Skip to content

clang/AMDGPU: Enable opencl 2.0 features for unknown target #170308

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 2 commits into from
Dec 3, 2025
+27 −5
Merged

clang/AMDGPU: Enable opencl 2.0 features for unknown target #170308

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
afb198a
clang/AMDGPU: Add missing opencl feature macros
arsenm Dec 2, 2025
bab99b5
clang/AMDGPU: Enable opencl 2.0 features for unknown target
arsenm Dec 2, 2025
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
16 changes: 15 additions & 1 deletion clang/lib/Basic/Targets/AMDGPU.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,18 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
return TT.getArch() == llvm::Triple::r600;
}

bool hasFlatSupport() const {
if (GPUKind >= llvm::AMDGPU::GK_GFX700)
return true;

// Dummy target is assumed to be gfx700+ for amdhsa.
if (GPUKind == llvm::AMDGPU::GK_NONE &&
getTriple().getOS() == llvm::Triple::AMDHSA)
return true;

return false;
}

public:
AMDGPUTargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts);

Expand Down Expand Up @@ -316,14 +328,16 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
Opts["cl_amd_media_ops"] = true;
Opts["cl_amd_media_ops2"] = true;

// FIXME: Check subtarget for image support.
Opts["__opencl_c_images"] = true;
Opts["__opencl_c_3d_image_writes"] = true;
Opts["__opencl_c_read_write_images"] = true;
Opts["cl_khr_3d_image_writes"] = true;
Opts["__opencl_c_program_scope_global_variables"] = true;
Opts["__opencl_c_atomic_order_seq_cst"] = true;
Opts["__opencl_c_atomic_scope_all_devices"] = true;

if (GPUKind >= llvm::AMDGPU::GK_GFX700) {
if (hasFlatSupport()) {
Opts["__opencl_c_generic_address_space"] = true;
Opts["__opencl_c_device_enqueue"] = true;
}
Expand Down
5 changes: 3 additions & 2 deletions clang/test/CodeGenOpenCL/address-spaces.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,10 @@
// RUN: %clang_cc1 %s -O0 -cl-std=CL3.0 -cl-ext=-all -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,SPIR
// RUN: %clang_cc1 %s -O0 -cl-std=clc++2021 -cl-ext=-all -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,SPIR
// RUN: %clang_cc1 %s -O0 -DCL20 -cl-std=CL2.0 -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20SPIR
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa -emit-llvm -o - | FileCheck --check-prefixes=CHECK,AMDGCN %s
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa -cl-std=CL3.0 -emit-llvm -o - | FileCheck --check-prefixes=CHECK,AMDGCN %s
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-mesa3d -emit-llvm -o - | FileCheck --check-prefixes=CHECK,AMDGCN %s
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-mesa3d -cl-std=CL3.0 -emit-llvm -o - | FileCheck --check-prefixes=CHECK,AMDGCN %s
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa -DCL20 -cl-std=CL2.0 -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20AMDGCN
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa -DCL20 -cl-std=CL3.0 -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20AMDGCN
// RUN: %clang_cc1 %s -O0 -triple amdgcn-mesa-mesa3d -emit-llvm -o - | FileCheck --check-prefixes=CHECK,AMDGCN %s
// RUN: %clang_cc1 %s -O0 -triple amdgcn-mesa-mesa3d -cl-std=CL3.0 -emit-llvm -o - | FileCheck --check-prefixes=CHECK,AMDGCN %s
// RUN: %clang_cc1 %s -O0 -triple r600-- -emit-llvm -o - | FileCheck --check-prefixes=CHECK,AMDGCN %s
Expand Down
4 changes: 2 additions & 2 deletions clang/test/CodeGenOpenCL/builtins-alloca.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,9 @@
// RUN: -emit-llvm -o - | FileCheck --check-prefixes=OPENCL12 %s
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa -cl-std=CL2.0 \
// RUN: -emit-llvm -o - | FileCheck --check-prefixes=OPENCL20 %s
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa -cl-std=CL3.0 \
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-mesa3d -target-cpu gfx600 -cl-std=CL3.0 \
// RUN: -emit-llvm -o - | FileCheck --check-prefixes=OPENCL30 %s
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa -cl-std=CL3.0 -cl-ext=+__opencl_c_generic_address_space \
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa -cl-std=CL3.0 \
// RUN: -emit-llvm -o - | FileCheck --check-prefixes=OPENCL30GAS %s

// OPENCL-LABEL: define dso_local void @test1_builtin_alloca(
Expand Down
7 changes: 7 additions & 0 deletions clang/test/Misc/amdgcn.languageOptsOpenCL.cl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,9 @@
// RUN: %clang_cc1 -x cl -cl-std=CL3.0 %s -verify -triple amdgcn-unknown-unknown -Wpedantic-core-features -DTEST_CORE_FEATURES
// RUN: %clang_cc1 -x cl -cl-std=CL3.0 %s -verify -triple amdgcn-unknown-unknown -target-cpu gfx700 -Wpedantic-core-features -DTEST_CORE_FEATURES -DFLAT_SUPPORT

// Test none target with amdhsa triple, which implies >= gfx700
// RUN: %clang_cc1 -x cl -cl-std=CL3.0 %s -verify -triple amdgcn-unknown-amdhsa -Wpedantic-core-features -DTEST_CORE_FEATURES -DFLAT_SUPPORT

// Extensions in all versions
#ifndef cl_clang_storage_class_specifiers
#error "Missing cl_clang_storage_class_specifiers define"
Expand Down Expand Up @@ -162,6 +165,10 @@
#ifndef __opencl_c_program_scope_global_variables
#error "Missing __opencl_c_program_scope_global_variables define"
#endif

#ifndef __opencl_c_read_write_images
#error "Missing __opencl_c_read_write_images define"
#endif
#endif

#if (__OPENCL_C_VERSION__ >= 300)
Expand Down
Loading