domada updated this revision to Diff 503672.
domada added a comment.
Fixed formatting
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D145579/new/
https://reviews.llvm.org/D145579
Files:
clang/lib/Basic/Targets/AMDGPU.cpp
clang/lib/Driver/ToolChains/CommonArgs.cpp
clang/lib/Driver/ToolChains/Flang.cpp
flang/include/flang/Frontend/FrontendActions.h
flang/lib/Frontend/FrontendActions.cpp
flang/test/Driver/target-cpu-features.f90
flang/test/Lower/OpenMP/target_cpu_features.f90
llvm/include/llvm/TargetParser/TargetParser.h
llvm/lib/TargetParser/TargetParser.cpp
mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td
mlir/lib/Dialect/OpenMP/IR/OpenMPDialect.cpp
Index: mlir/lib/Dialect/OpenMP/IR/OpenMPDialect.cpp
===================================================================
--- mlir/lib/Dialect/OpenMP/IR/OpenMPDialect.cpp
+++ mlir/lib/Dialect/OpenMP/IR/OpenMPDialect.cpp
@@ -1437,6 +1437,39 @@
return false;
}
+// Set the omp.target_cpu attribute on the module with the specified string
+void OpenMPDialect::setTargetCpu(Operation *module, llvm::StringRef cpu) {
+ module->setAttr(mlir::StringAttr::get(module->getContext(),
+ llvm::Twine{"omp.target_cpu"}),
+ mlir::StringAttr::get(module->getContext(), cpu));
+}
+
+// Return the value of the omp.target_cpu attribute stored in the module if it
+// exists, otherwise return empty by default
+std::string OpenMPDialect::getTargetCpu(Operation *module) {
+ if (Attribute targetCpu = module->getAttr("omp.target_cpu"))
+ if (targetCpu.isa<mlir::StringAttr>())
+ return targetCpu.dyn_cast<StringAttr>().getValue().str();
+ return llvm::Twine{""}.str();
+}
+
+// Set the omp.target_cpu_features attribute on the module with
+// the specified string
+void OpenMPDialect::setTargetCpuFeatures(Operation *module,
+ llvm::StringRef cpuFeatures) {
+ module->setAttr(mlir::StringAttr::get(module->getContext(),
+ llvm::Twine{"omp.target_cpu_features"}),
+ mlir::StringAttr::get(module->getContext(), cpuFeatures));
+}
+
+// Return the value of the omp.target_cpu_features attribute stored in the
+// module if it exists, otherwise return empty by default
+std::string OpenMPDialect::getTargetCpuFeatures(Operation *module) {
+ if (Attribute targetCpu = module->getAttr("omp.target_cpu_features"))
+ if (targetCpu.isa<mlir::StringAttr>())
+ return targetCpu.dyn_cast<StringAttr>().getValue().str();
+ return llvm::Twine{""}.str();
+}
#define GET_ATTRDEF_CLASSES
#include "mlir/Dialect/OpenMP/OpenMPOpsAttributes.cpp.inc"
Index: mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td
===================================================================
--- mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td
+++ mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td
@@ -36,6 +36,21 @@
// Return the value of the omp.is_device attribute stored in the module if it
// exists, otherwise return false by default
static bool getIsDevice(Operation* module);
+
+ // Set the omp.target_cpu attribute on the module with the specified string
+ static void setTargetCpu(Operation* module, StringRef cpu);
+
+ // Return the value of the omp.target_cpu attribute stored in the module if it
+ // exists, otherwise return empty by default
+ static std::string getTargetCpu(Operation* module);
+
+ // Set the omp.target_cpu_features attribute on the module with
+ // the specified string
+ static void setTargetCpuFeatures(Operation* module, StringRef cpuFeatures);
+
+ // Return the value of the omp.target_cpu_features attribute stored in
+ // the module if it exists, otherwise return empty by default
+ static std::string getTargetCpuFeatures(Operation* module);
}];
}
Index: llvm/lib/TargetParser/TargetParser.cpp
===================================================================
--- llvm/lib/TargetParser/TargetParser.cpp
+++ llvm/lib/TargetParser/TargetParser.cpp
@@ -251,3 +251,212 @@
return T.isAMDGCN() ? getArchNameAMDGCN(ProcKind) : getArchNameR600(ProcKind);
}
+
+void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
+ StringMap<bool> &Features) {
+ // XXX - What does the member GPU mean if device name string passed here?
