[OpenCL] Augment pipe built-ins with pipe packet size and alignment.

[bader]

Summary

Keep pipe packet size and alignment in LLVM IR layer to enable
translation from LLVM IR to SPIR-V format.

[Anastasia]

lib/CodeGen/CGOpenCLRuntime.cpp

97

Perhaps it's safer to use getTypeSizeInChars instead? Even though most of architectures should have an 8-bit byte, it will allow us to avoid having hard-coded numbers.

[bader]

Applied code review comment from Anastasia.

Use getTypeSizeInChars instead of getTypeSize to get type size in bytes. Assume that char size is always one byte.

[Anastasia]

LGTM! Thanks!

[bader]

Valery, do you have any additional comments/questions regarding this patch?

[vpykhtin]

Sorry for a deeeeeelaaaaaaaaay, LGTM either.

lib/CodeGen/CGBuiltin.cpp

 //===---- CGBuiltin.cpp - Emit LLVM Code for builtins ---------------------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 // This contains code to emit Builtin calls as LLVM code.
 //
 //===----------------------------------------------------------------------===//
 
 #include "CodeGenFunction.h"
 #include "CGCXXABI.h"
 #include "CGObjCRuntime.h"
+#include "CGOpenCLRuntime.h"
 #include "CodeGenModule.h"
 #include "TargetInfo.h"
 #include "clang/AST/ASTContext.h"
 #include "clang/AST/Decl.h"
 #include "clang/Basic/TargetBuiltins.h"
 #include "clang/Basic/TargetInfo.h"
 #include "clang/CodeGen/CGFunctionInfo.h"
 #include "llvm/ADT/StringExtras.h"
case Builtin::BI__GetExceptionInfo: {
     break;
   }
 
   // OpenCL v2.0 s6.13.16.2, Built-in pipe read and write functions
   case Builtin::BIread_pipe:
   case Builtin::BIwrite_pipe: {
     Value *Arg0 = EmitScalarExpr(E->getArg(0)),
           *Arg1 = EmitScalarExpr(E->getArg(1));
+    CGOpenCLRuntime OpenCLRT(CGM);
+    Value *PacketSize = OpenCLRT.getPipeElemSize(E->getArg(0));
+    Value *PacketAlign = OpenCLRT.getPipeElemAlign(E->getArg(0));
 
     // Type of the generic packet parameter.
     unsigned GenericAS =
         getContext().getTargetAddressSpace(LangAS::opencl_generic);
     llvm::Type *I8PTy = llvm::PointerType::get(
         llvm::Type::getInt8Ty(getLLVMContext()), GenericAS);
 
     // Testing which overloaded version we should generate the call for.
     if (2U == E->getNumArgs()) {
       const char *Name = (BuiltinID == Builtin::BIread_pipe) ? "__read_pipe_2"
                                                              : "__write_pipe_2";
       // Creating a generic function type to be able to call with any builtin or
       // user defined type.
-      llvm::Type *ArgTys[] = {Arg0->getType(), I8PTy};
+      llvm::Type *ArgTys[] = {Arg0->getType(), I8PTy, Int32Ty, Int32Ty};
       llvm::FunctionType *FTy = llvm::FunctionType::get(
           Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
       Value *BCast = Builder.CreatePointerCast(Arg1, I8PTy);
-      return RValue::get(Builder.CreateCall(
-          CGM.CreateRuntimeFunction(FTy, Name), {Arg0, BCast}));
+      return RValue::get(
+          Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
+                             {Arg0, BCast, PacketSize, PacketAlign}));
     } else {
       assert(4 == E->getNumArgs() &&
              "Illegal number of parameters to pipe function");
       const char *Name = (BuiltinID == Builtin::BIread_pipe) ? "__read_pipe_4"
                                                              : "__write_pipe_4";
 
