Merge branch 'sycl' into sycl-devops-pr/udit/oclcpu_test_precommit

intel · Jan 8, 2025 · 0d58a35 · 0d58a35
2 parents f647b20 + e9822b2
commit 0d58a35
Show file tree

Hide file tree

Showing 77 changed files with 1,730 additions and 847 deletions.
diff --git a/.github/workflows/sycl-linux-precommit.yml b/.github/workflows/sycl-linux-precommit.yml
@@ -143,27 +143,27 @@ jobs:
             image_options: -u 1001 --device=/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --privileged --cap-add SYS_ADMIN
             target_devices: level_zero:gpu;opencl:gpu
             reset_intel_gpu: true
-            extra_lit_opts: --param matrix-xmx8=True --param gpu-intel-dg2=True
+            extra_lit_opts: --param matrix-xmx8=True
             env: '{"LIT_FILTER":${{ needs.determine_arc_tests.outputs.arc_tests }} }'
           - name: E2E tests with dev igc on Intel Arc A-Series Graphics
             runner: '["Linux", "arc"]'
             image: ghcr.io/intel/llvm/ubuntu2404_intel_drivers:devigc
             image_options: -u 1001 --device=/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --privileged --cap-add SYS_ADMIN
             target_devices: level_zero:gpu;opencl:gpu
             reset_intel_gpu: true
-            extra_lit_opts: --param matrix-xmx8=True --param gpu-intel-dg2=True
+            extra_lit_opts: --param matrix-xmx8=True
             env: '{"LIT_FILTER":${{ needs.determine_arc_tests.outputs.arc_tests }} }'
             use_igc_dev: true
           - name: E2E tests on Intel Ponte Vecchio GPU
             runner: '["Linux", "pvc"]'
             image: ghcr.io/intel/llvm/ubuntu2404_intel_drivers:latest
-            image_options: -u 1001 --device=/dev/dri --privileged --cap-add SYS_ADMIN
+            image_options: -u 1001 --device=/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --privileged --cap-add SYS_ADMIN
             target_devices: level_zero:gpu;opencl:gpu;opencl:cpu
             extra_lit_opts: -j 50
           - name: E2E tests with dev igc on Intel Ponte Vecchio GPU
             runner: '["Linux", "pvc"]'
             image: ghcr.io/intel/llvm/ubuntu2404_intel_drivers:devigc
-            image_options: -u 1001 --device=/dev/dri --privileged --cap-add SYS_ADMIN
+            image_options: -u 1001 --device=/dev/dri -v /dev/dri/by-path:/dev/dri/by-path --privileged --cap-add SYS_ADMIN
             target_devices: level_zero:gpu;opencl:gpu
             use_igc_dev: true
             extra_lit_opts: -j 50

diff --git a/.github/workflows/sycl-linux-run-tests.yml b/.github/workflows/sycl-linux-run-tests.yml
@@ -189,6 +189,7 @@ on:
 
 permissions:
   contents: read
+  packages: read
 
 jobs:
   run:

diff --git a/.github/workflows/sycl-nightly.yml b/.github/workflows/sycl-nightly.yml
@@ -58,7 +58,6 @@ jobs:
             target_devices: level_zero:gpu
             reset_intel_gpu: true
             tests_selector: e2e
-            extra_lit_opts: --param gpu-intel-gen12=True
 
           - name: Intel OCL GPU
             runner: '["Linux", "gen12"]'
@@ -67,7 +66,6 @@ jobs:
             target_devices: opencl:gpu
             reset_intel_gpu: true
             tests_selector: e2e
-            extra_lit_opts: --param gpu-intel-gen12=True
 