+ if (T.isAMDGCN()) {
+ switch (parseArchAMDGCN(GPU)) {
+ case GK_GFX1103:
+ case GK_GFX1102:
+ case GK_GFX1101:
+ case GK_GFX1100:
+ Features["ci-insts"] = true;
+ Features["dot5-insts"] = true;
+ Features["dot7-insts"] = true;
+ Features["dot8-insts"] = true;
+ Features["dot9-insts"] = true;
+ Features["dot10-insts"] = true;
+ Features["dl-insts"] = true;
+ Features["16-bit-insts"] = true;
+ Features["dpp"] = true;
+ Features["gfx8-insts"] = true;
+ Features["gfx9-insts"] = true;
+ Features["gfx10-insts"] = true;
+ Features["gfx10-3-insts"] = true;
+ Features["gfx11-insts"] = true;
+ break;
+ case GK_GFX1036:
+ case GK_GFX1035:
+ case GK_GFX1034:
+ case GK_GFX1033:
+ case GK_GFX1032:
+ case GK_GFX1031:
+ case GK_GFX1030:
+ Features["ci-insts"] = true;
+ Features["dot1-insts"] = true;
+ Features["dot2-insts"] = true;
+ Features["dot5-insts"] = true;
+ Features["dot6-insts"] = true;
+ Features["dot7-insts"] = true;
+ Features["dot10-insts"] = true;
+ Features["dl-insts"] = true;
+ Features["16-bit-insts"] = true;
+ Features["dpp"] = true;
+ Features["gfx8-insts"] = true;
+ Features["gfx9-insts"] = true;
+ Features["gfx10-insts"] = true;
+ Features["gfx10-3-insts"] = true;
+ Features["s-memrealtime"] = true;
+ Features["s-memtime-inst"] = true;
+ break;
+ case GK_GFX1012:
+ case GK_GFX1011:
+ Features["dot1-insts"] = true;
+ Features["dot2-insts"] = true;
+ Features["dot5-insts"] = true;
+ Features["dot6-insts"] = true;
+ Features["dot7-insts"] = true;
+ Features["dot10-insts"] = true;
+ [[fallthrough]];
+ case GK_GFX1013:
+ case GK_GFX1010:
+ Features["dl-insts"] = true;
+ Features["ci-insts"] = true;
+ Features["16-bit-insts"] = true;
+ Features["dpp"] = true;
+ Features["gfx8-insts"] = true;
+ Features["gfx9-insts"] = true;
+ Features["gfx10-insts"] = true;
+ Features["s-memrealtime"] = true;
+ Features["s-memtime-inst"] = true;
+ break;
+ case GK_GFX940:
+ Features["gfx940-insts"] = true;
+ Features["fp8-insts"] = true;
+ [[fallthrough]];
+ case GK_GFX90A:
+ Features["gfx90a-insts"] = true;
+ [[fallthrough]];
+ case GK_GFX908:
+ Features["dot3-insts"] = true;
+ Features["dot4-insts"] = true;
+ Features["dot5-insts"] = true;
+ Features["dot6-insts"] = true;
+ Features["mai-insts"] = true;
+ [[fallthrough]];
+ case GK_GFX906:
+ Features["dl-insts"] = true;
+ Features["dot1-insts"] = true;
+ Features["dot2-insts"] = true;
+ Features["dot7-insts"] = true;
+ Features["dot10-insts"] = true;
+ [[fallthrough]];
+ case GK_GFX90C:
+ case GK_GFX909:
+ case GK_GFX904:
+ case GK_GFX902:
+ case GK_GFX900:
+ Features["gfx9-insts"] = true;
+ [[fallthrough]];
+ case GK_GFX810:
+ case GK_GFX805:
+ case GK_GFX803:
+ case GK_GFX802:
+ case GK_GFX801:
+ Features["gfx8-insts"] = true;
+ Features["16-bit-insts"] = true;
+ Features["dpp"] = true;
+ Features["s-memrealtime"] = true;
+ [[fallthrough]];
+ case GK_GFX705:
+ case GK_GFX704:
+ case GK_GFX703:
+ case GK_GFX702:
+ case GK_GFX701:
+ case GK_GFX700:
+ Features["ci-insts"] = true;
+ [[fallthrough]];
+ case GK_GFX602:
+ case GK_GFX601:
+ case GK_GFX600:
+ Features["s-memtime-inst"] = true;
+ break;
+ case GK_NONE:
+ break;
+ default:
+ llvm_unreachable("Unhandled GPU!");
+ }
+ } else {
+ if (GPU.empty())
+ GPU = "r600";
+
+ switch (llvm::AMDGPU::parseArchR600(GPU)) {
+ case GK_CAYMAN:
+ case GK_CYPRESS:
+ case GK_RV770:
+ case GK_RV670:
+ // TODO: Add fp64 when implemented.