-      llvm::Type *ArgTys[] = {Arg0->getType(), Arg1->getType(), Int32Ty, I8PTy};
+      llvm::Type *ArgTys[] = {Arg0->getType(), Arg1->getType(), Int32Ty, I8PTy,
+                              Int32Ty, Int32Ty};
       Value *Arg2 = EmitScalarExpr(E->getArg(2)),
             *Arg3 = EmitScalarExpr(E->getArg(3));
       llvm::FunctionType *FTy = llvm::FunctionType::get(
           Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
       Value *BCast = Builder.CreatePointerCast(Arg3, I8PTy);
       // We know the third argument is an integer type, but we may need to cast
       // it to i32.
       if (Arg2->getType() != Int32Ty)
         Arg2 = Builder.CreateZExtOrTrunc(Arg2, Int32Ty);
       return RValue::get(Builder.CreateCall(
-          CGM.CreateRuntimeFunction(FTy, Name), {Arg0, Arg1, Arg2, BCast}));
+          CGM.CreateRuntimeFunction(FTy, Name),
+          {Arg0, Arg1, Arg2, BCast, PacketSize, PacketAlign}));
     }
   }
   // OpenCL v2.0 s6.13.16 ,s9.17.3.5 - Built-in pipe reserve read and write
   // functions
   case Builtin::BIreserve_read_pipe:
   case Builtin::BIreserve_write_pipe:
   case Builtin::BIwork_group_reserve_read_pipe:
   case Builtin::BIwork_group_reserve_write_pipe:
case Builtin::BIsub_group_reserve_write_pipe: {
     else if (BuiltinID == Builtin::BIsub_group_reserve_read_pipe)
       Name = "__sub_group_reserve_read_pipe";
     else
       Name = "__sub_group_reserve_write_pipe";
 
     Value *Arg0 = EmitScalarExpr(E->getArg(0)),
           *Arg1 = EmitScalarExpr(E->getArg(1));
     llvm::Type *ReservedIDTy = ConvertType(getContext().OCLReserveIDTy);
+    CGOpenCLRuntime OpenCLRT(CGM);
+    Value *PacketSize = OpenCLRT.getPipeElemSize(E->getArg(0));
+    Value *PacketAlign = OpenCLRT.getPipeElemAlign(E->getArg(0));
 
     // Building the generic function prototype.
-    llvm::Type *ArgTys[] = {Arg0->getType(), Int32Ty};
+    llvm::Type *ArgTys[] = {Arg0->getType(), Int32Ty, Int32Ty, Int32Ty};
     llvm::FunctionType *FTy = llvm::FunctionType::get(
         ReservedIDTy, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
     // We know the second argument is an integer type, but we may need to cast
     // it to i32.
     if (Arg1->getType() != Int32Ty)
       Arg1 = Builder.CreateZExtOrTrunc(Arg1, Int32Ty);
     return RValue::get(
-        Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name), {Arg0, Arg1}));
+        Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
+                           {Arg0, Arg1, PacketSize, PacketAlign}));
   }
   // OpenCL v2.0 s6.13.16, s9.17.3.5 - Built-in pipe commit read and write
   // functions
   case Builtin::BIcommit_read_pipe:
   case Builtin::BIcommit_write_pipe:
   case Builtin::BIwork_group_commit_read_pipe:
   case Builtin::BIwork_group_commit_write_pipe:
   case Builtin::BIsub_group_commit_read_pipe:
else if (BuiltinID == Builtin::BIwork_group_commit_write_pipe)
       Name = "__work_group_commit_write_pipe";
     else if (BuiltinID == Builtin::BIsub_group_commit_read_pipe)
       Name = "__sub_group_commit_read_pipe";
     else
       Name = "__sub_group_commit_write_pipe";
 
     Value *Arg0 = EmitScalarExpr(E->getArg(0)),
           *Arg1 = EmitScalarExpr(E->getArg(1));
+    CGOpenCLRuntime OpenCLRT(CGM);
+    Value *PacketSize = OpenCLRT.getPipeElemSize(E->getArg(0));
+    Value *PacketAlign = OpenCLRT.getPipeElemAlign(E->getArg(0));
 
