Merge from 'main' to 'sycl-web' (5 commits)

vmaksimo · vmaksimo · commit 0bb1bbb5d2ab · 2025-07-29T04:50:35.000-07:00
CONFLICT (content): Merge conflict in clang/lib/Driver/Driver.cpp
diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
@@ -7909,7 +7909,13 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
     // Compiling HIP in device-only non-RDC mode requires linking each action
     // individually.
     for (Action *&A : DeviceActions) {
-      if ((A->getType() != types::TY_Object &&
+      // Special handling for the HIP SPIR-V toolchain because it doesn't use
+      // the SPIR-V backend yet doesn't report the output as an object.
+      bool IsAMDGCNSPIRV = A->getOffloadingToolChain() &&
+                           A->getOffloadingToolChain()->getTriple().getOS() ==
+                               llvm::Triple::OSType::AMDHSA &&
+                           A->getOffloadingToolChain()->getTriple().isSPIRV();
+      if ((A->getType() != types::TY_Object && !IsAMDGCNSPIRV &&
            A->getType() != types::TY_LTO_BC) ||
           !HIPNoRDC || !offloadDeviceOnly())
         continue;
@@ -7980,8 +7986,9 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
     // fatbinary for each translation unit, linking each input individually.
     Action *FatbinAction =
         C.MakeAction<LinkJobAction>(OffloadActions, types::TY_HIP_FATBIN);
-    DDep.add(*FatbinAction, *C.getSingleOffloadToolChain<Action::OFK_HIP>(),
-             nullptr, Action::OFK_HIP);
+    DDep.add(*FatbinAction,
+             *C.getOffloadToolChains<Action::OFK_HIP>().first->second, nullptr,
+             Action::OFK_HIP);
   } else if (C.isOffloadingHostKind(Action::OFK_SYCL) &&
              Args.hasArg(options::OPT_fsyclbin_EQ)) {
     // With '-fsyclbin', package all the offloading actions into a single output
diff --git a/clang/test/Driver/hip-phases.hip b/clang/test/Driver/hip-phases.hip
@@ -675,3 +675,26 @@
 // DEVICE-ONLY-NEXT: 2: compiler, {1}, ir, (device-hip, gfx90a)
 // DEVICE-ONLY-NEXT: 3: backend, {2}, ir, (device-hip, gfx90a)
 // DEVICE-ONLY-NEXT: 4: offload, "device-hip (amdgcn-amd-amdhsa:gfx90a)" {3}, none
+
+//
+// Test the new driver when not bundling
+//
+// RUN: %clang -### --target=x86_64-linux-gnu --offload-new-driver -ccc-print-phases \
+// RUN:        --offload-device-only --offload-arch=amdgcnspirv,gfx1030 %s 2>&1 \
+// RUN: | FileCheck -check-prefix=SPIRV-ONLY %s
+//      SPIRV-ONLY: 0: input, "[[INPUT:.+]]", hip, (device-hip, gfx1030)
+// SPIRV-ONLY-NEXT: 1: preprocessor, {0}, hip-cpp-output, (device-hip, gfx1030)
+// SPIRV-ONLY-NEXT: 2: compiler, {1}, ir, (device-hip, gfx1030)
+// SPIRV-ONLY-NEXT: 3: backend, {2}, assembler, (device-hip, gfx1030)
+// SPIRV-ONLY-NEXT: 4: assembler, {3}, object, (device-hip, gfx1030)
+// SPIRV-ONLY-NEXT: 5: linker, {4}, image, (device-hip, gfx1030)
+// SPIRV-ONLY-NEXT: 6: offload, "device-hip (amdgcn-amd-amdhsa:gfx1030)" {5}, image
+// SPIRV-ONLY-NEXT: 7: input, "[[INPUT]]", hip, (device-hip, amdgcnspirv)
+// SPIRV-ONLY-NEXT: 8: preprocessor, {7}, hip-cpp-output, (device-hip, amdgcnspirv)
+// SPIRV-ONLY-NEXT: 9: compiler, {8}, ir, (device-hip, amdgcnspirv)
+// SPIRV-ONLY-NEXT: 10: backend, {9}, assembler, (device-hip, amdgcnspirv)
+// SPIRV-ONLY-NEXT: 11: assembler, {10}, object, (device-hip, amdgcnspirv)
+// SPIRV-ONLY-NEXT: 12: linker, {11}, image, (device-hip, amdgcnspirv)
+// SPIRV-ONLY-NEXT: 13: offload, "device-hip (spirv64-amd-amdhsa:amdgcnspirv)" {12}, image
+// SPIRV-ONLY-NEXT: 14: linker, {6, 13}, hip-fatbin, (device-hip)
+// SPIRV-ONLY-NEXT: 15: offload, "device-hip (amdgcn-amd-amdhsa)" {14}, none
diff --git a/llvm/lib/Transforms/Utils/Local.cpp b/llvm/lib/Transforms/Utils/Local.cpp
@@ -482,16 +482,11 @@ bool llvm::wouldInstructionBeTriviallyDead(const Instruction *I,
 
