diff options
| -rw-r--r-- | polly/lib/CodeGen/PPCGCodeGeneration.cpp | 15 | ||||
| -rw-r--r-- | polly/test/GPGPU/kernel-params-scop-parameter.ll | 43 |
2 files changed, 57 insertions, 1 deletions
diff --git a/polly/lib/CodeGen/PPCGCodeGeneration.cpp b/polly/lib/CodeGen/PPCGCodeGeneration.cpp index e38fed44b1d..fcfc9ff6c8f 100644 --- a/polly/lib/CodeGen/PPCGCodeGeneration.cpp +++ b/polly/lib/CodeGen/PPCGCodeGeneration.cpp @@ -141,7 +141,7 @@ private: /// /// - One i8 pointer for each external array reference used in the kernel. /// - Host iterators - /// - Parameters (TODO) + /// - Parameters /// - Other LLVM Value references (TODO) /// /// @param Kernel The kernel to generate the function declaration for. @@ -228,6 +228,11 @@ Function *GPUNodeBuilder::createKernelFunctionDecl(ppcg_kernel *Kernel) { for (long i = 0; i < NumHostIters; i++) Args.push_back(Builder.getInt64Ty()); + int NumVars = isl_space_dim(Kernel->space, isl_dim_param); + + for (long i = 0; i < NumVars; i++) + Args.push_back(Builder.getInt64Ty()); + auto *FT = FunctionType::get(Builder.getVoidTy(), Args, false); auto *FN = Function::Create(FT, Function::ExternalLinkage, Identifier, GPUModule.get()); @@ -250,6 +255,14 @@ Function *GPUNodeBuilder::createKernelFunctionDecl(ppcg_kernel *Kernel) { Arg++; } + for (long i = 0; i < NumVars; i++) { + isl_id *Id = isl_space_get_dim_id(Kernel->space, isl_dim_param, i); + Arg->setName(isl_id_get_name(Id)); + IDToValue[Id] = &*Arg; + KernelIDs.insert(std::unique_ptr<isl_id, IslIdDeleter>(Id)); + Arg++; + } + return FN; } diff --git a/polly/test/GPGPU/kernel-params-scop-parameter.ll b/polly/test/GPGPU/kernel-params-scop-parameter.ll new file mode 100644 index 00000000000..d73af4d616e --- /dev/null +++ b/polly/test/GPGPU/kernel-params-scop-parameter.ll @@ -0,0 +1,43 @@ +; RUN: opt %loadPolly -polly-codegen-ppcg -polly-acc-dump-kernel-ir \ +; RUN: -disable-output < %s | \ +; RUN: FileCheck -check-prefix=KERNEL-IR %s + +; void kernel_params_scop_parameter(float A[], long n) { +; for (long i = 0; i < n; i++) +; A[i] += 42; +; } + +; KERNEL-IR: define ptx_kernel void @kernel_0(i8* %MemRef_A, i64 %n) { +; KERNEL-IR-NEXT: entry: +; KERNEL-IR-NEXT: %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x() +; KERNEL-IR-NEXT: %b0 = zext i32 %0 to i64 +; KERNEL-IR-NEXT: %1 = call i32 @llvm.nvvm.read.ptx.sreg.tid.x() +; KERNEL-IR-NEXT: %t0 = zext i32 %1 to i64 +; KERNEL-IR-NEXT: ret void +; KERNEL-IR-NEXT: } + +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" + +define void @kernel_params_scop_parameter(float* %A, i64 %n) { +bb: + br label %bb1 + +bb1: ; preds = %bb6, %bb + %i.0 = phi i64 [ 0, %bb ], [ %tmp7, %bb6 ] + %tmp = icmp slt i64 %i.0, %n + br i1 %tmp, label %bb2, label %bb8 + +bb2: ; preds = %bb1 + %tmp3 = getelementptr inbounds float, float* %A, i64 %i.0 + %tmp4 = load float, float* %tmp3, align 4 + %tmp5 = fadd float %tmp4, 4.200000e+01 + store float %tmp5, float* %tmp3, align 4 + br label %bb6 + +bb6: ; preds = %bb2 + %tmp7 = add nuw nsw i64 %i.0, 1 + br label %bb1 + +bb8: ; preds = %bb1 + ret void +} |