+ break;
+ case GK_TURKS:
+ case GK_CAICOS:
+ case GK_BARTS:
+ case GK_SUMO:
+ case GK_REDWOOD:
+ case GK_JUNIPER:
+ case GK_CEDAR:
+ case GK_RV730:
+ case GK_RV710:
+ case GK_RS880:
+ case GK_R630:
+ case GK_R600:
+ break;
+ default:
+ llvm_unreachable("Unhandled GPU!");
+ }
+ }
+}
+
+static bool isWave32Capable(StringRef GPU, const Triple &T) {
+ bool IsWave32Capable = false;
+ // XXX - What does the member GPU mean if device name string passed here?
+ if (T.isAMDGCN()) {
+ switch (parseArchAMDGCN(GPU)) {
+ case GK_GFX1103:
+ case GK_GFX1102:
+ case GK_GFX1101:
+ case GK_GFX1100:
+ case GK_GFX1036:
+ case GK_GFX1035:
+ case GK_GFX1034:
+ case GK_GFX1033:
+ case GK_GFX1032:
+ case GK_GFX1031:
+ case GK_GFX1030:
+ case GK_GFX1012:
+ case GK_GFX1011:
+ case GK_GFX1013:
+ case GK_GFX1010:
+ IsWave32Capable = true;
+ break;
+ default:
+ break;
+ }
+ }
+ return IsWave32Capable;
+}
+
+bool AMDGPU::insertWaveSizeFeature(StringRef GPU, const Triple &T,
+ StringMap<bool> &Features,
+ std::string &ErrorMsg) {
+ bool IsWave32Capable = isWave32Capable(GPU, T);
+ const bool IsNullGPU = GPU.empty();
+ // FIXME: Not diagnosing wavefrontsize32 on wave64 only targets.
+ const bool HaveWave32 =
+ (IsWave32Capable || IsNullGPU) && Features.count("wavefrontsize32");
+ const bool HaveWave64 = Features.count("wavefrontsize64");
+ if (HaveWave32 && HaveWave64) {
+ ErrorMsg = "'wavefrontsize32' and 'wavefrontsize64' are mutually exclusive";
+ return false;
+ }
+ // Don't assume any wavesize with an unknown subtarget.
