[AMDGPU][OpenMP] Support linking of math libraries

Math libraries are linked only when -lm is specified. This is because
host system could be missing rocm-device-libs.

Reviewed By: JonChesterfield, yaxunl

Differential Revision: https://reviews.llvm.org/D105981

diff --git a/clang/lib/Driver/ToolChains/AMDGPU.cpp b/clang/lib/Driver/ToolChains/AMDGPU.cpp
index d63c5e1..4a74131 100644 (file)
--- a/clang/lib/Driver/ToolChains/AMDGPU.cpp
+++ b/clang/lib/Driver/ToolChains/AMDGPU.cpp
@@ -893,3 +893,38 @@ bool AMDGPUToolChain::shouldSkipArgument(const llvm::opt::Arg *A) const {
     return true;
   return false;
 }
+
+llvm::SmallVector<std::string, 12>
+ROCMToolChain::getCommonDeviceLibNames(const llvm::opt::ArgList &DriverArgs,
+                                       const std::string &GPUArch) const {
+  auto Kind = llvm::AMDGPU::parseArchAMDGCN(GPUArch);
+  const StringRef CanonArch = llvm::AMDGPU::getArchNameAMDGCN(Kind);
+
+  std::string LibDeviceFile = RocmInstallation.getLibDeviceFile(CanonArch);
+  if (LibDeviceFile.empty()) {
+    getDriver().Diag(diag::err_drv_no_rocm_device_lib) << 1 << GPUArch;
+    return {};
+  }
+
+  // If --hip-device-lib is not set, add the default bitcode libraries.
+  // TODO: There are way too many flags that change this. Do we need to check
+  // them all?
+  bool DAZ = DriverArgs.hasFlag(options::OPT_fgpu_flush_denormals_to_zero,
+                                options::OPT_fno_gpu_flush_denormals_to_zero,
+                                getDefaultDenormsAreZeroForTarget(Kind));
+  bool FiniteOnly = DriverArgs.hasFlag(
+      options::OPT_ffinite_math_only, options::OPT_fno_finite_math_only, false);
+  bool UnsafeMathOpt =
+      DriverArgs.hasFlag(options::OPT_funsafe_math_optimizations,
+                         options::OPT_fno_unsafe_math_optimizations, false);
+  bool FastRelaxedMath = DriverArgs.hasFlag(options::OPT_ffast_math,
+                                            options::OPT_fno_fast_math, false);
+  bool CorrectSqrt = DriverArgs.hasFlag(
+      options::OPT_fhip_fp32_correctly_rounded_divide_sqrt,
+      options::OPT_fno_hip_fp32_correctly_rounded_divide_sqrt);
+  bool Wave64 = isWave64(DriverArgs, Kind);
+
+  return RocmInstallation.getCommonBitcodeLibs(
+      DriverArgs, LibDeviceFile, Wave64, DAZ, FiniteOnly, UnsafeMathOpt,
+      FastRelaxedMath, CorrectSqrt);
+}
\ No newline at end of file

diff --git a/clang/lib/Driver/ToolChains/AMDGPU.h b/clang/lib/Driver/ToolChains/AMDGPU.h
index 50ed3b3..a4bcf31 100644 (file)
--- a/clang/lib/Driver/ToolChains/AMDGPU.h
+++ b/clang/lib/Driver/ToolChains/AMDGPU.h
@@ -136,6 +136,11 @@ public:
   addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
                         llvm::opt::ArgStringList &CC1Args,
                         Action::OffloadKind DeviceOffloadKind) const override;
+
+  // Returns a list of device library names shared by different languages
+  llvm::SmallVector<std::string, 12>
+  getCommonDeviceLibNames(const llvm::opt::ArgList &DriverArgs,
+                          const std::string &GPUArch) const;
 };
 
 } // end namespace toolchains

diff --git a/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp b/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
index fe1d19c..7b335f3 100644 (file)
--- a/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
+++ b/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp
@@ -9,12 +9,14 @@
 #include "AMDGPUOpenMP.h"
 #include "AMDGPU.h"
 #include "CommonArgs.h"
+#include "ToolChains/ROCm.h"
 #include "clang/Basic/DiagnosticDriver.h"
 #include "clang/Driver/Compilation.h"
 #include "clang/Driver/Driver.h"
 #include "clang/Driver/DriverDiagnostic.h"
 #include "clang/Driver/InputInfo.h"
 #include "clang/Driver/Options.h"
+#include "llvm/ADT/STLExtras.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/FormatAdapters.h"
 #include "llvm/Support/FormatVariadic.h"
@@ -232,6 +234,27 @@ void AMDGPUOpenMPToolChain::addClangTargetOptions(
 
   addOpenMPDeviceRTL(getDriver(), DriverArgs, CC1Args, BitcodeSuffix,
                      getTriple());
+
+  if (!DriverArgs.hasArg(options::OPT_l))
+    return;
+
+  auto Lm = DriverArgs.getAllArgValues(options::OPT_l);
+  bool HasLibm = false;
+  for (auto &Lib : Lm) {
+    if (Lib == "m") {
+      HasLibm = true;
+      break;
+    }
+  }
+
+  if (HasLibm) {
+    SmallVector<std::string, 12> BCLibs =
+        getCommonDeviceLibNames(DriverArgs, GPUArch);
+    llvm::for_each(BCLibs, [&](StringRef BCFile) {
+      CC1Args.push_back("-mlink-builtin-bitcode");
+      CC1Args.push_back(DriverArgs.MakeArgString(BCFile));
+    });
+  }
 }
 
