Merge branch 'intel:sycl' into pablo/graph_enqueue_functions

Author: reble

.github/workflows/sycl-containers.yaml

@@ -51,6 +51,13 @@ jobs:
             file: ubuntu2204_intel_drivers
             tag: unstable
             build_args: "use_latest=true"
+          - name: Build + Intel Drivers Ubuntu 22.04 Docker image
+            file: ubuntu2204_intel_drivers
+            tag: alldeps
+            build_args: |
+              base_image=ghcr.io/intel/llvm/ubuntu2204_build
+              base_tag=latest
+              use_latest=false
     steps:
       - name: Checkout
         uses: actions/checkout@v4

.github/workflows/sycl-linux-run-tests.yml

@@ -185,8 +185,8 @@ jobs:
       with:
         path: khronos_sycl_cts
         repository: 'KhronosGroup/SYCL-CTS'
-        ref: 'SYCL-2020'
-        default_branch: 'SYCL-2020'
+        ref: 'main'
+        default_branch: 'main'
         cache_path: "/__w/repo_cache/"
     - name: SYCL CTS GIT submodules init
       if: inputs.tests_selector == 'cts'

.gitignore

@@ -30,6 +30,9 @@
 /build*
 !buildbot
 
+#pulldown temp folder
+/spirv-patches-*
+
 #==============================================================================#
 # Explicit files to ignore (only matches one).
 #==============================================================================#

clang/lib/Driver/ToolChains/Clang.cpp

@@ -5194,7 +5194,10 @@ void Clang::ConstructHostCompilerJob(Compilation &C, const JobAction &JA,
   if (HostCompilerDefArg) {
     ExecPath = HostCompilerDefArg->getValue();
     if (!ExecPath.empty() && ExecPath == llvm::sys::path::stem(ExecPath))
-      ExecPath = TC.GetProgramPath(ExecPath.c_str());
+      // Use PATH to find executable passed in from -fsycl-host-compiler.
+      if (llvm::ErrorOr<std::string> Prog =
+              llvm::sys::findProgramByName(ExecPath))
+        ExecPath = *Prog;
   }
 
   // Add any user-specified arguments.

clang/lib/Driver/ToolChains/SYCL.cpp

@@ -1081,7 +1081,9 @@ static bool hasPVCDevice(const ArgStringList &CmdArgs, std::string &DevArg) {
       for (int HexVal : PVCDevices[I].HexValues) {
         int Value = 0;
         if (!SingleArg.getAsInteger(0, Value) && Value == HexVal) {
-          DevArg = SingleArg.str();
+          // TODO: Pass back the hex string to use for -device_options when
+          // IGC is updated to allow.  Currently -device_options only accepts
+          // the device ID (i.e. pvc) or the version (12.60.7).
           return true;
         }
       }
@@ -1502,18 +1504,13 @@ static void parseTargetOpts(StringRef ArgString, const llvm::opt::ArgList &Args,
 void SYCLToolChain::TranslateGPUTargetOpt(const llvm::opt::ArgList &Args,
                                           llvm::opt::ArgStringList &CmdArgs,
                                           OptSpecifier Opt_EQ) const {
-  for (auto *A : Args) {
-    if (A->getOption().matches(Opt_EQ)) {
-      if (auto GpuDevice =
-              tools::SYCL::gen::isGPUTarget<tools::SYCL::gen::AmdGPU>(
-                  A->getValue())) {
-        StringRef ArgString;
-        SmallString<64> OffloadArch("--offload-arch=");
-        OffloadArch += GpuDevice->data();
-        ArgString = OffloadArch;
-        parseTargetOpts(ArgString, Args, CmdArgs);
-        A->claim();
-      }
+  if (const Arg *TargetArg = Args.getLastArg(Opt_EQ)) {
+    StringRef Val = TargetArg->getValue();
+    if (auto GpuDevice =
+            tools::SYCL::gen::isGPUTarget<tools::SYCL::gen::AmdGPU>(Val)) {
+      SmallString<64> OffloadArch("--offload-arch=");
+      OffloadArch += GpuDevice->data();
+      parseTargetOpts(OffloadArch, Args, CmdArgs);
     }
   }
 }