+ if (!IsNullGPU) {
+ // Default to wave32 if available, or wave64 if not
+ if (!HaveWave32 && !HaveWave64) {
+ StringRef DefaultWaveSizeFeature =
+ IsWave32Capable ? "wavefrontsize32" : "wavefrontsize64";
+ Features.insert(std::make_pair(DefaultWaveSizeFeature, true));
+ }
+ }
+ return true;
+}
Index: llvm/include/llvm/TargetParser/TargetParser.h
===================================================================
--- llvm/include/llvm/TargetParser/TargetParser.h
+++ llvm/include/llvm/TargetParser/TargetParser.h
@@ -14,6 +14,7 @@
#ifndef LLVM_TARGETPARSER_TARGETPARSER_H
#define LLVM_TARGETPARSER_TARGETPARSER_H
+#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringRef.h"
namespace llvm {
@@ -149,6 +150,14 @@
IsaVersion getIsaVersion(StringRef GPU);
+/// Fills Features map with default values for given target GPU
+void fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
+ StringMap<bool> &Features);
+
+/// Inserts wave size feature for given GPU into features map
+bool insertWaveSizeFeature(StringRef GPU, const Triple &T,
+ StringMap<bool> &Features, std::string &ErrorMsg);
+
} // namespace AMDGPU
} // namespace llvm
Index: flang/test/Lower/OpenMP/target_cpu_features.f90
===================================================================
--- /dev/null
+++ flang/test/Lower/OpenMP/target_cpu_features.f90
@@ -0,0 +1,16 @@
+!REQUIRES: amdgpu-registered-target
+!RUN: %flang_fc1 -emit-fir -triple amdgcn-amd-amdhsa -target-cpu gfx908 -fopenmp %s -o - | FileCheck %s
+
+!===============================================================================
+! Target_Enter Simple
+!===============================================================================
+
+!CHECK: omp.target_cpu = "gfx908",
+!CHECK-SAME: omp.target_cpu_features = "+dot3-insts,+dot4-insts,+s-memtime-inst,
+!CHECK-SAME: +16-bit-insts,+s-memrealtime,+dot6-insts,+dl-insts,+wavefrontsize64,
+!CHECK-SAME: +gfx9-insts,+gfx8-insts,+ci-insts,+dot10-insts,+dot7-insts,
+!CHECK-SAME: +dot1-insts,+dot5-insts,+mai-insts,+dpp,+dot2-insts"
+!CHECK-LABEL: func.func @_QPomp_target_simple() {
+subroutine omp_target_simple
+end subroutine omp_target_simple
+
Index: flang/test/Driver/target-cpu-features.f90
===================================================================
--- flang/test/Driver/target-cpu-features.f90
+++ flang/test/Driver/target-cpu-features.f90
@@ -1,4 +1,4 @@
-! REQUIRES: aarch64-registered-target, x86-registered-target
+! REQUIRES: aarch64-registered-target, x86-registered-target, amdgpu-registered-target
! Test that -mcpu/march are used and that the -target-cpu and -target-features
! are also added to the fc1 command.
@@ -22,6 +22,8 @@
! RUN: %flang --target=x86_64h-linux-gnu -c %s -### 2>&1 \
! RUN: | FileCheck %s -check-prefix=CHECK-X86_64H
+! RUN: %flang --target=amdgcn-amd-amdhsa -mcpu=gfx908 -c %s -### 2>&1 \
+! RUN: | FileCheck %s -check-prefix=CHECK-AMDGPU
! Test that invalid cpu and features are ignored.
@@ -52,5 +54,7 @@
! CHECK-X86_64H: "-fc1" "-triple" "x86_64h-unknown-linux-gnu"
! CHECK-X86_64H-SAME: "-target-cpu" "x86-64" "-target-feature" "-rdrnd" "-target-feature" "-aes" "-target-feature" "-pclmul" "-target-feature" "-rtm" "-target-feature" "-fsgsbase"
+! CHECK-AMDGPU: "-fc1" "-triple" "amdgcn-amd-amdhsa"
+! CHECK-AMDGPU-SAME: "-target-cpu" "gfx908"
! CHECK-INVALID-CPU: 'supercpu' is not a recognized processor for this target (ignoring processor)
! CHECK-INVALID-FEATURE: '+superspeed' is not a recognized feature for this target (ignoring feature)
Index: flang/lib/Frontend/FrontendActions.cpp
===================================================================
--- flang/lib/Frontend/FrontendActions.cpp
+++ flang/lib/Frontend/FrontendActions.cpp
@@ -54,6 +54,7 @@
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/SourceMgr.h"
#include "llvm/Target/TargetMachine.h"
+#include "llvm/TargetParser/TargetParser.h"
#include "llvm/Transforms/Utils/ModuleUtils.h"
#include <memory>
@@ -89,6 +90,54 @@
(generateRtTypeTables() || true);
}
+std::string CodeGenAction::getAllTargetFeatures() {
+ std::string allFeaturesStr;
+ CompilerInstance &ci = this->getInstance();
+ const TargetOptions &targetOpts = ci.getInvocation().getTargetOpts();
+ const llvm::Triple triple(targetOpts.triple);
+
+ // Clang does not append all target features to the clang -cc1 invocation.