           - name: OCL CPU (AMD)
             runner: '["Linux", "amdgpu"]'
@@ -126,7 +124,6 @@ jobs:
       name: Intel GEN12 Graphics with Level Zero
       runner: '["Windows","gen12"]'
       sycl_toolchain_archive: ${{ needs.build-win.outputs.artifact_archive_name }}
-      extra_lit_opts: --param gpu-intel-gen12=True
 
   cuda-aws-start:
     needs: [ubuntu2204_build]
@@ -237,9 +234,7 @@ jobs:
           echo "TAG=$(date +'%Y-%m-%d')-${GITHUB_SHA::7}" >> "$GITHUB_OUTPUT"
         fi
     - name: Upload binaries
-      # v2.2.0 of the action is broken.
-      # https://github.com/softprops/action-gh-release/issues/556
-      uses: softprops/[email protected]
+      uses: softprops/[email protected]
       with:
         files: |
           sycl_linux.tar.gz

diff --git a/.github/workflows/sycl-post-commit.yml b/.github/workflows/sycl-post-commit.yml
@@ -47,12 +47,11 @@ jobs:
         include:
           - name: Intel GEN12 Graphics with Level Zero
             runner: '["Linux", "gen12"]'
-            extra_lit_opts: --param gpu-intel-gen12=True
             target_devices: level_zero:gpu;opencl:fpga
             reset_intel_gpu: true
           - name: Intel Arc A-Series Graphics with Level Zero
             runner: '["Linux", "arc"]'
-            extra_lit_opts: --param matrix-xmx8=True --param gpu-intel-dg2=True
+            extra_lit_opts: --param matrix-xmx8=True
             reset_intel_gpu: true
           - name: AMD/HIP
             runner: '["Linux", "amdgpu"]'
@@ -69,7 +68,7 @@ jobs:
           - name: Perf tests on Intel GEN12 Graphics system
             runner: '["Linux", "gen12"]'
             env: '{"LIT_FILTER":"PerformanceTests/"}'
-            extra_lit_opts: -a -j 1 --param enable-perf-tests=True --param gpu-intel-gen12=True
+            extra_lit_opts: -a -j 1 --param enable-perf-tests=True
             target_devices: all
             reset_intel_gpu: true
           - name: Perf tests on Intel Arc A-Series Graphics system
@@ -120,7 +119,6 @@ jobs:
       name: Intel GEN12 Graphics with Level Zero
       runner: '["Windows","gen12"]'
       sycl_toolchain_archive: ${{ needs.build-win.outputs.artifact_archive_name }}
-      extra_lit_opts: --param gpu-intel-gen12=True
       compiler: icx
 
   macos_default:

diff --git a/.github/workflows/sycl-rel-nightly.yml b/.github/workflows/sycl-rel-nightly.yml
@@ -19,7 +19,7 @@ jobs:
     steps:
     - uses: actions/checkout@v4
       with:
-        ref: draft-sycl-rel-6_0_0
+        ref: sycl-rel-6_0_0
     - run: git show --quiet | tee -a $GITHUB_STEP_SUMMARY
 
     - id: is_new_commit
@@ -39,7 +39,7 @@ jobs:
       build_artifact_suffix: v6
       build_configure_extra_args: '--hip --cuda'
       merge_ref: ''
-      ref: draft-sycl-rel-6_0_0
+      ref: sycl-rel-6_0_0
 
       # We upload the build for people to download/use, override its name and
       # prefer widespread gzip compression.
@@ -107,7 +107,7 @@ jobs:
       tests_selector: ${{ matrix.tests_selector }}
       extra_lit_opts: ${{ matrix.extra_lit_opts }}
       reset_intel_gpu: ${{ matrix.reset_intel_gpu }}
-      ref: draft-sycl-rel-6_0_0
+      ref: sycl-rel-6_0_0
       merge_ref: ''
       sycl_toolchain_artifact: sycl_linux_default
       sycl_toolchain_archive: ${{ needs.ubuntu2204_build.outputs.artifact_archive_name }}
@@ -121,7 +121,7 @@ jobs:
       # We upload both Linux/Windows build via Github's "Releases"
       # functionality, make sure Linux/Windows names follow the same pattern.
       artifact_archive_name: sycl_windows.tar.gz
-      build_ref: draft-sycl-rel-6_0_0
+      build_ref: sycl-rel-6_0_0
 
