Prefix the name of the calling host function in the name of callee GPU kernel

Summary:
Provide more context to the name of a GPU kernel by prefixing its name with the host function that calls it. E.g. The first kernel called by `gemm` would be `FUNC_gemm_KERNEL_0`.

Kernels currently follow the "kernel_#" (# = 0,1,2,3,...) nomenclature. This patch makes it easier to map host caller and device callee, especially when there are many kernels produced by Polly-ACC.

Reviewers: grosser, Meinersbur, bollu, philip.pfaffe, kbarton!

Reviewed By: grosser

Subscribers: nemanjai, pollydev

Tags: #polly

Differential Revision: https://reviews.llvm.org/D33985

llvm-svn: 307173

7 files changed, 23 insertions, 15 deletions

diff --git a/polly/lib/CodeGen/PPCGCodeGeneration.cpp b/polly/lib/CodeGen/PPCGCodeGeneration.cpp
index b882455c620..4e49d1c46ff 100644
--- a/polly/lib/CodeGen/PPCGCodeGeneration.cpp
+++ b/polly/lib/CodeGen/PPCGCodeGeneration.cpp
@@ -299,6 +299,9 @@ public:
   /// The maximal number of loops surrounding a parallel kernel.
   unsigned DeepestParallel = 0;
 
+  /// Return the name to set for the ptx_kernel.
+  std::string getKernelFuncName(int Kernel_id);
+
 private:
   /// A vector of array base pointers for which a new ScopArrayInfo was created.
   ///
@@ -662,6 +665,11 @@ private:
                               Value *Parameters);
 };
 
+std::string GPUNodeBuilder::getKernelFuncName(int Kernel_id) {
+  return "FUNC_" + S.getFunction().getName().str() + "_KERNEL_" +
+         std::to_string(Kernel_id);
+}
+
 void GPUNodeBuilder::initializeAfterRTH() {
   BasicBlock *NewBB = SplitBlock(Builder.GetInsertBlock(),
                                  &*Builder.GetInsertPoint(), &DT, &LI);
@@ -1621,7 +1629,7 @@ void GPUNodeBuilder::createKernel(__isl_take isl_ast_node *KernelStmt) {
   Builder.SetInsertPoint(&HostInsertPoint);
   Value *Parameters = createLaunchParameters(Kernel, F, SubtreeValues);
 
-  std::string Name = "kernel_" + std::to_string(Kernel->id);
+  std::string Name = getKernelFuncName(Kernel->id);
   Value *KernelString = Builder.CreateGlobalStringPtr(ASMString, Name);
   Value *NameString = Builder.CreateGlobalStringPtr(Name, Name + "_name");
   Value *GPUKernel = createCallGetKernel(KernelString, NameString);
@@ -1662,7 +1670,7 @@ Function *
 GPUNodeBuilder::createKernelFunctionDecl(ppcg_kernel *Kernel,
                                          SetVector<Value *> &SubtreeValues) {
   std::vector<Type *> Args;
-  std::string Identifier = "kernel_" + std::to_string(Kernel->id);
+  std::string Identifier = getKernelFuncName(Kernel->id);
 
   for (long i = 0; i < Prog->n_array; i++) {
     if (!ppcg_kernel_requires_array_argument(Kernel, i))
@@ -1926,7 +1934,7 @@ void GPUNodeBuilder::createKernelVariables(ppcg_kernel *Kernel, Function *FN) {
 void GPUNodeBuilder::createKernelFunction(
     ppcg_kernel *Kernel, SetVector<Value *> &SubtreeValues,
     SetVector<Function *> &SubtreeFunctions) {
-  std::string Identifier = "kernel_" + std::to_string(Kernel->id);
+  std::string Identifier = getKernelFuncName(Kernel->id);
   GPUModule.reset(new Module(Identifier, Builder.getContext()));
 
   switch (Arch) {
diff --git a/polly/test/GPGPU/cuda-annotations.ll b/polly/test/GPGPU/cuda-annotations.ll
index ed1fa6a30ee..57b2e160983 100644
--- a/polly/test/GPGPU/cuda-annotations.ll
+++ b/polly/test/GPGPU/cuda-annotations.ll
@@ -4,11 +4,11 @@
 
