[Driver][clang-linker-wrapper] Add initial support for OpenMP offloading to generic SPIR-V (#120145)

sarnex · web-flow · commit cd19f3f787b0 · 2025-01-02T14:18:33.000-06:00
This is the first of a series of patches to add support for OpenMP
offloading to SPIR-V through liboffload with the first intended target
being Intel GPUs. This patch implements the basic driver and
`clang-linker-wrapper` work for JIT mode. There are still many missing
pieces, so this is not yet usable.

We introduce `spirv64-intel-unknown` as the only currently supported
triple. The user-facing argument to enable offloading will be `-fopenmp
-fopenmp-targets=spirv64-intel`

Add a new `SPIRVOpenMPToolChain` toolchain based on the existing general
SPIR-V toolchain which will call all the required SPIR-V tools (and
eventually the SPIR-V backend) as well as add the corresponding device
RTL as an argument to the linker.

We can't get through the front end consistently yet, so it's difficult
to add any LIT tests that execute any tools, but front end changes are
planned very shortly, and then we can add those tests.

---------

Signed-off-by: Sarnie, Nick &lt;nick.sarnie@intel.com&gt;
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
@@ -1493,6 +1493,8 @@ def libomptarget_amdgcn_bc_path_EQ : Joined<["--"], "libomptarget-amdgcn-bc-path
   HelpText<"Path to libomptarget-amdgcn bitcode library">, Alias<libomptarget_amdgpu_bc_path_EQ>;
 def libomptarget_nvptx_bc_path_EQ : Joined<["--"], "libomptarget-nvptx-bc-path=">, Group<i_Group>,
   HelpText<"Path to libomptarget-nvptx bitcode library">;
+def libomptarget_spirv_bc_path_EQ : Joined<["--"], "libomptarget-spirv-bc-path=">, Group<i_Group>,
+  HelpText<"Path to libomptarget-spirv bitcode library">;
 def dD : Flag<["-"], "dD">, Group<d_Group>, Visibility<[ClangOption, CC1Option]>,
   HelpText<"Print macro definitions in -E mode in addition to normal output">;
 def dI : Flag<["-"], "dI">, Group<d_Group>, Visibility<[ClangOption, CC1Option]>,
diff --git a/clang/lib/Driver/CMakeLists.txt b/clang/lib/Driver/CMakeLists.txt
@@ -77,6 +77,7 @@ add_clang_library(clangDriver
   ToolChains/RISCVToolchain.cpp
   ToolChains/Solaris.cpp
   ToolChains/SPIRV.cpp
+  ToolChains/SPIRVOpenMP.cpp
   ToolChains/TCE.cpp
   ToolChains/UEFI.cpp
   ToolChains/VEToolchain.cpp
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
@@ -43,6 +43,7 @@
 #include "ToolChains/PS4CPU.h"
 #include "ToolChains/RISCVToolchain.h"
 #include "ToolChains/SPIRV.h"
+#include "ToolChains/SPIRVOpenMP.h"
 #include "ToolChains/Solaris.h"
 #include "ToolChains/TCE.h"
 #include "ToolChains/UEFI.h"
@@ -890,9 +891,9 @@ void Driver::CreateOffloadingDeviceToolChains(Compilation &C,
                                                       HostTC->getTriple());
 
       // Attempt to deduce the offloading triple from the set of architectures.
-      // We can only correctly deduce NVPTX / AMDGPU triples currently. We need
-      // to temporarily create these toolchains so that we can access tools for
-      // inferring architectures.
+      // We can only correctly deduce NVPTX / AMDGPU triples currently.
+      // We need to temporarily create these toolchains so that we can access
+      // tools for inferring architectures.
       llvm::DenseSet<StringRef> Archs;
       if (NVPTXTriple) {
         auto TempTC = std::make_unique<toolchains::CudaToolChain>(
@@ -962,7 +963,7 @@ void Driver::CreateOffloadingDeviceToolChains(Compilation &C,
         const ToolChain *TC;
         // Device toolchains have to be selected differently. They pair host
         // and device in their implementation.
-        if (TT.isNVPTX() || TT.isAMDGCN()) {
+        if (TT.isNVPTX() || TT.isAMDGCN() || TT.isSPIRV()) {
           const ToolChain *HostTC =
               C.getSingleOffloadToolChain<Action::OFK_Host>();
           assert(HostTC && "Host toolchain should be always defined.");
@@ -975,6 +976,9 @@ void Driver::CreateOffloadingDeviceToolChains(Compilation &C,
             else if (TT.isAMDGCN())
               DeviceTC = std::make_unique<toolchains::AMDGPUOpenMPToolChain>(
                   *this, TT, *HostTC, C.getInputArgs());
+            else if (TT.isSPIRV())
+              DeviceTC = std::make_unique<toolchains::SPIRVOpenMPToolChain>(
+                  *this, TT, *HostTC, C.getInputArgs());
             else
               assert(DeviceTC && "Device toolchain not defined.");
           }
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.cpp b/clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -2839,10 +2839,13 @@ void tools::addOpenMPDeviceRTL(const Driver &D,
     LibraryPaths.emplace_back(LibPath);
 