   e2e-win:
     needs: build-win
@@ -136,7 +136,7 @@ jobs:
       runner: '["Windows","gen12"]'
       sycl_toolchain_archive: ${{ needs.build-win.outputs.artifact_archive_name }}
       extra_lit_opts: --param gpu-intel-gen12=True
-      ref: draft-sycl-rel-6_0_0
+      ref: sycl-rel-6_0_0
 
   cuda-aws-start:
     needs: [ubuntu2204_build]
@@ -145,7 +145,7 @@ jobs:
     secrets: inherit
     with:
       mode: start
-      ref: draft-sycl-rel-6_0_0
+      ref: sycl-rel-6_0_0
 
   cuda-run-tests:
     needs: [ubuntu2204_build, cuda-aws-start]
@@ -157,7 +157,7 @@ jobs:
       image: ghcr.io/intel/llvm/ubuntu2204_build:latest-0300ac924620a51f76c4929794637b82790f12ab
       image_options: -u 1001 --gpus all --cap-add SYS_ADMIN --env NVIDIA_DISABLE_REQUIRE=1
       target_devices: cuda:gpu
-      ref: draft-sycl-rel-6_0_0
+      ref: sycl-rel-6_0_0
       merge_ref: ''
 
       sycl_toolchain_artifact: sycl_linux_default
@@ -171,4 +171,4 @@ jobs:
     secrets: inherit
     with:
       mode: stop
-      ref: draft-sycl-rel-6_0_0
+      ref: sycl-rel-6_0_0
diff --git a/.github/workflows/sycl-windows-precommit.yml b/.github/workflows/sycl-windows-precommit.yml
@@ -55,4 +55,3 @@ jobs:
       name: Intel GEN12 Graphics with Level Zero
       runner: '["Windows","gen12"]'
       sycl_toolchain_archive: ${{ needs.build.outputs.artifact_archive_name }}
-      extra_lit_opts: --param gpu-intel-gen12=True
diff --git a/README.md b/README.md
@@ -46,10 +46,10 @@ Project documentation is available at:
 
 ### How to use DPC++
 
-#### Docker containers
+#### Dockerfiles
 
-See available containers with pre-built/pre-installed DPC++ compiler at:
-[Containers](./sycl/doc/developer/DockerBKMs.md#sycl-containers-overview)
+See available Dockerfiles to create containers with pre-built/pre-installed DPC++ compiler at:
+[Containers](./sycl/doc/developer/DockerBKMs.md#sycl-dockerfiles-overview)
 
 #### Releases
 

diff --git a/SECURITY.md b/SECURITY.md
@@ -1,5 +1,17 @@
-# Reporting LLVM Security Issues
+# Security Policy
 
-To report security issues in LLVM, please follow the steps outlined on the
-[LLVM Security Group](https://llvm.org/docs/Security.html#how-to-report-a-security-issue)
-page.
+Intel is committed to rapidly addressing security vulnerabilities affecting our
+customers and providing clear guidance on the solution, impact, severity and
+mitigation.
+
+## Reporting a Vulnerability
+
+`intel/llvm` project is based upon the upstream
+[`llvm/llvm-project`](https://github.com/llvm/llvm-project) and leverages lots
+of functionality provided by it. If an issue you found concerns functionality
+which is available in upstream, then it is more efficient to directly report it
+there, see corresponding `SECURITY.md` for their policy.
+
+If you are unsure, or if you know that the issue is specific to additions
+developed in `intel/llvm`, then please report any security vulnerabilities
+[utilizing the guidelines here](https://www.intel.com/content/www/us/en/security-center/vulnerability-handling-guidelines.html).
diff --git a/clang/include/clang/Driver/ToolChain.h b/clang/include/clang/Driver/ToolChain.h
@@ -377,9 +377,9 @@ class ToolChain {
     return nullptr;
   }
 