+ // Some AMDGPU features are passed implicitly by the Clang frontend.
+ // That's why we need to extract implicit AMDGPU target features and add
+ // them to the target features specified by the user
+ if (triple.isAMDGPU()) {
+ llvm::StringRef cpu = targetOpts.cpu;
+ llvm::StringMap<bool> implicitFeaturesMap;
+ std::string errorMsg;
+ // Get the set of implicit target features
+ llvm::AMDGPU::fillAMDGPUFeatureMap(cpu, triple, implicitFeaturesMap);
+ if (!llvm::AMDGPU::insertWaveSizeFeature(cpu, triple, implicitFeaturesMap,
+ errorMsg)) {
+ llvm::SMDiagnostic err;
+ CompilerInstance &ci = this->getInstance();
+ err.print(errorMsg.data(), llvm::errs());
+ unsigned diagID = ci.getDiagnostics().getCustomDiagID(
+ clang::DiagnosticsEngine::Error, "Unsupported feature ID");
+ ci.getDiagnostics().Report(diagID);
+ return allFeaturesStr;
+ }
+
+ // Add target features specified by the user
+ for (auto &userFeature : targetOpts.featuresAsWritten) {
+ std::string userKeyString = userFeature.substr(1);
+ implicitFeaturesMap[userKeyString] = (userFeature[0] == '+');
+ }
+ llvm::SmallVector<std::string> featuresVec;
+ for (auto &implicitFeatureItem : implicitFeaturesMap) {
+ featuresVec.push_back(
+ (llvm::Twine(implicitFeatureItem.second ? "+" : "-") +
+ implicitFeatureItem.first().str())
+ .str());
+ }
+
+ allFeaturesStr = llvm::join(featuresVec, ",");
+ } else {
+ allFeaturesStr = llvm::join(targetOpts.featuresAsWritten.begin(),
+ targetOpts.featuresAsWritten.end(), ",");
+ }
+ return allFeaturesStr;
+}
+
static void setMLIRDataLayout(mlir::ModuleOp &mlirModule,
const llvm::DataLayout &dl) {
mlir::MLIRContext *context = mlirModule.getContext();
@@ -178,13 +227,16 @@
// Fetch module from lb, so we can set
mlirModule = std::make_unique<mlir::ModuleOp>(lb.getModule());
+ setUpTargetMachine();
+
if (ci.getInvocation().getFrontendOpts().features.IsEnabled(
Fortran::common::LanguageFeature::OpenMP)) {
mlir::omp::OpenMPDialect::setIsDevice(
*mlirModule, ci.getInvocation().getLangOpts().OpenMPIsDevice);
+ mlir::omp::OpenMPDialect::setTargetCpu(*mlirModule, tm->getTargetCPU());
+ mlir::omp::OpenMPDialect::setTargetCpuFeatures(
+ *mlirModule, tm->getTargetFeatureString());
}
-
- setUpTargetMachine();
const llvm::DataLayout &dl = tm->createDataLayout();
setMLIRDataLayout(*mlirModule, dl);
@@ -603,8 +655,7 @@
llvm::CodeGenOpt::getLevel(CGOpts.OptimizationLevel);
assert(OptLevelOrNone && "Invalid optimization level!");
llvm::CodeGenOpt::Level OptLevel = *OptLevelOrNone;
- std::string featuresStr = llvm::join(targetOpts.featuresAsWritten.begin(),
- targetOpts.featuresAsWritten.end(), ",");
+ std::string featuresStr = getAllTargetFeatures();
tm.reset(theTarget->createTargetMachine(
theTriple, /*CPU=*/targetOpts.cpu,
/*Features=*/featuresStr, llvm::TargetOptions(),
Index: flang/include/flang/Frontend/FrontendActions.h
===================================================================
--- flang/include/flang/Frontend/FrontendActions.h
+++ flang/include/flang/Frontend/FrontendActions.h
@@ -208,6 +208,8 @@
/// Runs the optimization (aka middle-end) pipeline on the LLVM module
/// associated with this action.