clang/test/Driver/sycl-ftarget-register-alloc-mode-old-model.cpp

@@ -22,7 +22,7 @@
 
 // RUN: %clang -### -fsycl --no-offload-new-driver \
 // RUN:    -fsycl-targets=spir64_gen -Xs "-device 0x0BD5" %s 2>&1 \
-// RUN:   | FileCheck %if system-windows %{ -check-prefix=DEFAULT_AOT %} %else %{ -check-prefix=AUTO_AOT %} %s -DDEVICE=0x0BD5
+// RUN:   | FileCheck %if system-windows %{ -check-prefix=DEFAULT_AOT %} %else %{ -check-prefix=AUTO_AOT %} %s -DDEVICE=pvc
 
 // RUN: %clang -### -fsycl --no-offload-new-driver \
 // RUN:    -fsycl-targets=spir64_gen -Xs "-device 12.60.7" %s 2>&1 \

clang/test/Driver/sycl-ftarget-register-alloc-mode.cpp

@@ -22,7 +22,7 @@
 
 // RUN: %clang -### -fsycl --offload-new-driver \
 // RUN:    -fsycl-targets=spir64_gen -Xs "-device 0x0BD5" %s 2>&1 \
-// RUN:   | FileCheck %if system-windows %{ -check-prefix=DEFAULT_AOT %} %else %{ -check-prefix=AUTO_AOT %} %s -DDEVICE=0x0BD5
+// RUN:   | FileCheck %if system-windows %{ -check-prefix=DEFAULT_AOT %} %else %{ -check-prefix=AUTO_AOT %} %s -DDEVICE=pvc
 
 // RUN: %clang -### -fsycl --offload-new-driver \
 // RUN:    -fsycl-targets=spir64_gen -Xs "-device 12.60.7" %s 2>&1 \

clang/test/Driver/sycl-host-compiler-old-model.cpp

@@ -90,3 +90,13 @@
 // CHECK_SAVE_TEMPS-NEXT: g++{{.*}} "[[APPEND_CPP]]" "-c"
 // CHECK_SAVE_TEMPS-SAME: "-o" "[[HOST_OBJ:.+\.o]]"
 // CHECK_SAVE_TEMPS-NEXT: clang-offload-bundler{{.*}} "-input=[[DEVICE_BC]]" "-input=[[HOST_OBJ]]"
+
+/// Test to verify binary from PATH is used
+// RUN: rm -rf %t && mkdir -p %t/test_path
+// RUN: touch %t/test_path/clang++ && chmod +x %t/test_path/clang++
+// RUN: env "PATH=%t/test_path%{pathsep}%PATH%" \
+// RUN: %clangxx -### -fsycl -fsycl-host-compiler=clang++ \
+// RUN:   -fsycl-host-compiler-options=-DDUMMY_OPT --no-offload-new-driver \
+// RUN:   %s 2>&1 \
+// RUN: | FileCheck -check-prefix=PATH_CHECK %s
+// PATH_CHECK: {{(/|\\\\)}}test_path{{(/|\\\\)}}clang++{{.*}} "-DDUMMY_OPT"

clang/test/Driver/sycl-offload.cpp

@@ -104,3 +104,9 @@
 // CHECK_FSYCL_FP64_CONV_EMU_WIN-NOT: clang{{.*}} "-cc1" "-triple x86_64-unknown-linux-gnu" {{.*}} "-fsycl-fp64-conv-emu"
 // CHECK_FSYCL_FP64_CONV_EMU_WIN-DAG: clang{{.*}} "-cc1" "-triple" "spir64_gen{{.*}}" "-fsycl-fp64-conv-emu"
 // CHECK_FSYCL_FP64_CONV_EMU_WIN-DAG: clang-offload-packager{{.*}} "--image=file={{.*}}.bc,triple=spir64_gen-unknown-unknown,arch=,kind=sycl,compile-opts={{.*}}-options -ze-fp64-gen-conv-emu{{.*}}"
+
+/// Compilation checks to make sure an early empty -fsycl-targets does not
+/// crash.
+// RUN: %clangxx -### -fsycl -fsycl-targets= -fsycl-targets=spir64 %s 2>&1 \
+// RUN:  | FileCheck %s -check-prefix=CHECK_SPIR64
+// CHECK_SPIR64: clang{{.*}} "-cc1" "-triple" "spir64-unknown-unknown"{{.*}} "-fsycl-is-device"