-  /// TranslateOffloadTargetArgs - Create a new derived argument list for
-  /// that contains the Offload target specific flags passed via
-  /// -Xopenmp-target -opt=val OR -Xopenmp-target=<triple> -opt=val
+  /// TranslateOffloadTargetArgs - Create a new derived argument list that
+  /// contains the Offload target specific flags passed via -Xopenmp-target
+  /// -opt=val OR -Xopenmp-target=<triple> -opt=val
   /// Also handles -Xsycl-target OR -Xsycl-target=<triple>
   virtual llvm::opt::DerivedArgList *TranslateOffloadTargetArgs(
       const llvm::opt::DerivedArgList &Args, bool SameTripleAsHost,

diff --git a/clang/lib/Driver/ToolChain.cpp b/clang/lib/Driver/ToolChain.cpp
@@ -1640,6 +1640,8 @@ llvm::opt::DerivedArgList *ToolChain::TranslateOffloadTargetArgs(
   DerivedArgList *DAL = new DerivedArgList(Args.getBaseArgs());
   const OptTable &Opts = getDriver().getOpts();
   bool Modified = false;
+  auto &Triple = getTriple();
+  const bool IsSYCL = DeviceOffloadKind == Action::OFK_SYCL;
 
   // Handle -Xopenmp-target and -Xsycl-target-frontend flags
   for (auto *A : Args) {
@@ -1654,13 +1656,15 @@ llvm::opt::DerivedArgList *ToolChain::TranslateOffloadTargetArgs(
       // to correctly set metadata in intermediate files.
       if (SameTripleAsHost ||
           A->getOption().matches(options::OPT_mcode_object_version_EQ) ||
-          (getTriple().getArch() == llvm::Triple::amdgcn &&
-           DeviceOffloadKind != Action::OFK_SYCL)) {
+          (Triple.getArch() == llvm::Triple::amdgcn && !IsSYCL)) {
         DAL->append(A);
         continue;
       }
-      // SPIR/SPIR-V special case for -mlong-double
-      if (getTriple().isSPIROrSPIRV() &&
+      // SPIR/SPIR-V and SYCL GPU special case for -mlong-double. We have to
+      // make sure that if user requested 64bit long double it is honored on
+      // both host and device.
+      if ((Triple.isSPIROrSPIRV() ||
+           (IsSYCL && (Triple.isAMDGCN() || Triple.isNVPTX()))) &&
           A->getOption().matches(options::OPT_LongDouble_Group)) {
         DAL->append(A);
         continue;
@@ -1683,7 +1687,7 @@ llvm::opt::DerivedArgList *ToolChain::TranslateOffloadTargetArgs(
     // is similar, can be improved
     if (DeviceOffloadKind == Action::OFK_OpenMP) {
       XOffloadTargetNoTriple =
-        A->getOption().matches(options::OPT_Xopenmp_target);
+          A->getOption().matches(options::OPT_Xopenmp_target);
       if (A->getOption().matches(options::OPT_Xopenmp_target_EQ)) {
         llvm::Triple TT(getOpenMPTriple(A->getValue(0)));
 
@@ -1699,12 +1703,12 @@ llvm::opt::DerivedArgList *ToolChain::TranslateOffloadTargetArgs(
         DAL->append(A);
         continue;
       }
-    } else if (DeviceOffloadKind == Action::OFK_SYCL) {
+    } else if (IsSYCL) {
       XOffloadTargetNoTriple =
-        A->getOption().matches(options::OPT_Xsycl_frontend);
+          A->getOption().matches(options::OPT_Xsycl_frontend);
       if (A->getOption().matches(options::OPT_Xsycl_frontend_EQ)) {
         // Passing device args: -Xsycl-target-frontend=<triple> -opt=val.
-        if (getDriver().getSYCLDeviceTriple(A->getValue(0)) == getTriple())
+        if (getDriver().getSYCLDeviceTriple(A->getValue(0)) == Triple)
           Index = Args.getBaseArgs().MakeIndex(A->getValue(1));
         else
           continue;
@@ -1744,8 +1748,7 @@ llvm::opt::DerivedArgList *ToolChain::TranslateOffloadTargetArgs(
         getDriver().Diag(diag::err_drv_Xopenmp_target_missing_triple);
         continue;
       }
-      if (DeviceOffloadKind == Action::OFK_SYCL &&
-          !SingleTargetTripleCount(options::OPT_fsycl_targets_EQ)) {
+      if (IsSYCL && !SingleTargetTripleCount(options::OPT_fsycl_targets_EQ)) {
         getDriver().Diag(diag::err_drv_Xsycl_target_missing_triple)
             << A->getSpelling();
         continue;

diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -6751,6 +6751,11 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
              (A->getOption().getID() == options::OPT_mlong_double_64))
       // Only allow for -mlong-double-64 for SPIR/SPIR-V
       A->render(Args, CmdArgs);
+    else if ((IsSYCL &&
+              (TC.getTriple().isAMDGCN() || TC.getTriple().isNVPTX())) &&
+             (A->getOption().getID() == options::OPT_mlong_double_64))
+      // similarly, allow 64bit long double for SYCL GPU targets
+      A->render(Args, CmdArgs);
     else if (TC.getTriple().isPPC() &&
              (A->getOption().getID() != options::OPT_mlong_double_80))
       A->render(Args, CmdArgs);
@@ -10246,7 +10251,11 @@ void OffloadWrapper::ConstructJob(Compilation &C, const JobAction &JA,
     WrapperArgs.push_back(C.getArgs().MakeArgString(OutOpt));
 
     SmallString<128> HostTripleOpt("-host=");
-    HostTripleOpt += getToolChain().getAuxTriple()->str();
+    const ToolChain *HostTC = C.getSingleOffloadToolChain<Action::OFK_Host>();
+    // Use the Effective Triple to match the expected triple when using the
+    // clang compiler to compile the wrapped binary.
+    std::string HostTripleStr = HostTC->ComputeEffectiveClangTriple(TCArgs);
+    HostTripleOpt += HostTripleStr;
     WrapperArgs.push_back(C.getArgs().MakeArgString(HostTripleOpt));
 
     llvm::Triple TT = getToolChain().getTriple();
@@ -10375,9 +10384,9 @@ void OffloadWrapper::ConstructJob(Compilation &C, const JobAction &JA,
 
     if (WrapperCompileEnabled) {
       // TODO Use TC.SelectTool().
-      ArgStringList ClangArgs{
-          TCArgs.MakeArgString("--target=" + TC.getAuxTriple()->str()), "-c",
-          "-o", Output.getFilename(), WrapperFileName};
+      ArgStringList ClangArgs{TCArgs.MakeArgString("--target=" + HostTripleStr),
+                              "-c", "-o", Output.getFilename(),
+                              WrapperFileName};
       llvm::Reloc::Model RelocationModel;
       unsigned PICLevel;
       bool IsPIE;

diff --git a/clang/test/Driver/mlong-double-128.c b/clang/test/Driver/mlong-double-128.c
@@ -12,8 +12,16 @@
 // RUN: not %clang --target=powerpc -c -### %s -mlong-double-80 2>&1 | FileCheck --check-prefix=ERR2 %s
 // RUN: not %clang --target=spir64-unknown-unknown -c -### %s -mlong-double-128 2>&1 | FileCheck --check-prefix=ERR3 %s
 // RUN: not %clang --target=spir64-unknown-unknown -c -### %s -mlong-double-80 2>&1 | FileCheck --check-prefix=ERR4 %s
+// RUN: not %clang --target=nvptx64-nvidia-cuda -c -### %s -mlong-double-128 2>&1 | FileCheck --check-prefix=ERR5 %s
+// RUN: not %clang --target=nvptx64-nvidia-cuda -c -### %s -mlong-double-80 2>&1 | FileCheck --check-prefix=ERR6 %s
+// RUN: not %clang --target=amd_gpu_gfx1031 -c -### %s -mlong-double-128 2>&1 | FileCheck --check-prefix=ERR7 %s
+// RUN: not %clang --target=amd_gpu_gfx1031 -c -### %s -mlong-double-80 2>&1 | FileCheck --check-prefix=ERR8 %s
 
