[OpenCL] Fix typos in emitted enqueue kernel function names

[yaxunl]

Summary

Two typos:
vaarg => vararg
get_kernel_preferred_work_group_multiple => get_kernel_preferred_work_group_size_multiple

[b-sumner]

Thanks! Looks good to me.

[Anastasia]

LGTM! Although I think vaarg is common too. :)

lib/CodeGen/CGBuiltin.cpp

         auto *V =
             Builder.CreateZExtOrTrunc(EmitScalarExpr(E->getArg(I)), SizeTy);
         Builder.CreateAlignedStore(
             V, GEP, CGM.getDataLayout().getPrefTypeAlignment(SizeTy));
       }
       return Ptr;
     };
 
-    // Could have events and/or vaargs.
+    // Could have events and/or varargs.
     if (E->getArg(3)->getType()->isBlockPointerType()) {
       // No events passed, but has variadic arguments.
-      Name = "__enqueue_kernel_vaargs";
+      Name = "__enqueue_kernel_varargs";
       auto Info =
           CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(3));
       llvm::Value *Kernel =
           Builder.CreatePointerCast(Info.Kernel, GenericVoidPtrTy);
       auto *Block = Builder.CreatePointerCast(Info.BlockArg, GenericVoidPtrTy);
       auto *PtrToSizeArray = CreateArrayForSizeVar(4);
 
       // Create a vector of the arguments, as well as a constant value to

         return RValue::get(
             Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
                                llvm::ArrayRef<llvm::Value *>(Args)));
       }
       // Has event info and variadics
       // Pass the number of variadics to the runtime function too.
       Args.push_back(ConstantInt::get(Int32Ty, NumArgs - 7));
       ArgTys.push_back(Int32Ty);
-      Name = "__enqueue_kernel_events_vaargs";
+      Name = "__enqueue_kernel_events_varargs";
 
       auto *PtrToSizeArray = CreateArrayForSizeVar(7);
       Args.push_back(PtrToSizeArray);
       ArgTys.push_back(PtrToSizeArray->getType());
 
       llvm::FunctionType *FTy = llvm::FunctionType::get(
           Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
       return RValue::get(

     auto Info =
         CGM.getOpenCLRuntime().emitOpenCLEnqueuedBlock(*this, E->getArg(0));
     Value *Kernel = Builder.CreatePointerCast(Info.Kernel, GenericVoidPtrTy);
     Value *Arg = Builder.CreatePointerCast(Info.BlockArg, GenericVoidPtrTy);
     return RValue::get(Builder.CreateCall(
         CGM.CreateRuntimeFunction(
             llvm::FunctionType::get(IntTy, {GenericVoidPtrTy, GenericVoidPtrTy},
                                     false),
-            "__get_kernel_preferred_work_group_multiple_impl"),
+            "__get_kernel_preferred_work_group_size_multiple_impl"),
         {Kernel, Arg}));
   }
   case Builtin::BIget_kernel_max_sub_group_size_for_ndrange:
   case Builtin::BIget_kernel_sub_group_count_for_ndrange: {
     llvm::Type *GenericVoidPtrTy = Builder.getInt8PtrTy(
         getContext().getTargetAddressSpace(LangAS::opencl_generic));
     LValue NDRangeL = EmitAggExprToLValue(E->getArg(0));
     llvm::Value *NDRange = NDRangeL.getAddress().getPointer();

test/CodeGenOpenCL/cl20-device-side-enqueue.cl

kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // B32: %[[TMP:.*]] = alloca [1 x i32]
   // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0
   // B32: store i32 256, i32* %[[TMP1]], align 4
   // B64: %[[TMP:.*]] = alloca [1 x i64]
   // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0
   // B64: store i64 256, i64* %[[TMP1]], align 8
-  // COMMON-LABEL: call i32 @__enqueue_kernel_vaargs(
+  // COMMON-LABEL: call i32 @__enqueue_kernel_varargs(
   // COMMON-SAME: %opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}},
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK1:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG1]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1,
   // B32-SAME: i32* %[[TMP1]])
   // B64-SAME: i64* %[[TMP1]])
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(local void *p) {
                    return;
                  },
                  256);
   char c;
   // Emits global block literal [[BLG2]] and block kernel [[INVGK2]].
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // B32: %[[TMP:.*]] = alloca [1 x i32]
   // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0
   // B32: store i32 %{{.*}}, i32* %[[TMP1]], align 4
   // B64: %[[TMP:.*]] = alloca [1 x i64]
   // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0
   // B64: store i64 %{{.*}}, i64* %[[TMP1]], align 8
-  // COMMON-LABEL: call i32 @__enqueue_kernel_vaargs(
+  // COMMON-LABEL: call i32 @__enqueue_kernel_varargs(
   // COMMON-SAME: %opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}},
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK2:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG2]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1,
   // B32-SAME: i32* %[[TMP1]])
   // B64-SAME: i64* %[[TMP1]])
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(local void *p) {
                    return;
                  },
                  c);
 