clang/test/Driver/sycl-spirv-ext.c

@@ -0,0 +1,103 @@
+// Generate .o file as SYCL device library file.
+//
+// RUN: touch %t.devicelib.cpp
+// RUN: %clang %t.devicelib.cpp -fsycl -fsycl-targets=spir64-unknown-unknown -c --offload-new-driver -o %t_1.devicelib.o
+// RUN: %clang %t.devicelib.cpp -fsycl -fsycl-targets=spir64_gen-unknown-unknown -c --offload-new-driver -o %t_2.devicelib.o
+// RUN: %clang %t.devicelib.cpp -fsycl -fsycl-targets=spir64_x86_64-unknown-unknown -c --offload-new-driver -o %t_3.devicelib.o
+
+/// Check llvm-spirv extensions that are set
+
+// RUN: %clang -target x86_64-unknown-linux-gnu -fsycl --offload-new-driver \ 
+// RUN:   -fsycl-targets=spir64-unknown-unknown -c %s -o %t_1.o
+// RUN: clang-linker-wrapper -sycl-device-libraries=%t_1.devicelib.o \
+// RUN:   "--host-triple=x86_64-unknown-linux-gnu" "--linker-path=/usr/bin/ld" \
+// RUN:   "--" "-o" "a.out" %t_1.o --dry-run 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHECK-DEFAULT %s
+// RUN: %clang -target x86_64-unknown-linux-gnu -fsycl --offload-new-driver \
+// RUN:   -fsycl-targets=spir64_gen-unknown-unknown -c %s -o %t_2.o
+// RUN: clang-linker-wrapper -sycl-device-libraries=%t_2.devicelib.o \
+// RUN:   "--host-triple=x86_64-unknown-linux-gnu" "--linker-path=/usr/bin/ld" \
+// RUN:   "--" "-o" "a.out" %t_2.o --dry-run 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHECK-DEFAULT %s
+// RUN: %clang -target x86_64-unknown-linux-gnu -fsycl --offload-new-driver \
+// RUN:   -fsycl-targets=spir64_x86_64-unknown-unknown -c %s -o %t_3.o
+// RUN: clang-linker-wrapper -sycl-device-libraries=%t_3.devicelib.o \
+// RUN:   "--host-triple=x86_64-unknown-linux-gnu" "--linker-path=/usr/bin/ld" \
+// RUN:   "--" "-o" "a.out" %t_3.o --dry-run 2>&1 \
+// RUN:   | FileCheck -check-prefix=CHECK-CPU %s
+
+// CHECK-DEFAULT: llvm-spirv{{.*}}-spirv-ext=-all
+// CHECK-DEFAULT-SAME:,+SPV_EXT_shader_atomic_float_add
+// CHECK-DEFAULT-SAME:,+SPV_EXT_shader_atomic_float_min_max
+// CHECK-DEFAULT-SAME:,+SPV_KHR_no_integer_wrap_decoration,+SPV_KHR_float_controls
+// CHECK-DEFAULT-SAME:,+SPV_KHR_expect_assume,+SPV_KHR_linkonce_odr
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_subgroups,+SPV_INTEL_media_block_io
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_device_side_avc_motion_estimation
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_fpga_loop_controls
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_unstructured_loop_controls,+SPV_INTEL_fpga_reg
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_blocking_pipes,+SPV_INTEL_function_pointers
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_kernel_attributes,+SPV_INTEL_io_pipes
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_inline_assembly,+SPV_INTEL_arbitrary_precision_integers
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_float_controls2
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_vector_compute,+SPV_INTEL_fast_composite
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_arbitrary_precision_fixed_point
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_arbitrary_precision_floating_point
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_variable_length_array,+SPV_INTEL_fp_fast_math_mode
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_long_constant_composite
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_arithmetic_fence