 // ERR: error: unsupported option '-mlong-double-128' for target 'aarch64'
 // ERR2: error: unsupported option '-mlong-double-80' for target 'powerpc'
 // ERR3: error: unsupported option '-mlong-double-128' for target 'spir64-unknown-unknown'
 // ERR4: error: unsupported option '-mlong-double-80' for target 'spir64-unknown-unknown'
+// ERR5: error: unsupported option '-mlong-double-128' for target 'nvptx64-nvidia-cuda'
+// ERR6: error: unsupported option '-mlong-double-80' for target 'nvptx64-nvidia-cuda'
+// ERR7: error: unsupported option '-mlong-double-128' for target 'amd_gpu_gfx1031'
+// ERR8: error: unsupported option '-mlong-double-80' for target 'amd_gpu_gfx1031'
diff --git a/clang/test/Driver/sycl-mlong-double.cpp b/clang/test/Driver/sycl-mlong-double.cpp
@@ -5,11 +5,27 @@
 // CHECK: clang{{.*}} "-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME:  "-mlong-double-64"
 
-/// -mlong-double-128 and -mlong-double-80 are not supported for spir64.
+/// -mlong-double-128 and -mlong-double-80 are not supported for spir64, or SYCL GPU targets.
 // RUN: not %clangxx -c -fsycl -mlong-double-128 -target x86_64-unknown-linux-gnu %s -### 2>&1 | FileCheck --check-prefix=CHECK-128 %s
 // CHECK-128: error: unsupported option '-mlong-double-128' for target 'spir64-unknown-unknown'
 // CHECK-128-NOT: clang{{.*}} "-triple" "-spir64-unknown-unknown" {{.*}} "-mlong-double-128"
 