   // Emits global block literal [[BLG3]] and block kernel [[INVGK3]].
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[AD:%arraydecay[0-9]*]] = getelementptr inbounds [1 x %opencl.clk_event_t*], [1 x %opencl.clk_event_t*]* %event_wait_list2, i32 0, i32 0
   // COMMON: [[WAIT_EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** [[AD]] to %opencl.clk_event_t{{.*}}* addrspace(4)*
   // COMMON: [[EVNT:%[0-9]+]]  = addrspacecast %opencl.clk_event_t{{.*}}** %clk_event to %opencl.clk_event_t{{.*}}* addrspace(4)*
   // B32: %[[TMP:.*]] = alloca [1 x i32]
   // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0
   // B32: store i32 256, i32* %[[TMP1]], align 4
   // B64: %[[TMP:.*]] = alloca [1 x i64]
   // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0
   // B64: store i64 256, i64* %[[TMP1]], align 8
-  // COMMON-LABEL: call i32 @__enqueue_kernel_events_vaargs
+  // COMMON-LABEL: call i32 @__enqueue_kernel_events_varargs
   // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}} [[WAIT_EVNT]], %opencl.clk_event_t{{.*}} [[EVNT]],
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK3:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG3]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1,
   // B32-SAME: i32* %[[TMP1]])
   // B64-SAME: i64* %[[TMP1]])
   enqueue_kernel(default_queue, flags, ndrange, 2, event_wait_list2, &clk_event,
                  ^(local void *p) {
                    return;
                  },
                  256);
 
   // Emits global block literal [[BLG4]] and block kernel [[INVGK4]].
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // COMMON: [[AD:%arraydecay[0-9]*]] = getelementptr inbounds [1 x %opencl.clk_event_t*], [1 x %opencl.clk_event_t*]* %event_wait_list2, i32 0, i32 0
   // COMMON: [[WAIT_EVNT:%[0-9]+]] = addrspacecast %opencl.clk_event_t{{.*}}** [[AD]] to %opencl.clk_event_t{{.*}}* addrspace(4)*
   // COMMON: [[EVNT:%[0-9]+]]  = addrspacecast %opencl.clk_event_t{{.*}}** %clk_event to %opencl.clk_event_t{{.*}}* addrspace(4)*
   // B32: %[[TMP:.*]] = alloca [1 x i32]
   // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0
   // B32: store i32 %{{.*}}, i32* %[[TMP1]], align 4
   // B64: %[[TMP:.*]] = alloca [1 x i64]
   // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0
   // B64: store i64 %{{.*}}, i64* %[[TMP1]], align 8
-  // COMMON-LABEL: call i32 @__enqueue_kernel_events_vaargs
+  // COMMON-LABEL: call i32 @__enqueue_kernel_events_varargs
   // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]],  %struct.ndrange_t* {{.*}}, i32 2, %opencl.clk_event_t{{.*}}* addrspace(4)* [[WAIT_EVNT]], %opencl.clk_event_t{{.*}}* addrspace(4)* [[EVNT]],
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK4:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG4]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1,
   // B32-SAME: i32* %[[TMP1]])
   // B64-SAME: i64* %[[TMP1]])
   enqueue_kernel(default_queue, flags, ndrange, 2, event_wait_list2, &clk_event,
                  ^(local void *p) {
                    return;
                  },
                  c);
 