   OptSpecifier LibomptargetBCPathOpt =
-      Triple.isAMDGCN() ? options::OPT_libomptarget_amdgpu_bc_path_EQ
-                        : options::OPT_libomptarget_nvptx_bc_path_EQ;
+      Triple.isAMDGCN()  ? options::OPT_libomptarget_amdgpu_bc_path_EQ
+      : Triple.isNVPTX() ? options::OPT_libomptarget_nvptx_bc_path_EQ
+                         : options::OPT_libomptarget_spirv_bc_path_EQ;
 
-  StringRef ArchPrefix = Triple.isAMDGCN() ? "amdgpu" : "nvptx";
+  StringRef ArchPrefix = Triple.isAMDGCN()  ? "amdgpu"
+                         : Triple.isNVPTX() ? "nvptx"
+                                            : "spirv64";
   std::string LibOmpTargetName = ("libomptarget-" + ArchPrefix + ".bc").str();
 
   // First check whether user specifies bc library
diff --git a/clang/lib/Driver/ToolChains/SPIRV.h b/clang/lib/Driver/ToolChains/SPIRV.h
@@ -52,7 +52,7 @@ class LLVM_LIBRARY_VISIBILITY Linker final : public Tool {
 
 namespace toolchains {
 
-class LLVM_LIBRARY_VISIBILITY SPIRVToolChain final : public ToolChain {
+class LLVM_LIBRARY_VISIBILITY SPIRVToolChain : public ToolChain {
   mutable std::unique_ptr<Tool> Translator;
 
 public:
diff --git a/clang/lib/Driver/ToolChains/SPIRVOpenMP.cpp b/clang/lib/Driver/ToolChains/SPIRVOpenMP.cpp
@@ -0,0 +1,34 @@
+//==- SPIRVOpenMP.cpp - SPIR-V OpenMP Tool Implementations --------*- C++ -*==//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//==------------------------------------------------------------------------==//
+#include "SPIRVOpenMP.h"
+#include "CommonArgs.h"
+
+using namespace clang::driver;
+using namespace clang::driver::toolchains;
+using namespace clang::driver::tools;
+using namespace llvm::opt;
+
+namespace clang::driver::toolchains {
+SPIRVOpenMPToolChain::SPIRVOpenMPToolChain(const Driver &D,
+                                           const llvm::Triple &Triple,
+                                           const ToolChain &HostToolchain,
+                                           const ArgList &Args)
+    : SPIRVToolChain(D, Triple, Args), HostTC(HostToolchain) {}
+
+void SPIRVOpenMPToolChain::addClangTargetOptions(
+    const llvm::opt::ArgList &DriverArgs, llvm::opt::ArgStringList &CC1Args,
+    Action::OffloadKind DeviceOffloadingKind) const {
+
+  if (DeviceOffloadingKind != Action::OFK_OpenMP)
+    return;
+
+  if (DriverArgs.hasArg(options::OPT_nogpulib))
+    return;
+  addOpenMPDeviceRTL(getDriver(), DriverArgs, CC1Args, "", getTriple(), HostTC);
+}
+} // namespace clang::driver::toolchains
diff --git a/clang/lib/Driver/ToolChains/SPIRVOpenMP.h b/clang/lib/Driver/ToolChains/SPIRVOpenMP.h
@@ -0,0 +1,29 @@
+//===--- SPIRVOpenMP.h - SPIR-V OpenMP Tool Implementations ------*- C++-*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_LIB_DRIVER_TOOLCHAINS_SPIRV_OPENMP_H
+#define LLVM_CLANG_LIB_DRIVER_TOOLCHAINS_SPIRV_OPENMP_H
+
+#include "SPIRV.h"
+#include "clang/Driver/Tool.h"
+#include "clang/Driver/ToolChain.h"
+
+namespace clang::driver::toolchains {
+class LLVM_LIBRARY_VISIBILITY SPIRVOpenMPToolChain : public SPIRVToolChain {
+public:
+  SPIRVOpenMPToolChain(const Driver &D, const llvm::Triple &Triple,
+                       const ToolChain &HostTC, const llvm::opt::ArgList &Args);
+
+  void addClangTargetOptions(
+      const llvm::opt::ArgList &DriverArgs, llvm::opt::ArgStringList &CC1Args,
+      Action::OffloadKind DeviceOffloadingKind) const override;
+
+  const ToolChain &HostTC;
+};
+} // namespace clang::driver::toolchains
+#endif
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -4263,6 +4263,7 @@ bool CompilerInvocation::ParseLangArgs(LangOptions &Opts, ArgList &Args,
 