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_cache_controls
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_fpga_buffer_location
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_fpga_argument_interfaces
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_fpga_invocation_pipelining_attributes
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_fpga_latency_control
+// CHECK-DEFAULT-SAME:,+SPV_KHR_shader_clock
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_bindless_images
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_task_sequence
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_token_type
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_bfloat16_conversion
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_joint_matrix
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_hw_thread_queries
+// CHECK-DEFAULT-SAME:,+SPV_KHR_uniform_group_instructions
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_masked_gather_scatter
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_tensor_float32_conversion
+// CHECK-DEFAULT-SAME:,+SPV_INTEL_optnone
+// CHECK-DEFAULT-SAME:,+SPV_KHR_non_semantic_info
+// CHECK-DEFAULT-SAME:,+SPV_KHR_cooperative_matrix
+// CHECK-DEFAULT-SAME:,+SPV_EXT_shader_atomic_float16_add
+
+// CHECK-CPU: llvm-spirv{{.*}}-spirv-ext=-all
+// CHECK-CPU-SAME:,+SPV_EXT_shader_atomic_float_add
+// CHECK-CPU-SAME:,+SPV_EXT_shader_atomic_float_min_max
+// CHECK-CPU-SAME:,+SPV_KHR_no_integer_wrap_decoration,+SPV_KHR_float_controls
+// CHECK-CPU-SAME:,+SPV_KHR_expect_assume,+SPV_KHR_linkonce_odr
+// CHECK-CPU-SAME:,+SPV_INTEL_subgroups,+SPV_INTEL_media_block_io
+// CHECK-CPU-SAME:,+SPV_INTEL_device_side_avc_motion_estimation
+// CHECK-CPU-SAME:,+SPV_INTEL_fpga_loop_controls
+// CHECK-CPU-SAME:,+SPV_INTEL_unstructured_loop_controls,+SPV_INTEL_fpga_reg
+// CHECK-CPU-SAME:,+SPV_INTEL_blocking_pipes,+SPV_INTEL_function_pointers
+// CHECK-CPU-SAME:,+SPV_INTEL_kernel_attributes,+SPV_INTEL_io_pipes
+// CHECK-CPU-SAME:,+SPV_INTEL_inline_assembly,+SPV_INTEL_arbitrary_precision_integers
+// CHECK-CPU-SAME:,+SPV_INTEL_float_controls2
+// CHECK-CPU-SAME:,+SPV_INTEL_vector_compute,+SPV_INTEL_fast_composite
+// CHECK-CPU-SAME:,+SPV_INTEL_arbitrary_precision_fixed_point
+// CHECK-CPU-SAME:,+SPV_INTEL_arbitrary_precision_floating_point
+// CHECK-CPU-SAME:,+SPV_INTEL_variable_length_array,+SPV_INTEL_fp_fast_math_mode
+// CHECK-CPU-SAME:,+SPV_INTEL_long_constant_composite
+// CHECK-CPU-SAME:,+SPV_INTEL_arithmetic_fence
+// CHECK-CPU-SAME:,+SPV_INTEL_cache_controls
+// CHECK-CPU-SAME:,+SPV_INTEL_fpga_buffer_location
+// CHECK-CPU-SAME:,+SPV_INTEL_fpga_argument_interfaces
+// CHECK-CPU-SAME:,+SPV_INTEL_fpga_invocation_pipelining_attributes
+// CHECK-CPU-SAME:,+SPV_INTEL_fpga_latency_control
+// CHECK-CPU-SAME:,+SPV_INTEL_task_sequence
+// CHECK-CPU-SAME:,+SPV_INTEL_token_type
+// CHECK-CPU-SAME:,+SPV_INTEL_bfloat16_conversion
+// CHECK-CPU-SAME:,+SPV_INTEL_joint_matrix
+// CHECK-CPU-SAME:,+SPV_INTEL_hw_thread_queries
+// CHECK-CPU-SAME:,+SPV_KHR_uniform_group_instructions
+// CHECK-CPU-SAME:,+SPV_INTEL_masked_gather_scatter
+// CHECK-CPU-SAME:,+SPV_INTEL_tensor_float32_conversion
+// CHECK-CPU-SAME:,+SPV_INTEL_optnone
+// CHECK-CPU-SAME:,+SPV_KHR_non_semantic_info
+// CHECK-CPU-SAME:,+SPV_KHR_cooperative_matrix
+// CHECK-CPU-SAME:,+SPV_INTEL_fp_max_error