     if (II->isLifetimeStartOrEnd()) {
       auto *Arg = II->getArgOperand(1);
-      // Lifetime intrinsics are dead when their right-hand is undef.
-      if (isa<UndefValue>(Arg))
-        return true;
-      // If the right-hand is an alloc, global, or argument and the only uses
-      // are lifetime intrinsics then the intrinsics are dead.
-      if (isa<AllocaInst>(Arg) || isa<GlobalValue>(Arg) || isa<Argument>(Arg))
-        return llvm::all_of(Arg->uses(), [](Use &Use) {
-          return isa<LifetimeIntrinsic>(Use.getUser());
-        });
-      return false;
+      // If the only uses of the alloca are lifetime intrinsics, then the
+      // intrinsics are dead.
+      return llvm::all_of(Arg->uses(), [](Use &Use) {
+        return isa<LifetimeIntrinsic>(Use.getUser());
+      });
     }
 
     // Assumptions are dead if their condition is trivially true.
diff --git a/llvm/lib/Transforms/Vectorize/VPlan.h b/llvm/lib/Transforms/Vectorize/VPlan.h
@@ -2335,8 +2335,9 @@ class LLVM_ABI_FOR_TEST VPBlendRecipe : public VPSingleDefRecipe {
     return Idx == 0 ? getOperand(1) : getOperand(Idx * 2 + !isNormalized());
   }
 
-  /// Generate the phi/select nodes.
-  void execute(VPTransformState &State) override;
+  void execute(VPTransformState &State) override {
+    llvm_unreachable("VPBlendRecipe should be expanded by simplifyBlends");
+  }
 
   /// Return the cost of this VPWidenMemoryRecipe.
   InstructionCost computeCost(ElementCount VF,
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
@@ -2411,42 +2411,6 @@ void VPVectorPointerRecipe::print(raw_ostream &O, const Twine &Indent,
 }
 #endif
 
-void VPBlendRecipe::execute(VPTransformState &State) {
-  assert(isNormalized() && "Expected blend to be normalized!");
-  // We know that all PHIs in non-header blocks are converted into
-  // selects, so we don't have to worry about the insertion order and we
-  // can just use the builder.
-  // At this point we generate the predication tree. There may be
-  // duplications since this is a simple recursive scan, but future
-  // optimizations will clean it up.
-
-  unsigned NumIncoming = getNumIncomingValues();
-
-  // Generate a sequence of selects of the form:
-  // SELECT(Mask3, In3,
-  //        SELECT(Mask2, In2,
-  //               SELECT(Mask1, In1,
-  //                      In0)))
-  // Note that Mask0 is never used: lanes for which no path reaches this phi and
-  // are essentially undef are taken from In0.
-  bool OnlyFirstLaneUsed = vputils::onlyFirstLaneUsed(this);
-  Value *Result = nullptr;
-  for (unsigned In = 0; In < NumIncoming; ++In) {
-    // We might have single edge PHIs (blocks) - use an identity
-    // 'select' for the first PHI operand.
-    Value *In0 = State.get(getIncomingValue(In), OnlyFirstLaneUsed);
-    if (In == 0)
-      Result = In0; // Initialize with the first incoming value.
-    else {
-      // Select between the current value and the previous incoming edge
-      // based on the incoming mask.
-      Value *Cond = State.get(getMask(In), OnlyFirstLaneUsed);
-      Result = State.Builder.CreateSelect(Cond, In0, Result, "predphi");
-    }
-  }
-  State.set(this, Result, OnlyFirstLaneUsed);
-}
-
 InstructionCost VPBlendRecipe::computeCost(ElementCount VF,
                                            VPCostContext &Ctx) const {
   // Handle cases where only the first lane is used the same way as the legacy
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -2711,6 +2711,18 @@ void VPlanTransforms::convertToConcreteRecipes(VPlan &Plan,
         continue;
       }
 