 ; REQUIRES: pollyacc
 
-; KERNEL: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A, i64 %n) #0 {
+; KERNEL: define ptx_kernel void @FUNC_foo_KERNEL_0(i8 addrspace(1)* %MemRef_A, i64 %n) #0 {
 
 ; KERNEL: !nvvm.annotations = !{!0}
 
-; KERNEL: !0 = !{void (i8 addrspace(1)*, i64)* @kernel_0, !"maxntidx", i32 32, !"maxntidy", i32 1, !"maxntidz", i32 1}
+; KERNEL: !0 = !{void (i8 addrspace(1)*, i64)* @FUNC_foo_KERNEL_0, !"maxntidx", i32 32, !"maxntidy", i32 1, !"maxntidz", i32 1}
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
diff --git a/polly/test/GPGPU/cuda-managed-memory-simple.ll b/polly/test/GPGPU/cuda-managed-memory-simple.ll
index a8a1d6ae9d2..9d2af1da897 100644
--- a/polly/test/GPGPU/cuda-managed-memory-simple.ll
+++ b/polly/test/GPGPU/cuda-managed-memory-simple.ll
@@ -54,7 +54,7 @@
 ; CHECK-NEXT:  %22 = getelementptr [4 x i8*], [4 x i8*]* %polly_launch_0_params, i64 0, i64 3
 ; CHECK-NEXT:  %23 = bitcast i32* %polly_launch_0_param_size_1 to i8*
 ; CHECK-NEXT:  store i8* %23, i8** %22
-; CHECK-NEXT:  %24 = call i8* @polly_getKernel(i8* getelementptr inbounds ([750 x i8], [750 x i8]* @kernel_0, i32 0, i32 0), i8* getelementptr inbounds ([9 x i8], [9 x i8]* @kernel_0_name, i32 0, i32 0))
+; CHECK-NEXT:  %24 = call i8* @polly_getKernel(i8* getelementptr inbounds ([810 x i8], [810 x i8]* @FUNC_copy_KERNEL_0, i32 0, i32 0), i8* getelementptr inbounds ([19 x i8], [19 x i8]* @FUNC_copy_KERNEL_0_name, i32 0, i32 0))
 ; CHECK-NEXT:  call void @polly_launchKernel(i8* %24, i32 2, i32 1, i32 32, i32 1, i32 1, i8* %polly_launch_0_params_i8ptr)
 ; CHECK-NEXT:  call void @polly_freeKernel(i8* %24)
 ; CHECK-NEXT:  call void @polly_synchronizeDevice()
diff --git a/polly/test/GPGPU/host-control-flow.ll b/polly/test/GPGPU/host-control-flow.ll
index e1258b707c7..15f66bbb160 100644
--- a/polly/test/GPGPU/host-control-flow.ll
+++ b/polly/test/GPGPU/host-control-flow.ll
@@ -42,7 +42,7 @@
 ; IR-NEXT:   %polly.loop_cond = icmp sle i64 %polly.indvar_next, 99
 ; IR-NEXT:   br i1 %polly.loop_cond, label %polly.loop_header, label %polly.loop_exit
 