     // Building the generic function prototype.
-    llvm::Type *ArgTys[] = {Arg0->getType(), Arg1->getType()};
+    llvm::Type *ArgTys[] = {Arg0->getType(), Arg1->getType(), Int32Ty, Int32Ty};
     llvm::FunctionType *FTy =
         llvm::FunctionType::get(llvm::Type::getVoidTy(getLLVMContext()),
                                 llvm::ArrayRef<llvm::Type *>(ArgTys), false);
 
     return RValue::get(
-        Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name), {Arg0, Arg1}));
+        Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
+                           {Arg0, Arg1, PacketSize, PacketAlign}));
   }
   // OpenCL v2.0 s6.13.16.4 Built-in pipe query functions
   case Builtin::BIget_pipe_num_packets:
   case Builtin::BIget_pipe_max_packets: {
     const char *Name;
     if (BuiltinID == Builtin::BIget_pipe_num_packets)
       Name = "__get_pipe_num_packets";
     else
       Name = "__get_pipe_max_packets";
 
     // Building the generic function prototype.
     Value *Arg0 = EmitScalarExpr(E->getArg(0));
-    llvm::Type *ArgTys[] = {Arg0->getType()};
+    CGOpenCLRuntime OpenCLRT(CGM);
+    Value *PacketSize = OpenCLRT.getPipeElemSize(E->getArg(0));
+    Value *PacketAlign = OpenCLRT.getPipeElemAlign(E->getArg(0));
+    llvm::Type *ArgTys[] = {Arg0->getType(), Int32Ty, Int32Ty};
     llvm::FunctionType *FTy = llvm::FunctionType::get(
         Int32Ty, llvm::ArrayRef<llvm::Type *>(ArgTys), false);
 
-    return RValue::get(
-        Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name), {Arg0}));
+    return RValue::get(Builder.CreateCall(CGM.CreateRuntimeFunction(FTy, Name),
+                                          {Arg0, PacketSize, PacketAlign}));
   }
 
   // OpenCL v2.0 s6.13.9 - Address space qualifier functions.
   case Builtin::BIto_global:
   case Builtin::BIto_local:
   case Builtin::BIto_private: {
     auto Arg0 = EmitScalarExpr(E->getArg(0));
     auto NewArgT = llvm::PointerType::get(Int8Ty,

lib/CodeGen/CGOpenCLRuntime.h

public:
   virtual void EmitWorkGroupLocalVarDecl(CodeGenFunction &CGF,
                                          const VarDecl &D);
 
   virtual llvm::Type *convertOpenCLSpecificType(const Type *T);
 
   virtual llvm::Type *getPipeType();
 
   llvm::PointerType *getSamplerType();
+
+  // \brief Returnes a value which indicates the size in bytes of the pipe
+  // element.
+  virtual llvm::Value *getPipeElemSize(const Expr *PipeArg);
+
+  // \brief Returnes a value which indicates the alignment in bytes of the pipe
+  // element.
+  virtual llvm::Value *getPipeElemAlign(const Expr *PipeArg);
 };
 
 }
 }
 
 #endif

lib/CodeGen/CGOpenCLRuntime.cpp

 llvm::Type *CGOpenCLRuntime::convertOpenCLSpecificType(const Type *T) {
   assert(T->isOpenCLSpecificType() &&
          "Not an OpenCL specific type!");
 
   llvm::LLVMContext& Ctx = CGM.getLLVMContext();
   uint32_t ImgAddrSpc = CGM.getContext().getTargetAddressSpace(
     CGM.getTarget().getOpenCLImageAddrSpace());
   switch (cast<BuiltinType>(T)->getKind()) {
-  default: 
+  default:
     llvm_unreachable("Unexpected opencl builtin type!");
     return nullptr;
 #define IMAGE_TYPE(ImgType, Id, SingletonId, Access, Suffix) \
   case BuiltinType::Id: \
     return llvm::PointerType::get( \
         llvm::StructType::create(Ctx, "opencl." #ImgType "_" #Suffix "_t"), \
         ImgAddrSpc);
 #include "clang/Basic/OpenCLImageTypes.def"