       if (TT.getArch() == llvm::Triple::UnknownArch ||
           !(TT.getArch() == llvm::Triple::aarch64 || TT.isPPC() ||
+            TT.getArch() == llvm::Triple::spirv64 ||
             TT.getArch() == llvm::Triple::systemz ||
             TT.getArch() == llvm::Triple::loongarch64 ||
             TT.getArch() == llvm::Triple::nvptx ||
diff --git a/clang/test/Driver/Inputs/spirv-openmp/lib/libomptarget-spirv64.bc b/clang/test/Driver/Inputs/spirv-openmp/lib/libomptarget-spirv64.bc
diff --git a/clang/test/Driver/spirv-openmp-toolchain.c b/clang/test/Driver/spirv-openmp-toolchain.c
@@ -0,0 +1,64 @@
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=spirv64-intel \
+// RUN:        --libomptarget-spirv-bc-path=%t/ -nogpulib %s 2>&1 \
+// RUN: | FileCheck %s
+
+// verify the tools invocations
+// CHECK: "-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-emit-llvm-bc"{{.*}}"-x" "c"
+// CHECK: "-cc1" "-triple" "spirv64-intel" "-aux-triple" "x86_64-unknown-linux-gnu"
+// CHECK: llvm-spirv{{.*}}
+// CHECK: "-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-emit-obj"
+// CHECK: clang-linker-wrapper{{.*}} "-o" "a.out"
+
+// RUN: %clang -ccc-print-phases --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=spirv64-intel %s 2>&1 \
+// RUN: | FileCheck --check-prefix=CHECK-PHASES %s
+
+// CHECK-PHASES: 0: input, "[[INPUT:.+]]", c, (host-openmp)
+// CHECK-PHASES: 1: preprocessor, {0}, cpp-output, (host-openmp)
+// CHECK-PHASES: 2: compiler, {1}, ir, (host-openmp)
+// CHECK-PHASES: 3: input, "[[INPUT]]", c, (device-openmp)
+// CHECK-PHASES: 4: preprocessor, {3}, cpp-output, (device-openmp)
+// CHECK-PHASES: 5: compiler, {4}, ir, (device-openmp)
+// CHECK-PHASES: 6: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, "device-openmp (spirv64-intel)" {5}, ir
+// CHECK-PHASES: 7: backend, {6}, assembler, (device-openmp)
+// CHECK-PHASES: 8: assembler, {7}, object, (device-openmp)
+// CHECK-PHASES: 9: offload, "device-openmp (spirv64-intel)" {8}, object
+// CHECK-PHASES: 10: clang-offload-packager, {9}, image, (device-openmp)
+// CHECK-PHASES: 11: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, "device-openmp (x86_64-unknown-linux-gnu)" {10}, ir
+// CHECK-PHASES: 12: backend, {11}, assembler, (host-openmp)
+// CHECK-PHASES: 13: assembler, {12}, object, (host-openmp)
+// CHECK-PHASES: 14: clang-linker-wrapper, {13}, image, (host-openmp)
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=spirv64-intel -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=spirv64-intel -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS
+
+// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[HOST_BC:.+]]"
+// CHECK-BINDINGS: "spirv64-intel" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_TEMP_BC:.+]]"
+// CHECK-BINDINGS: "spirv64-intel" - "SPIR-V::Translator", inputs: ["[[DEVICE_TEMP_BC]]"], output: "[[DEVICE_SPV:.+]]"
+// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_SPV]]"], output: "[[DEVICE_IMAGE:.+]]"
+// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[DEVICE_IMAGE]]"], output: "[[HOST_OBJ:.+]]"
+// CHECK-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[HOST_OBJ]]"], output: "a.out"