 llvm::opt::DerivedArgList *AMDGPUOpenMPToolChain::TranslateArgs(

diff --git a/clang/lib/Driver/ToolChains/HIP.cpp b/clang/lib/Driver/ToolChains/HIP.cpp
index 59d58aa..c4e840d 100644 (file)
--- a/clang/lib/Driver/ToolChains/HIP.cpp
+++ b/clang/lib/Driver/ToolChains/HIP.cpp
@@ -395,35 +395,8 @@ HIPToolChain::getHIPDeviceLibs(const llvm::opt::ArgList &DriverArgs) const {
     }
     StringRef GpuArch = getGPUArch(DriverArgs);
     assert(!GpuArch.empty() && "Must have an explicit GPU arch.");
-    (void)GpuArch;
-    auto Kind = llvm::AMDGPU::parseArchAMDGCN(GpuArch);
-    const StringRef CanonArch = llvm::AMDGPU::getArchNameAMDGCN(Kind);
-
-    std::string LibDeviceFile = RocmInstallation.getLibDeviceFile(CanonArch);
-    if (LibDeviceFile.empty()) {
-      getDriver().Diag(diag::err_drv_no_rocm_device_lib) << 1 << GpuArch;
-      return {};
-    }
 
     // If --hip-device-lib is not set, add the default bitcode libraries.
-    // TODO: There are way too many flags that change this. Do we need to check
-    // them all?
-    bool DAZ = DriverArgs.hasFlag(options::OPT_fgpu_flush_denormals_to_zero,
-                                  options::OPT_fno_gpu_flush_denormals_to_zero,
-                                  getDefaultDenormsAreZeroForTarget(Kind));
-    bool FiniteOnly =
-        DriverArgs.hasFlag(options::OPT_ffinite_math_only,
-                           options::OPT_fno_finite_math_only, false);
-    bool UnsafeMathOpt =
-        DriverArgs.hasFlag(options::OPT_funsafe_math_optimizations,
-                           options::OPT_fno_unsafe_math_optimizations, false);
-    bool FastRelaxedMath = DriverArgs.hasFlag(
-        options::OPT_ffast_math, options::OPT_fno_fast_math, false);
-    bool CorrectSqrt = DriverArgs.hasFlag(
-        options::OPT_fhip_fp32_correctly_rounded_divide_sqrt,
-        options::OPT_fno_hip_fp32_correctly_rounded_divide_sqrt);
-    bool Wave64 = isWave64(DriverArgs, Kind);
-
     if (DriverArgs.hasFlag(options::OPT_fgpu_sanitize,
                            options::OPT_fno_gpu_sanitize, false)) {
       auto AsanRTL = RocmInstallation.getAsanRTLPath();
@@ -442,10 +415,8 @@ HIPToolChain::getHIPDeviceLibs(const llvm::opt::ArgList &DriverArgs) const {
     // Add the HIP specific bitcode library.
     BCLibs.push_back(RocmInstallation.getHIPPath().str());
 
-    // Add the generic set of libraries.
-    BCLibs.append(RocmInstallation.getCommonBitcodeLibs(
-        DriverArgs, LibDeviceFile, Wave64, DAZ, FiniteOnly, UnsafeMathOpt,
-        FastRelaxedMath, CorrectSqrt));
+    // Add common device libraries like ocml etc.
+    BCLibs.append(getCommonDeviceLibNames(DriverArgs, GpuArch.str()));
 
     // Add instrument lib.
     auto InstLib =

diff --git a/clang/test/Driver/amdgpu-openmp-toolchain.c b/clang/test/Driver/amdgpu-openmp-toolchain.c
index cee9797..f4b6c8c 100644 (file)
--- a/clang/test/Driver/amdgpu-openmp-toolchain.c
+++ b/clang/test/Driver/amdgpu-openmp-toolchain.c
@@ -74,3 +74,6 @@
 
 // RUN:   %clang -### --target=x86_64-unknown-linux-gnu -emit-llvm -S -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-EMIT-LLVM-IR
 // CHECK-EMIT-LLVM-IR: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-emit-llvm"
+
+// RUN: env LIBRARY_PATH=%S/Inputs/hip_dev_lib %clang -### -target x86_64-pc-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -lm --rocm-device-lib-path=%S/Inputs/rocm/amdgcn/bitcode %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIB-DEVICE
+// CHECK-LIB-DEVICE: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-mlink-builtin-bitcode"{{.*}}libomptarget-amdgcn-gfx803.bc"{{.*}}"-mlink-builtin-bitcode"{{.*}}ocml.bc" "-mlink-builtin-bitcode"{{.*}}ockl.bc" "-mlink-builtin-bitcode"{{.*}}oclc_daz_opt_on.bc" "-mlink-builtin-bitcode"{{.*}}oclc_unsafe_math_off.bc" "-mlink-builtin-bitcode"{{.*}}oclc_finite_only_off.bc" "-mlink-builtin-bitcode"{{.*}}oclc_correctly_rounded_sqrt_on.bc" "-mlink-builtin-bitcode"{{.*}}oclc_wavefrontsize64_on.bc" "-mlink-builtin-bitcode"{{.*}}oclc_isa_version_803.bc"