 llvm::PointerType *CGOpenCLRuntime::getSamplerType() {
   if (!SamplerTy)
     SamplerTy = llvm::PointerType::get(llvm::StructType::create(
       CGM.getLLVMContext(), "opencl.sampler_t"),
       CGM.getContext().getTargetAddressSpace(
       LangAS::opencl_constant));
   return SamplerTy;
 }
+
+llvm::Value *CGOpenCLRuntime::getPipeElemSize(const Expr *PipeArg) {
+  const PipeType *PipeTy = PipeArg->getType()->getAs<PipeType>();
+  // The type of the last (implicit) argument to be passed.
+  llvm::Type *Int32Ty = llvm::IntegerType::getInt32Ty(CGM.getLLVMContext());
+  unsigned TypeSize = CGM.getContext()
+                          .getTypeSizeInChars(PipeTy->getElementType())
+                          .getQuantity();
+  return llvm::ConstantInt::get(Int32Ty, TypeSize, false);
+}
+
+llvm::Value *CGOpenCLRuntime::getPipeElemAlign(const Expr *PipeArg) {
+  const PipeType *PipeTy = PipeArg->getType()->getAs<PipeType>();
+  // The type of the last (implicit) argument to be passed.
+  llvm::Type *Int32Ty = llvm::IntegerType::getInt32Ty(CGM.getLLVMContext());
+  unsigned TypeSize = CGM.getContext()
+                          .getTypeAlignInChars(PipeTy->getElementType())
+                          .getQuantity();
+  return llvm::ConstantInt::get(Int32Ty, TypeSize, false);
+}

test/CodeGenOpenCL/pipe_builtin.cl

 // RUN: %clang_cc1 -emit-llvm -O0 -cl-std=CL2.0 -o - %s | FileCheck %s
 
 // CHECK: %opencl.pipe_t = type opaque
 // CHECK: %opencl.reserve_id_t = type opaque
 
 void test1(read_only pipe int p, global int *ptr) {
-  // CHECK: call i32 @__read_pipe_2(%opencl.pipe_t* %{{.*}}, i8* %{{.*}})
+  // CHECK: call i32 @__read_pipe_2(%opencl.pipe_t* %{{.*}}, i8* %{{.*}}, i32 4, i32 4)
   read_pipe(p, ptr);
-  // CHECK: call %opencl.reserve_id_t* @__reserve_read_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}})
+  // CHECK: call %opencl.reserve_id_t* @__reserve_read_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}}, i32 4, i32 4)
   reserve_id_t rid = reserve_read_pipe(p, 2);
-  // CHECK: call i32 @__read_pipe_4(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 {{.*}}, i8* %{{.*}})
+  // CHECK: call i32 @__read_pipe_4(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 {{.*}}, i8* %{{.*}}, i32 4, i32 4)
   read_pipe(p, rid, 2, ptr);
-  // CHECK: call void @__commit_read_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}})
+  // CHECK: call void @__commit_read_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 4, i32 4)
   commit_read_pipe(p, rid);
 }
 
 void test2(write_only pipe int p, global int *ptr) {
-  // CHECK: call i32 @__write_pipe_2(%opencl.pipe_t* %{{.*}}, i8* %{{.*}})
+  // CHECK: call i32 @__write_pipe_2(%opencl.pipe_t* %{{.*}}, i8* %{{.*}}, i32 4, i32 4)
   write_pipe(p, ptr);
-  // CHECK: call %opencl.reserve_id_t* @__reserve_write_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}})
+  // CHECK: call %opencl.reserve_id_t* @__reserve_write_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}}, i32 4, i32 4)
   reserve_id_t rid = reserve_write_pipe(p, 2);
-  // CHECK: call i32 @__write_pipe_4(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 {{.*}}, i8* %{{.*}})
+  // CHECK: call i32 @__write_pipe_4(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 {{.*}}, i8* %{{.*}}, i32 4, i32 4)
   write_pipe(p, rid, 2, ptr);
-  // CHECK: call void @__commit_write_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}})
+  // CHECK: call void @__commit_write_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 4, i32 4)
   commit_write_pipe(p, rid);
 }
 
