intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-01-20 10:58:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Assume amdhsa triples support flat addressing, which matches
the backend logic for the default target. This fixes the
rocm device-libs build.
This commit is contained in:
Matt Arsenault
2025-12-02 19:11:30 -05:00
committed by GitHub
parent 9dd3346589
commit 9fd288e886
4 changed files with 21 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
clang/lib/Basic/Targets/AMDGPU.h
View File

@@ -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);
@@ -325,7 +337,7 @@ public:
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;
}

5
clang/test/CodeGenOpenCL/address-spaces.cl
View File

@@ -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

4
clang/test/CodeGenOpenCL/builtins-alloca.cl
View File

@@ -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(

3
clang/test/Misc/amdgcn.languageOptsOpenCL.cl
View File

@@ -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"