Merge from 'main' to 'sycl-web' (26 commits)

  CONFLICT (content): Merge conflict in libclc/clc/include/clc/clcfunc.h

Author: fzou1

clang/include/clang/Basic/DiagnosticFrontendKinds.td

@@ -115,6 +115,8 @@ def err_fe_unable_to_load_plugin : Error<
     "unable to load plugin '%0': '%1'">;
 def err_fe_unable_to_create_target : Error<
     "unable to create target: '%0'">;
+def err_fe_unable_to_create_subtarget : Error<
+    "unable to create subtarget: '%0'%select{ with features '%2'|}1">;
 def err_fe_unable_to_interface_with_target : Error<
     "unable to interface with target machine">;
 def err_fe_unable_to_open_output : Error<
@@ -132,6 +134,8 @@ def err_fe_no_pch_in_dir : Error<
     "no suitable precompiled header file found in directory '%0'">;
 def err_fe_action_not_available : Error<
     "action %0 not compiled in">;
+def err_fe_cir_not_built : Error<"clang IR support not available, rebuild "
+                                 "clang with -DCLANG_ENABLE_CIR=ON">;
 def err_fe_invalid_multiple_actions : Error<
     "'%0' action ignored; '%1' action specified previously">;
 def err_fe_invalid_alignment : Error<

clang/include/clang/Basic/OffloadArch.h

@@ -104,6 +104,7 @@ enum class OffloadArch {
   GFX1200,
   GFX1201,
   GFX1250,
+  GFX1251,
   AMDGCNSPIRV,
   Generic, // A processor model named 'generic' if the target backend defines a
            // public one.

clang/lib/Basic/OffloadArch.cpp

@@ -91,6 +91,7 @@ static const OffloadArchToStringMap ArchNames[] = {
     GFX(1200), // gfx1200
     GFX(1201), // gfx1201
     GFX(1250), // gfx1250
+    GFX(1251), // gfx1251
     {OffloadArch::AMDGCNSPIRV, "amdgcnspirv", "compute_amdgcn"},
     // Intel CPUs
     {OffloadArch::SKYLAKEAVX512, "skylake-avx512", ""},

clang/lib/Basic/Targets/NVPTX.cpp

@@ -246,6 +246,7 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case OffloadArch::GFX1200:
       case OffloadArch::GFX1201:
       case OffloadArch::GFX1250:
+      case OffloadArch::GFX1251:
       case OffloadArch::AMDGCNSPIRV:
       case OffloadArch::Generic:
       case OffloadArch::GRANITERAPIDS:

clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp

@@ -2336,6 +2336,7 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(const OMPRequiresDecl *D) {
       case OffloadArch::GFX1200:
       case OffloadArch::GFX1201:
       case OffloadArch::GFX1250:
+      case OffloadArch::GFX1251:
       case OffloadArch::AMDGCNSPIRV:
       case OffloadArch::Generic:
       case OffloadArch::GRANITERAPIDS:

clang/lib/FrontendTool/ExecuteCompilerInvocation.cpp

@@ -81,7 +81,8 @@ CreateFrontendBaseAction(CompilerInstance &CI) {
 #if CLANG_ENABLE_CIR
     return std::make_unique<cir::EmitCIRAction>();
 #else
-    llvm_unreachable("CIR suppport not built into clang");
+    CI.getDiagnostics().Report(diag::err_fe_cir_not_built);
+    return nullptr;
 #endif
   case EmitHTML:               return std::make_unique<HTMLPrintAction>();
   case EmitLLVM: {

clang/test/CodeGenOpenCL/amdgpu-features.cl

@@ -53,6 +53,7 @@
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1200 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1200 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1201 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1201 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1250 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1250 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1251 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1251 %s
 
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1103 -target-feature +wavefrontsize64 -emit-llvm -o - %s | FileCheck --check-prefix=GFX1103-W64 %s
 