void runOptimizationPipeline(llvm::raw_pwrite_stream &os);
+ /// Produces the string which represents all target features
+ std::string getAllTargetFeatures();
protected:
CodeGenAction(BackendActionTy act) : action{act} {};
Index: clang/lib/Driver/ToolChains/Flang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Flang.cpp
+++ clang/lib/Driver/ToolChains/Flang.cpp
@@ -104,6 +104,10 @@
switch (TC.getArch()) {
default:
break;
+ case llvm::Triple::r600:
+ [[fallthrough]];
+ case llvm::Triple::amdgcn:
+ [[fallthrough]];
case llvm::Triple::aarch64:
[[fallthrough]];
case llvm::Triple::x86_64:
Index: clang/lib/Driver/ToolChains/CommonArgs.cpp
===================================================================
--- clang/lib/Driver/ToolChains/CommonArgs.cpp
+++ clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -331,6 +331,9 @@
.Case("aruba", "cayman")
.Default(GPUName.str());
}
+ if (Arg *A = Args.getLastArg(options::OPT_march_EQ)) {
+ return getProcessorFromTargetID(T, A->getValue()).str();
+ }
return "";
}
Index: clang/lib/Basic/Targets/AMDGPU.cpp
===================================================================
--- clang/lib/Basic/Targets/AMDGPU.cpp
+++ clang/lib/Basic/Targets/AMDGPU.cpp
@@ -179,191 +179,19 @@
bool AMDGPUTargetInfo::initFeatureMap(
llvm::StringMap<bool> &Features, DiagnosticsEngine &Diags, StringRef CPU,
const std::vector<std::string> &FeatureVec) const {
- const bool IsNullCPU = CPU.empty();
- bool IsWave32Capable = false;
using namespace llvm::AMDGPU;
-
- // XXX - What does the member GPU mean if device name string passed here?
- if (isAMDGCN(getTriple())) {
- switch (llvm::AMDGPU::parseArchAMDGCN(CPU)) {
- case GK_GFX1103:
- case GK_GFX1102:
- case GK_GFX1101:
- case GK_GFX1100:
- IsWave32Capable = true;
- Features["ci-insts"] = true;
- Features["dot5-insts"] = true;
- Features["dot7-insts"] = true;
- Features["dot8-insts"] = true;
- Features["dot9-insts"] = true;
- Features["dot10-insts"] = true;
- Features["dl-insts"] = true;
- Features["16-bit-insts"] = true;
- Features["dpp"] = true;
- Features["gfx8-insts"] = true;
- Features["gfx9-insts"] = true;
- Features["gfx10-insts"] = true;
- Features["gfx10-3-insts"] = true;
- Features["gfx11-insts"] = true;
- break;
- case GK_GFX1036:
- case GK_GFX1035:
- case GK_GFX1034:
- case GK_GFX1033:
- case GK_GFX1032:
- case GK_GFX1031:
- case GK_GFX1030:
- IsWave32Capable = true;
- Features["ci-insts"] = true;
- Features["dot1-insts"] = true;
- Features["dot2-insts"] = true;
- Features["dot5-insts"] = true;
- Features["dot6-insts"] = true;
- Features["dot7-insts"] = true;
- Features["dot10-insts"] = true;
- Features["dl-insts"] = true;
- Features["16-bit-insts"] = true;
- Features["dpp"] = true;
- Features["gfx8-insts"] = true;
- Features["gfx9-insts"] = true;
- Features["gfx10-insts"] = true;
- Features["gfx10-3-insts"] = true;
- Features["s-memrealtime"] = true;
- Features["s-memtime-inst"] = true;
- break;
- case GK_GFX1012:
- case GK_GFX1011:
- Features["dot1-insts"] = true;
- Features["dot2-insts"] = true;
- Features["dot5-insts"] = true;
- Features["dot6-insts"] = true;
- Features["dot7-insts"] = true;
- Features["dot10-insts"] = true;
- [[fallthrough]];
- case GK_GFX1013:
- case GK_GFX1010:
- IsWave32Capable = true;