 // RUN: not %clangxx -c -fsycl -mlong-double-80 -target x86_64-unknown-linux-gnu %s -### 2>&1 | FileCheck --check-prefix=CHECK-80 %s
 // CHECK-80: error: unsupported option '-mlong-double-80' for target 'spir64-unknown-unknown'
 // CHECK-80-NOT: clang{{.*}} "-triple" "-spir64-unknown-unknown" {{.*}} "-mlong-double-80"
+
+// RUN: not %clangxx -c -fsycl -mlong-double-128 --target=x86_64-unknown-linux-gnu -fsycl-targets=amd_gpu_gfx1031 %s -### 2>&1 | FileCheck --check-prefix=CHECK-128-AMD %s
+// CHECK-128-AMD: error: unsupported option '-mlong-double-128' for target 'amdgcn-amd-amdhsa'
+// CHECK-128-AMD-NOT: clang{{.*}} "-triple" "-amd_gpu_gfx1031" {{.*}} "-mlong-double-128"
+
+// RUN: not %clangxx -c -fsycl -mlong-double-80 --target=x86_64-unknown-linux-gnu -fsycl-targets=amd_gpu_gfx1031 %s -### 2>&1 | FileCheck --check-prefix=CHECK-80-AMD %s
+// CHECK-80-AMD: error: unsupported option '-mlong-double-80' for target 'amdgcn-amd-amdhsa'
+// CHECK-80-AMD-NOT: clang{{.*}} "-triple" "-amd_gpu_gfx1031" {{.*}} "-mlong-double-80"
+
+// RUN: not %clangxx -c -fsycl -mlong-double-128 --target=x86_64-unknown-linux-gnu -fsycl-targets=nvptx64-nvidia-cuda %s -### 2>&1 | FileCheck --check-prefix=CHECK-128-NVPTX %s
+// CHECK-128-NVPTX: error: unsupported option '-mlong-double-128' for target 'nvptx64-nvidia-cuda'
+// CHECK-128-NVPTX-NOT: clang{{.*}} "-triple" "-nvptx64-nvidia-cuda" {{.*}} "-mlong-double-128"
+
+// RUN: not %clangxx -c -fsycl -mlong-double-80 --target=x86_64-unknown-linux-gnu -fsycl-targets=nvptx64-nvidia-cuda %s -### 2>&1 | FileCheck --check-prefix=CHECK-80-NVPTX %s
+// CHECK-80-NVPTX: error: unsupported option '-mlong-double-80' for target 'nvptx64-nvidia-cuda'
+// CHECK-80-NVPTX-NOT: clang{{.*}} "-triple" "-nvptx64-nvidia-cuda" {{.*}} "-mlong-double-80"
diff --git a/clang/test/Driver/sycl-offload-aot.cpp b/clang/test/Driver/sycl-offload-aot.cpp
@@ -153,10 +153,10 @@
 // CHK-TOOLS-GEN: ocloc{{.*}} "-output" "[[OUTPUT4_T:.+\.out]]" {{.*}} "[[OUTPUT3_T]]"
 // CHK-TOOLS-CPU: opencl-aot{{.*}} "-o=[[OUTPUT4_T:.+\.out]]" {{.*}} "[[OUTPUT3_T]]"
 // CHK-TOOLS-AOT: file-table-tform{{.*}} "-o" "[[OUTPUT4:.+\.table]]" "{{.*}}.table"{{.*}} "[[OUTPUT4_T]]"
-// CHK-TOOLS-FPGA: clang-offload-wrapper{{.*}} "-o=[[OUTPUT5:.+\.bc]]" "-host=x86_64-unknown-linux-gnu" "-target=spir64_fpga{{.*}}" "-kind=sycl" "-batch" "[[OUTPUT4]]"
-// CHK-TOOLS-GEN: clang-offload-wrapper{{.*}} "-o=[[OUTPUT5:.+\.bc]]" "-host=x86_64-unknown-linux-gnu" "-target=spir64_gen{{.*}}" "-kind=sycl" "-batch" "[[OUTPUT4]]"
-// CHK-TOOLS-CPU: clang-offload-wrapper{{.*}} "-o=[[OUTPUT5:.+\.bc]]" "-host=x86_64-unknown-linux-gnu" "-target=spir64_x86_64{{.*}}" "-kind=sycl" "-batch" "[[OUTPUT4]]"
-// CHK-TOOLS-AOT: clang{{.*}} "-c" "-o" "[[OUTPUT6:.+\.o]]" "[[OUTPUT5]]"
+// CHK-TOOLS-FPGA: clang-offload-wrapper{{.*}} "-o=[[OUTPUT5:.+\.bc]]" "-host=[[HOST_TARGET:.+]]" "-target=spir64_fpga{{.*}}" "-kind=sycl" "-batch" "[[OUTPUT4]]"
+// CHK-TOOLS-GEN: clang-offload-wrapper{{.*}} "-o=[[OUTPUT5:.+\.bc]]" "-host=[[HOST_TARGET:.+]]" "-target=spir64_gen{{.*}}" "-kind=sycl" "-batch" "[[OUTPUT4]]"
+// CHK-TOOLS-CPU: clang-offload-wrapper{{.*}} "-o=[[OUTPUT5:.+\.bc]]" "-host=[[HOST_TARGET:.+]]" "-target=spir64_x86_64{{.*}}" "-kind=sycl" "-batch" "[[OUTPUT4]]"
+// CHK-TOOLS-AOT: clang{{.*}} "--target=[[HOST_TARGET]]" "-c" "-o" "[[OUTPUT6:.+\.o]]" "[[OUTPUT5]]"
 // CHK-TOOLS-AOT: ld{{.*}} "[[OUTPUT7]]" "[[OUTPUT6]]" {{.*}} "-lsycl"
 
 // Check to be sure that for windows, the 'exe' tools are called
-Original file line number
+Diff line change
@@ Expand Up / @@ -189,6 +189,7 @@ on: @@
     permissions:
       contents: read
+      packages: read
     jobs:
       run:
@@ Expand Down @@