+      // Expand VPBlendRecipe into VPInstruction::Select.
+      VPBuilder Builder(&R);
+      if (auto *Blend = dyn_cast<VPBlendRecipe>(&R)) {
+        VPValue *Select = Blend->getIncomingValue(0);
+        for (unsigned I = 1; I != Blend->getNumIncomingValues(); ++I)
+          Select = Builder.createSelect(Blend->getMask(I),
+                                        Blend->getIncomingValue(I), Select,
+                                        R.getDebugLoc(), "predphi");
+        Blend->replaceAllUsesWith(Select);
+        ToRemove.push_back(Blend);
+      }
+
       if (auto *Expr = dyn_cast<VPExpressionRecipe>(&R)) {
         Expr->decompose();
         ToRemove.push_back(Expr);
@@ -2724,7 +2736,6 @@ void VPlanTransforms::convertToConcreteRecipes(VPlan &Plan,
 
       // Expand WideIVStep.
       auto *VPI = cast<VPInstruction>(&R);
-      VPBuilder Builder(VPI);
       Type *IVTy = TypeInfo.inferScalarType(VPI);
       if (TypeInfo.inferScalarType(VectorStep) != IVTy) {
         Instruction::CastOps CastOp = IVTy->isFloatingPointTy()
diff --git a/llvm/test/CodeGen/AMDGPU/wait-xcnt.mir b/llvm/test/CodeGen/AMDGPU/wait-xcnt.mir
@@ -966,3 +966,45 @@ body: |
     $vgpr2 = V_MOV_B32_e32 $vgpr2, implicit $exec
     $sgpr0 = S_MOV_B32 0
 ...
+
+# TODO: Unnecessary wait before overwriting vgpr0.
+---
+name: overwrite_vgpr_after_smem
+tracksRegLiveness: true
+machineFunctionInfo:
+  isEntryFunction: true
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $sgpr0_sgpr1
+    ; GCN-LABEL: name: overwrite_vgpr_after_smem
+    ; GCN: liveins: $vgpr0_vgpr1, $sgpr0_sgpr1
+    ; GCN-NEXT: {{  $}}
+    ; GCN-NEXT: $vgpr2 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec
+    ; GCN-NEXT: $sgpr2 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 0, 0
+    ; GCN-NEXT: S_WAIT_XCNT 0
+    ; GCN-NEXT: $vgpr0 = V_MOV_B32_e32 0, implicit $exec
+    $vgpr2 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec
+    $sgpr2 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 0, 0
+    $vgpr0 = V_MOV_B32_e32 0, implicit $exec
+...
+
+# TODO: Unnecessary wait before overwriting sgpr0.
+---
+name: overwrite_sgpr_after_vmem
+tracksRegLiveness: true
+machineFunctionInfo:
+  isEntryFunction: true
+body: |
+  bb.0:
+    liveins: $vgpr0_vgpr1, $sgpr0_sgpr1
+    ; GCN-LABEL: name: overwrite_sgpr_after_vmem
+    ; GCN: liveins: $vgpr0_vgpr1, $sgpr0_sgpr1
+    ; GCN-NEXT: {{  $}}
+    ; GCN-NEXT: $sgpr2 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 0, 0
+    ; GCN-NEXT: $vgpr2 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec
+    ; GCN-NEXT: S_WAIT_XCNT 0
+    ; GCN-NEXT: $sgpr0 = S_MOV_B32 0
+    $sgpr2 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 0, 0
+    $vgpr2 = GLOBAL_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec
+    $sgpr0 = S_MOV_B32 0
+...
diff --git a/llvm/test/Transforms/Inline/inlined-mustprogress-loop-metadata.ll b/llvm/test/Transforms/Inline/inlined-mustprogress-loop-metadata.ll