- Features["dl-insts"] = true;
- Features["ci-insts"] = true;
- Features["16-bit-insts"] = true;
- Features["dpp"] = true;
- Features["gfx8-insts"] = true;
- Features["gfx9-insts"] = true;
- Features["gfx10-insts"] = true;
- Features["s-memrealtime"] = true;
- Features["s-memtime-inst"] = true;
- break;
- case GK_GFX940:
- Features["gfx940-insts"] = true;
- Features["fp8-insts"] = true;
- [[fallthrough]];
- case GK_GFX90A:
- Features["gfx90a-insts"] = true;
- [[fallthrough]];
- case GK_GFX908:
- Features["dot3-insts"] = true;
- Features["dot4-insts"] = true;
- Features["dot5-insts"] = true;
- Features["dot6-insts"] = true;
- Features["mai-insts"] = true;
- [[fallthrough]];
- case GK_GFX906:
- Features["dl-insts"] = true;
- Features["dot1-insts"] = true;
- Features["dot2-insts"] = true;
- Features["dot7-insts"] = true;
- Features["dot10-insts"] = true;
- [[fallthrough]];
- case GK_GFX90C:
- case GK_GFX909:
- case GK_GFX904:
- case GK_GFX902:
- case GK_GFX900:
- Features["gfx9-insts"] = true;
- [[fallthrough]];
- case GK_GFX810:
- case GK_GFX805:
- case GK_GFX803:
- case GK_GFX802:
- case GK_GFX801:
- Features["gfx8-insts"] = true;
- Features["16-bit-insts"] = true;
- Features["dpp"] = true;
- Features["s-memrealtime"] = true;
- [[fallthrough]];
- case GK_GFX705:
- case GK_GFX704:
- case GK_GFX703:
- case GK_GFX702:
- case GK_GFX701:
- case GK_GFX700:
- Features["ci-insts"] = true;
- [[fallthrough]];
- case GK_GFX602:
- case GK_GFX601:
- case GK_GFX600:
- Features["s-memtime-inst"] = true;
- break;
- case GK_NONE:
- break;
- default:
- llvm_unreachable("Unhandled GPU!");
- }
- } else {
- if (CPU.empty())
- CPU = "r600";
-
- switch (llvm::AMDGPU::parseArchR600(CPU)) {
- case GK_CAYMAN:
- case GK_CYPRESS:
- case GK_RV770:
- case GK_RV670:
- // TODO: Add fp64 when implemented.
- break;
- case GK_TURKS:
- case GK_CAICOS:
- case GK_BARTS:
- case GK_SUMO:
- case GK_REDWOOD:
- case GK_JUNIPER:
- case GK_CEDAR:
- case GK_RV730:
- case GK_RV710:
- case GK_RS880:
- case GK_R630:
- case GK_R600:
- break;
- default:
- llvm_unreachable("Unhandled GPU!");
- }
- }
-
+ fillAMDGPUFeatureMap(CPU, getTriple(), Features);
if (!TargetInfo::initFeatureMap(Features, Diags, CPU, FeatureVec))
return false;
- // FIXME: Not diagnosing wavefrontsize32 on wave64 only targets.
- const bool HaveWave32 =
- (IsWave32Capable || IsNullCPU) && Features.count("wavefrontsize32");
- const bool HaveWave64 = Features.count("wavefrontsize64");
-
// TODO: Should move this logic into TargetParser
- if (HaveWave32 && HaveWave64) {
- Diags.Report(diag::err_invalid_feature_combination)
- << "'wavefrontsize32' and 'wavefrontsize64' are mutually exclusive";
+ std::string ErrorMsg;
+ if (!insertWaveSizeFeature(CPU, getTriple(), Features, ErrorMsg)) {
+ Diags.Report(diag::err_invalid_feature_combination) << ErrorMsg;
return false;
}
- // Don't assume any wavesize with an unknown subtarget.
- if (!IsNullCPU) {
- // Default to wave32 if available, or wave64 if not
- if (!HaveWave32 && !HaveWave64) {
- StringRef DefaultWaveSizeFeature =
- IsWave32Capable ? "wavefrontsize32" : "wavefrontsize64";
- Features.insert(std::make_pair(DefaultWaveSizeFeature, true));
- }
- }
-
return true;
}
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