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -save-temps -fopenmp -fopenmp-targets=spirv64-intel -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS-TEMPS
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -save-temps -fopenmp -fopenmp-targets=spirv64-intel %s 2>&1 | FileCheck %s --check-prefix=CHECK-BINDINGS-TEMPS
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[HOST_PP:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_PP]]"], output: "[[HOST_BC:.+]]"
+// CHECK-BINDINGS-TEMPS: "spirv64-intel" - "clang", inputs: ["[[INPUT]]"], output: "[[DEVICE_PP:.+]]"
+// CHECK-BINDINGS-TEMPS: "spirv64-intel" - "clang", inputs: ["[[DEVICE_PP]]", "[[HOST_BC]]"], output: "[[DEVICE_TEMP_BC:.+]]"
+// CHECK-BINDINGS-TEMPS: "spirv64-intel" - "SPIR-V::Translator", inputs: ["[[DEVICE_TEMP_BC]]"], output: "[[DEVICE_ASM:.+]]"
+// CHECK-BINDINGS-TEMPS: "spirv64-intel" - "SPIR-V::Translator", inputs: ["[[DEVICE_ASM]]"], output: "[[DEVICE_SPV:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_SPV]]"], output: "[[DEVICE_IMAGE:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[DEVICE_IMAGE]]"], output: "[[HOST_ASM:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "clang::as", inputs: ["[[HOST_ASM]]"], output: "[[HOST_OBJ:.+]]"
+// CHECK-BINDINGS-TEMPS: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[HOST_OBJ]]"], output: "a.out"
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp -fopenmp-targets=spirv64-intel -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
+// CHECK-EMIT-LLVM-IR: "-cc1" "-triple" "spirv64-intel"{{.*}}"-emit-llvm-bc"
+
+// RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=spirv64-intel \
+// RUN: --sysroot=%S/Inputs/spirv-openmp/ %s 2>&1 | FileCheck --check-prefix=CHECK-GPULIB %s
+// CHECK-GPULIB: "-cc1" "-triple" "spirv64-intel"{{.*}}"-mlink-builtin-bitcode" "{{.*}}libomptarget-spirv64.bc"
+
+// RUN: not %clang -### --target=x86_64-unknown-linux-gnu -fopenmp --offload-arch=spirv64-intel \
+// RUN:        --libomptarget-spirv-bc-path=%t/ -nogpulib %s 2>&1 \
+// RUN: | FileCheck %s --check-prefix=CHECK-OFFLOAD-ARCH-ERROR
+// CHECK-OFFLOAD-ARCH-ERROR: error: failed to deduce triple for target architecture 'spirv64-intel'; specify the triple using '-fopenmp-targets' and '-Xopenmp-target' instead
diff --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -504,14 +504,14 @@ Expected<StringRef> clang(ArrayRef<StringRef> InputFiles, const ArgList &Args) {
         {"-Xlinker",
          Args.MakeArgString("--plugin-opt=" + StringRef(Arg->getValue()))});
 
-  if (!Triple.isNVPTX())
+  if (!Triple.isNVPTX() && !Triple.isSPIRV())
     CmdArgs.push_back("-Wl,--no-undefined");
 
   for (StringRef InputFile : InputFiles)
     CmdArgs.push_back(InputFile);
 
   // If this is CPU offloading we copy the input libraries.
-  if (!Triple.isAMDGPU() && !Triple.isNVPTX()) {
+  if (!Triple.isAMDGPU() && !Triple.isNVPTX() && !Triple.isSPIRV()) {
     CmdArgs.push_back("-Wl,-Bsymbolic");
     CmdArgs.push_back("-shared");
     ArgStringList LinkerArgs;
@@ -595,6 +595,7 @@ Expected<StringRef> linkDevice(ArrayRef<StringRef> InputFiles,
   case Triple::aarch64_be:
   case Triple::ppc64:
   case Triple::ppc64le:
+  case Triple::spirv64:
   case Triple::systemz:
   case Triple::loongarch64:
     return generic::clang(InputFiles, Args);