   long l;
   // Emits global block literal [[BLG5]] and block kernel [[INVGK5]].
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t{{.*}}*, %opencl.queue_t{{.*}}** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // B32: %[[TMP:.*]] = alloca [1 x i32]
   // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0
   // B32: store i32 %{{.*}}, i32* %[[TMP1]], align 4
   // B64: %[[TMP:.*]] = alloca [1 x i64]
   // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0
   // B64: store i64 %{{.*}}, i64* %[[TMP1]], align 8
-  // COMMON-LABEL: call i32 @__enqueue_kernel_vaargs
+  // COMMON-LABEL: call i32 @__enqueue_kernel_varargs
   // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}},
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK5:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG5]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1,
   // B32-SAME: i32* %[[TMP1]])
   // B64-SAME: i64* %[[TMP1]])
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(local void *p) {
                    return;
kernel void device_side_enqueue(global int *a, global int *b, int i) {
   // B32: store i32 4, i32* %[[TMP3]], align 4
   // B64: %[[TMP:.*]] = alloca [3 x i64]
   // B64: %[[TMP1:.*]] = getelementptr [3 x i64], [3 x i64]* %[[TMP]], i32 0, i32 0
   // B64: store i64 1, i64* %[[TMP1]], align 8
   // B64: %[[TMP2:.*]] = getelementptr [3 x i64], [3 x i64]* %[[TMP]], i32 0, i32 1
   // B64: store i64 2, i64* %[[TMP2]], align 8
   // B64: %[[TMP3:.*]] = getelementptr [3 x i64], [3 x i64]* %[[TMP]], i32 0, i32 2
   // B64: store i64 4, i64* %[[TMP3]], align 8
-  // COMMON-LABEL: call i32 @__enqueue_kernel_vaargs
+  // COMMON-LABEL: call i32 @__enqueue_kernel_varargs
   // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}},
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK6:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG6]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 3,
   // B32-SAME: i32* %[[TMP1]])
   // B64-SAME: i64* %[[TMP1]])
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(local void *p1, local void *p2, local void *p3) {
                    return;
                  },
                  1, 2, 4);
 
   // Emits global block literal [[BLG7]] and block kernel [[INVGK7]].
   // COMMON: [[DEF_Q:%[0-9]+]] = load %opencl.queue_t*, %opencl.queue_t** %default_queue
   // COMMON: [[FLAGS:%[0-9]+]] = load i32, i32* %flags
   // B32: %[[TMP:.*]] = alloca [1 x i32]
   // B32: %[[TMP1:.*]] = getelementptr [1 x i32], [1 x i32]* %[[TMP]], i32 0, i32 0
   // B32: store i32 0, i32* %[[TMP1]], align 4
   // B64: %[[TMP:.*]] = alloca [1 x i64]
   // B64: %[[TMP1:.*]] = getelementptr [1 x i64], [1 x i64]* %[[TMP]], i32 0, i32 0
   // B64: store i64 4294967296, i64* %[[TMP1]], align 8
-  // COMMON-LABEL: call i32 @__enqueue_kernel_vaargs
+  // COMMON-LABEL: call i32 @__enqueue_kernel_varargs
   // COMMON-SAME: (%opencl.queue_t{{.*}}* [[DEF_Q]], i32 [[FLAGS]], %struct.ndrange_t* [[NDR]]{{([0-9]+)?}},
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK7:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG7]] to i8 addrspace(1)*) to i8 addrspace(4)*), i32 1,
   // B32-SAME: i32* %[[TMP1]])
   // B64-SAME: i64* %[[TMP1]])
   enqueue_kernel(default_queue, flags, ndrange,
                  ^(local void *p) {
                    return;
kernel void device_side_enqueue(global int *a, global int *b, int i) {
 
   // Emits global block literal [[BLG9]] and block kernel [[INVGK9]]. [[INVGK9]] calls [[INVG9]].
   // COMMON: call i32 @__get_kernel_work_group_size_impl(
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK9:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG9]] to i8 addrspace(1)*) to i8 addrspace(4)*))
   size = get_kernel_work_group_size(block_B);
 
   // Uses global block literal [[BLG8]] and block kernel [[INVGK8]]. Make sure no redundant block literal ind invoke functions are emitted.
-  // COMMON: call i32 @__get_kernel_preferred_work_group_multiple_impl(
+  // COMMON: call i32 @__get_kernel_preferred_work_group_size_multiple_impl(
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK8]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG8]] to i8 addrspace(1)*) to i8 addrspace(4)*))
   size = get_kernel_preferred_work_group_size_multiple(block_A);
 
   // Uses global block literal [[BL_GLOBAL]] and block kernel [[INV_G_K]]. [[INV_G_K]] calls [[INV_G]].
-  // COMMON: call i32 @__get_kernel_preferred_work_group_multiple_impl(
+  // COMMON: call i32 @__get_kernel_preferred_work_group_size_multiple_impl(
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INV_G_K:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BL_GLOBAL]] to i8 addrspace(1)*) to i8 addrspace(4)*))
   size = get_kernel_preferred_work_group_size_multiple(block_G);
 
   // Emits global block literal [[BLG10]] and block kernel [[INVGK10]].
   // COMMON: call i32 @__get_kernel_max_sub_group_size_for_ndrange_impl(%struct.ndrange_t* {{[^,]+}},
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8* bitcast ({{.*}} [[INVGK10:[^ ]+_kernel]] to i8*) to i8 addrspace(4)*),
   // COMMON-SAME: i8 addrspace(4)* addrspacecast (i8 addrspace(1)* bitcast ({ i32, i32 } addrspace(1)* [[BLG10]] to i8 addrspace(1)*) to i8 addrspace(4)*))