 void test3(read_only pipe int p, global int *ptr) {
-  // CHECK: call %opencl.reserve_id_t* @__work_group_reserve_read_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}})
+  // CHECK: call %opencl.reserve_id_t* @__work_group_reserve_read_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}}, i32 4, i32 4)
   reserve_id_t rid = work_group_reserve_read_pipe(p, 2);
-  // CHECK: call void @__work_group_commit_read_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}})
+  // CHECK: call void @__work_group_commit_read_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 4, i32 4)
   work_group_commit_read_pipe(p, rid);
 }
 
 void test4(write_only pipe int p, global int *ptr) {
-  // CHECK: call %opencl.reserve_id_t* @__work_group_reserve_write_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}})
+  // CHECK: call %opencl.reserve_id_t* @__work_group_reserve_write_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}}, i32 4, i32 4)
   reserve_id_t rid = work_group_reserve_write_pipe(p, 2);
-  // CHECK: call void @__work_group_commit_write_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}})
+  // CHECK: call void @__work_group_commit_write_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 4, i32 4)
   work_group_commit_write_pipe(p, rid);
 }
 
 void test5(read_only pipe int p, global int *ptr) {
-  // CHECK: call %opencl.reserve_id_t* @__sub_group_reserve_read_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}})
+  // CHECK: call %opencl.reserve_id_t* @__sub_group_reserve_read_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}}, i32 4, i32 4)
   reserve_id_t rid = sub_group_reserve_read_pipe(p, 2);
-  // CHECK: call void @__sub_group_commit_read_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}})
+  // CHECK: call void @__sub_group_commit_read_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 4, i32 4)
   sub_group_commit_read_pipe(p, rid);
 }
 
 void test6(write_only pipe int p, global int *ptr) {
-  // CHECK: call %opencl.reserve_id_t* @__sub_group_reserve_write_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}})
+  // CHECK: call %opencl.reserve_id_t* @__sub_group_reserve_write_pipe(%opencl.pipe_t* %{{.*}}, i32 {{.*}}, i32 4, i32 4)
   reserve_id_t rid = sub_group_reserve_write_pipe(p, 2);
-  // CHECK: call void @__sub_group_commit_write_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}})
+  // CHECK: call void @__sub_group_commit_write_pipe(%opencl.pipe_t* %{{.*}}, %opencl.reserve_id_t* %{{.*}}, i32 4, i32 4)
   sub_group_commit_write_pipe(p, rid);
 }
 
 void test7(write_only pipe int p, global int *ptr) {
-  // CHECK: call i32 @__get_pipe_num_packets(%opencl.pipe_t* %{{.*}})
+  // CHECK: call i32 @__get_pipe_num_packets(%opencl.pipe_t* %{{.*}}, i32 4, i32 4)
   *ptr = get_pipe_num_packets(p);
-  // CHECK: call i32 @__get_pipe_max_packets(%opencl.pipe_t* %{{.*}})
+  // CHECK: call i32 @__get_pipe_max_packets(%opencl.pipe_t* %{{.*}}, i32 4, i32 4)
   *ptr = get_pipe_max_packets(p);
 }

test/CodeGenOpenCL/pipe_types.cl

struct Person {
   bool isFemale;
   int ID;
 };
 
 void test_reserved_read_pipe(global struct Person *SDst,
                              read_only pipe struct Person SPipe) {
 // CHECK: define void @test_reserved_read_pipe
   read_pipe (SPipe, SDst);
-  // CHECK: call i32 @__read_pipe_2(%opencl.pipe_t* %{{.*}}, i8* %{{.*}})
+  // CHECK: call i32 @__read_pipe_2(%opencl.pipe_t* %{{.*}}, i8* %{{.*}}, i32 16, i32 8)
   read_pipe (SPipe, SDst);
-  // CHECK: call i32 @__read_pipe_2(%opencl.pipe_t* %{{.*}}, i8* %{{.*}})
+  // CHECK: call i32 @__read_pipe_2(%opencl.pipe_t* %{{.*}}, i8* %{{.*}}, i32 16, i32 8)
 }