-; KERNEL-IR: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A, i64 %c0)
+; KERNEL-IR: define ptx_kernel void @FUNC_foo_KERNEL_0(i8 addrspace(1)* %MemRef_A, i64 %c0)
 ; KERNEL-IR-LABEL: entry:
 ; KERNEL-IR-NEXT:   %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
 ; KERNEL-IR-NEXT:   %b0 = zext i32 %0 to i64
diff --git a/polly/test/GPGPU/invariant-load-hoisting.ll b/polly/test/GPGPU/invariant-load-hoisting.ll
index 02f216d75e9..58a668971df 100644
--- a/polly/test/GPGPU/invariant-load-hoisting.ll
+++ b/polly/test/GPGPU/invariant-load-hoisting.ll
@@ -21,7 +21,7 @@
 ; HOST-IR:      call void @polly_launchKernel(i8* %215, i32 %221, i32 1, i32 32, i32 1, i32 1, i8* %polly_launch_0_params_i8ptr)
 ; HOST-IR-NEXT: call void @polly_freeKernel(i8* %215)
 ;
-; KERNEL-IR: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_B, i8 addrspace(1)* %MemRef_A, i32 %n, i32 %tmp12) #0 {
+; KERNEL-IR: define ptx_kernel void @FUNC_f_KERNEL_0(i8 addrspace(1)* %MemRef_B, i8 addrspace(1)* %MemRef_A, i32 %n, i32 %tmp12) #0 {
 ;
 ; Check that we generate correct GPU code in case of invariant load hoisting.
 ;
diff --git a/polly/test/GPGPU/kernel-params-only-some-arrays.ll b/polly/test/GPGPU/kernel-params-only-some-arrays.ll
index b6f3172abc6..a2233cc736d 100644
--- a/polly/test/GPGPU/kernel-params-only-some-arrays.ll
+++ b/polly/test/GPGPU/kernel-params-only-some-arrays.ll
@@ -16,12 +16,12 @@
 ;        B[i] += 42;
 ;    }
 
-; KERNEL: ; ModuleID = 'kernel_0'
-; KERNEL-NEXT: source_filename = "kernel_0"
+; KERNEL: ; ModuleID = 'FUNC_kernel_params_only_some_arrays_KERNEL_0'
+; KERNEL-NEXT: source_filename = "FUNC_kernel_params_only_some_arrays_KERNEL_0"
 ; KERNEL-NEXT: target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
 ; KERNEL-NEXT: target triple = "nvptx64-nvidia-cuda"
 
-; KERNEL: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A)
+; KERNEL: define ptx_kernel void @FUNC_kernel_params_only_some_arrays_KERNEL_0(i8 addrspace(1)* %MemRef_A)
 ; KERNEL-NEXT:   entry:
 ; KERNEL-NEXT:     %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
 ; KERNEL-NEXT:     %b0 = zext i32 %0 to i64
@@ -31,12 +31,12 @@
 ; KERNEL:     ret void
 ; KERNEL-NEXT: }
 
-; KERNEL: ; ModuleID = 'kernel_1'
-; KERNEL-NEXT: source_filename = "kernel_1"
+; KERNEL: ; ModuleID = 'FUNC_kernel_params_only_some_arrays_KERNEL_1'
+; KERNEL-NEXT: source_filename = "FUNC_kernel_params_only_some_arrays_KERNEL_1"
 ; KERNEL-NEXT: target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
 ; KERNEL-NEXT: target triple = "nvptx64-nvidia-cuda"
 
-; KERNEL: define ptx_kernel void @kernel_1(i8 addrspace(1)* %MemRef_B)
+; KERNEL: define ptx_kernel void @FUNC_kernel_params_only_some_arrays_KERNEL_1(i8 addrspace(1)* %MemRef_B)
 ; KERNEL-NEXT:   entry:
 ; KERNEL-NEXT:     %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
 ; KERNEL-NEXT:     %b0 = zext i32 %0 to i64
diff --git a/polly/test/GPGPU/kernel-params-scop-parameter.ll b/polly/test/GPGPU/kernel-params-scop-parameter.ll
index 7f07f2dda18..d2d5abaa991 100644
--- a/polly/test/GPGPU/kernel-params-scop-parameter.ll
+++ b/polly/test/GPGPU/kernel-params-scop-parameter.ll
@@ -9,7 +9,7 @@
 ;        A[i] += 42;
 ;    }
 
-; KERNEL-IR: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A, i64 %n)
+; KERNEL-IR: define ptx_kernel void @FUNC_kernel_params_scop_parameter_KERNEL_0(i8 addrspace(1)* %MemRef_A, i64 %n)
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"