@@ -109,6 +110,7 @@
 // GFX1200: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 // GFX1201: "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-global-pk-add-bf16-inst,+ci-insts,+dl-insts,+dot10-insts,+dot11-insts,+dot12-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+fp8-conversion-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize32"
 // GFX1250: "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+bf16-cvt-insts,+bf16-pk-insts,+bf16-trans-insts,+bitop3-insts,+ci-insts,+dl-insts,+dot7-insts,+dot8-insts,+dpp,+fp8-conversion-insts,+fp8e5m3-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx1250-insts,+gfx8-insts,+gfx9-insts,+permlane16-swap,+prng-inst,+setprio-inc-wg-inst,+tanh-insts,+tensor-cvt-lut-insts,+transpose-load-f4f6-insts,+vmem-pref-insts,+wavefrontsize32"
+// GFX1251: "target-features"="+16-bit-insts,+ashr-pk-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-buffer-pk-add-bf16-inst,+atomic-ds-pk-add-16-insts,+atomic-fadd-rtn-insts,+atomic-flat-pk-add-16-insts,+atomic-fmin-fmax-global-f32,+atomic-fmin-fmax-global-f64,+atomic-global-pk-add-bf16-inst,+bf16-cvt-insts,+bf16-pk-insts,+bf16-trans-insts,+bitop3-insts,+ci-insts,+dl-insts,+dot7-insts,+dot8-insts,+dpp,+fp8-conversion-insts,+fp8e5m3-insts,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx12-insts,+gfx1250-insts,+gfx8-insts,+gfx9-insts,+permlane16-swap,+prng-inst,+setprio-inc-wg-inst,+tanh-insts,+tensor-cvt-lut-insts,+transpose-load-f4f6-insts,+vmem-pref-insts,+wavefrontsize32"
 
 // GFX1103-W64: "target-features"="+16-bit-insts,+atomic-fadd-rtn-insts,+atomic-fmin-fmax-global-f32,+ci-insts,+dl-insts,+dot10-insts,+dot12-insts,+dot5-insts,+dot7-insts,+dot8-insts,+dot9-insts,+dpp,+gfx10-3-insts,+gfx10-insts,+gfx11-insts,+gfx8-insts,+gfx9-insts,+wavefrontsize64"
 

clang/test/CodeGenOpenCL/builtins-amdgcn-gfx1250-cooperative-atomics.cl

@@ -2,6 +2,7 @@
 
 // REQUIRES: amdgpu-registered-target
 // RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1250 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1251 -emit-llvm -o - %s | FileCheck %s
 
 typedef int    v2i   __attribute__((ext_vector_type(2)));
 typedef int    v4i   __attribute__((ext_vector_type(4)));

clang/test/Driver/amdgpu-macros.cl

@@ -131,6 +131,7 @@
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1200 -DFAMILY=GFX12
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1201 -DFAMILY=GFX12
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1250 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1250 -DFAMILY=GFX12
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1251 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=32 -DCPU=gfx1251 -DFAMILY=GFX12
 
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx9-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=64 -DCPU=gfx9_generic -DFAMILY=GFX9
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx9-4-generic %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,FAST_FMAF %s -DWAVEFRONT_SIZE=64 -DCPU=gfx9_4_generic -DFAMILY=GFX9
@@ -191,6 +192,12 @@
 // RUN:   %s 2>&1 | FileCheck --check-prefix=CUMODE-ON %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx1250 -mno-cumode \
 // RUN:   %s 2>&1 | FileCheck -DMCPU=gfx1250 --check-prefixes=CUMODE-ON,WARN-CUMODE %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1251 \
+// RUN:   %s 2>&1 | FileCheck --check-prefix=CUMODE-ON %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1251 -mcumode \
+// RUN:   %s 2>&1 | FileCheck --check-prefix=CUMODE-ON %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1251 -mno-cumode \
+// RUN:   %s 2>&1 | FileCheck -DMCPU=gfx1251 --check-prefixes=CUMODE-ON,WARN-CUMODE %s
 // WARN-CUMODE-DAG: warning: ignoring '-mno-cumode' option as it is not currently supported for processor '[[MCPU]]' [-Woption-ignored]
 // CUMODE-ON-DAG: #define __AMDGCN_CUMODE__ 1
 // CUMODE-OFF-DAG: #define __AMDGCN_CUMODE__ 0

clang/test/Driver/amdgpu-mcpu.cl

@@ -116,6 +116,7 @@
 // RUN: %clang -### -target amdgcn -mcpu=gfx1200 %s 2>&1 | FileCheck --check-prefix=GFX1200 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1201 %s 2>&1 | FileCheck --check-prefix=GFX1201 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx1250 %s 2>&1 | FileCheck --check-prefix=GFX1250 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1251 %s 2>&1 | FileCheck --check-prefix=GFX1251 %s
 
 // RUN: %clang -### -target amdgcn -mcpu=gfx9-generic %s 2>&1 | FileCheck --check-prefix=GFX9_GENERIC %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx9-4-generic %s 2>&1 | FileCheck --check-prefix=GFX9_4_GENERIC %s
@@ -171,6 +172,7 @@
 // GFX1200:   "-target-cpu" "gfx1200"
 // GFX1201:   "-target-cpu" "gfx1201"
 // GFX1250:   "-target-cpu" "gfx1250"
+// GFX1251:   "-target-cpu" "gfx1251"
 
 // GFX9_GENERIC:      "-target-cpu" "gfx9-generic"
 // GFX9_4_GENERIC:    "-target-cpu" "gfx9-4-generic"