Skip to content

[flang][cuda] Lower globaltimer to NVVM op #149217

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
merged 1 commit into from
Jul 17, 2025
Merged

[flang][cuda] Lower globaltimer to NVVM op #149217

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions flang/include/flang/Optimizer/Builder/IntrinsicCall.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -282,6 +282,7 @@ struct IntrinsicLibrary {
llvm::ArrayRef<mlir::Value> args);
mlir::Value genGetUID(mlir::Type resultType,
llvm::ArrayRef<mlir::Value> args);
mlir::Value genGlobalTimer(mlir::Type, llvm::ArrayRef<mlir::Value>);
fir::ExtendedValue genHostnm(std::optional<mlir::Type> resultType,
llvm::ArrayRef<fir::ExtendedValue> args);
fir::ExtendedValue genIall(mlir::Type, llvm::ArrayRef<fir::ExtendedValue>);
Expand Down
8 changes: 8 additions & 0 deletions flang/lib/Optimizer/Builder/IntrinsicCall.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -503,6 +503,7 @@ static constexpr IntrinsicHandler handlers[]{
{"getgid", &I::genGetGID},
{"getpid", &I::genGetPID},
{"getuid", &I::genGetUID},
{"globaltimer", &I::genGlobalTimer, {}, /*isElemental=*/false},
{"hostnm",
&I::genHostnm,
{{{"c", asBox}, {"status", asAddr, handleDynamicOptional}}},
Expand Down Expand Up @@ -4319,6 +4320,13 @@ mlir::Value IntrinsicLibrary::genGetUID(mlir::Type resultType,
fir::runtime::genGetUID(builder, loc));
}

// GLOBALTIMER
mlir::Value IntrinsicLibrary::genGlobalTimer(mlir::Type resultType,
llvm::ArrayRef<mlir::Value> args) {
assert(args.size() == 0 && "globalTimer takes no args");
return builder.create<mlir::NVVM::GlobalTimerOp>(loc, resultType).getResult();
}

// GET_COMMAND_ARGUMENT
void IntrinsicLibrary::genGetCommandArgument(
llvm::ArrayRef<fir::ExtendedValue> args) {
Expand Down
5 changes: 5 additions & 0 deletions flang/module/cudadevice.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1613,6 +1613,11 @@ attributes(device,host) logical function on_device() bind(c)
end function
end interface

interface
attributes(device) integer(8) function globalTimer()
end function
end interface

contains

attributes(device) subroutine syncthreads()
Expand Down
3 changes: 3 additions & 0 deletions flang/test/Lower/CUDA/cuda-device-proc.cuf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,8 @@ attributes(global) subroutine devsub()
ai = atomicdec(ai, 1_4)

time = clock64()

time = globalTimer()
end

! CHECK-LABEL: func.func @_QPdevsub() attributes {cuf.proc_attr = #cuf.cuda_proc<global>}
Expand Down Expand Up @@ -83,6 +85,7 @@ end
! CHECK: %{{.*}} = llvm.atomicrmw udec_wrap %{{.*}}, %{{.*}} seq_cst : !llvm.ptr, i32

! CHECK: fir.call @llvm.nvvm.read.ptx.sreg.clock64()
! CHECK: %{{.*}} = nvvm.read.ptx.sreg.globaltimer : i64

subroutine host1()
integer, device :: a(32)
Expand Down
Loading