Skip to content

[clang][AMDGPU][CUDA] Handle __builtin_printf for device printf #68515

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
Feb 5, 2024
Merged

[clang][AMDGPU][CUDA] Handle __builtin_printf for device printf #68515

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 clang/lib/CodeGen/CGBuiltin.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5710,6 +5710,7 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
Value *HalfVal = Builder.CreateLoad(Address);
return RValue::get(Builder.CreateFPExt(HalfVal, Builder.getFloatTy()));
}
case Builtin::BI__builtin_printf:
case Builtin::BIprintf:
if (getTarget().getTriple().isNVPTX() ||
getTarget().getTriple().isAMDGCN()) {
Expand Down
3 changes: 2 additions & 1 deletion clang/lib/CodeGen/CGGPUBuiltin.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,8 @@ RValue EmitDevicePrintfCallExpr(const CallExpr *E, CodeGenFunction *CGF,
llvm::Function *Decl, bool WithSizeArg) {
CodeGenModule &CGM = CGF->CGM;
CGBuilderTy &Builder = CGF->Builder;
assert(E->getBuiltinCallee() == Builtin::BIprintf);
assert(E->getBuiltinCallee() == Builtin::BIprintf ||
E->getBuiltinCallee() == Builtin::BI__builtin_printf);
assert(E->getNumArgs() >= 1); // printf always has at least one arg.

// Uses the same format as nvptx for the argument packing, but also passes
Expand Down
21 changes: 21 additions & 0 deletions clang/test/CodeGenCUDA/printf-builtin.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
// REQUIRES: x86-registered-target
// REQUIRES: nvptx-registered-target
// RUN: %clang_cc1 -triple nvptx64-nvidia-cuda -emit-llvm -disable-llvm-optzns -fno-builtin-printf -fcuda-is-device \
// RUN: -o - %s | FileCheck %s

#define __device__ __attribute__((device))

extern "C" __device__ int printf(const char *format, ...);

// CHECK-LABEL: @_Z4foo1v()
__device__ int foo1() {
// CHECK: call i32 @vprintf
// CHECK-NOT: call i32 (ptr, ...) @printf
return __builtin_printf("Hello World\n");
}

// CHECK-LABEL: @_Z4foo2v()
__device__ int foo2() {
// CHECK: call i32 (ptr, ...) @printf
return printf("Hello World\n");
}
23 changes: 23 additions & 0 deletions clang/test/CodeGenHIP/printf-builtin.hip
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -emit-llvm -disable-llvm-optzns -mprintf-kind=hostcall -fno-builtin-printf -fcuda-is-device \
// RUN: -o - %s | FileCheck --check-prefixes=CHECK,HOSTCALL %s
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -emit-llvm -disable-llvm-optzns -mprintf-kind=buffered -fno-builtin-printf -fcuda-is-device \
// RUN: -o - %s | FileCheck --check-prefixes=CHECK,BUFFERED %s

#define __device__ __attribute__((device))

extern "C" __device__ int printf(const char *format, ...);

// CHECK-LABEL: @_Z4foo1v()
__device__ int foo1() {
// HOSTCALL: call i64 @__ockl_printf_begin
// BUFFERED: call ptr addrspace(1) @__printf_alloc
// CHECK-NOT: call i32 (ptr, ...) @printf
return __builtin_printf("Hello World\n");
}

// CHECK-LABEL: @_Z4foo2v()
__device__ int foo2() {
// CHECK: call i32 (ptr, ...) @printf
return printf("Hello World\n");
}