatibility: replace removed NoNaNsFPMath/NoInfsFPMath TargetOptions fields #9029

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c34be88
Initial plan
Copilot Mar 15, 2026
96518b1
Fix LLVM 23 compatibility: guard NoNaNsFPMath usage with #if LLVM_VER…
Copilot Mar 15, 2026
bef5472
Add no-nans-fp-math/no-infs-fp-math function attrs as LLVM 23 replace…
Copilot Mar 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 12 additions & 1 deletion src/CodeGen_Internal.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -607,15 +607,16 @@ void get_target_options(const llvm::Module &module, llvm::TargetOptions &options
bool use_soft_float_abi = get_modflag_bool(module, "halide_use_soft_float_abi");
std::string mabi = get_modflag_string(module, "halide_mabi");

// FIXME: can this be migrated into `set_function_attributes_from_halide_target_options()`?
bool per_instruction_fast_math_flags = get_modflag_bool(module, "halide_per_instruction_fast_math_flags");

options = llvm::TargetOptions();
options.AllowFPOpFusion = per_instruction_fast_math_flags ? llvm::FPOpFusion::Strict : llvm::FPOpFusion::Fast;
#if LLVM_VERSION < 230
options.NoInfsFPMath = !per_instruction_fast_math_flags;
#endif
#if LLVM_VERSION < 230
options.NoNaNsFPMath = !per_instruction_fast_math_flags;
#endif
options.HonorSignDependentRoundingFPMathOption = !per_instruction_fast_math_flags;
options.NoZerosInBSS = false;
options.GuaranteedTailCallOpt = false;
Expand Down Expand Up @@ -720,6 +721,16 @@ void set_function_attributes_from_halide_target_options(llvm::Function &fn) {
fn.addFnAttr(llvm::Attribute::getWithVScaleRangeArgs(
module.getContext(), vscale_range, vscale_range));
}

// When not using per-instruction fast-math flags (i.e., the whole module
// is in fast-math mode), propagate the fast-math assumptions as function
// attributes. In LLVM 23+, NoNaNsFPMath and NoInfsFPMath were removed from
// TargetOptions in favor of these per-function attributes.
bool per_instruction_fast_math_flags = get_modflag_bool(module, "halide_per_instruction_fast_math_flags");
if (!per_instruction_fast_math_flags) {
fn.addFnAttr("no-nans-fp-math", "true");
Copy link
Copy Markdown
Member

@abadams abadams Mar 15, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This seems fishy. LLVM has been progressively removing these kinds of flags but I haven't seen us do this before. It's weird to have an LLVM API go from an enum to a magic string. Are you sure this is the correct fix?

fn.addFnAttr("no-infs-fp-math", "true");
}
}

void embed_bitcode(llvm::Module *M, const string &halide_command) {
Expand Down
7 changes: 7 additions & 0 deletions src/CodeGen_PTX_Dev.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,6 +230,11 @@ void CodeGen_PTX_Dev::init_module() {

module = get_initial_module_for_ptx_device(target, context);

// Propagate the strict-float flag as a module flag so that
// set_function_attributes_from_halide_target_options can read it.
module->addModuleFlag(llvm::Module::Warning, "halide_per_instruction_fast_math_flags",
CodeGen_GPU_Dev::any_strict_float ? 1 : 0);

struct Intrinsic {
const char *name;
Type ret_type;
Expand Down Expand Up @@ -631,7 +636,9 @@ vector<char> CodeGen_PTX_Dev::compile_to_src() {
#if LLVM_VERSION < 230
options.NoInfsFPMath = !CodeGen_GPU_Dev::any_strict_float;
#endif
#if LLVM_VERSION < 230
options.NoNaNsFPMath = !CodeGen_GPU_Dev::any_strict_float;
#endif
options.HonorSignDependentRoundingFPMathOption = !CodeGen_GPU_Dev::any_strict_float;
options.NoZerosInBSS = false;
options.GuaranteedTailCallOpt = false;
Expand Down
Loading