[PATCH] D29128: [OpenMP] Support for the proc_bind-clause on 'target parallel' on the NVPTX device.

[Phabricator via Phabricator via cfe-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL293069: [OpenMP] Support for the proc_bind-clause on 'target 
parallel' on the NVPTX… (authored by arpith).

Changed prior to commit:
  https://reviews.llvm.org/D29128?vs=85759=85765#toc

Repository:
  rL LLVM

https://reviews.llvm.org/D29128

Files:
  cfe/trunk/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
  cfe/trunk/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
  cfe/trunk/test/OpenMP/nvptx_target_parallel_proc_bind_codegen.cpp

Index: cfe/trunk/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
===
--- cfe/trunk/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
+++ cfe/trunk/lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
@@ -642,6 +642,17 @@
 llvm_unreachable("OpenMP NVPTX can only handle device code.");
 }
 
+void CGOpenMPRuntimeNVPTX::emitProcBindClause(CodeGenFunction ,
+  OpenMPProcBindClauseKind ProcBind,
+  SourceLocation Loc) {
+  // Do nothing in case of Spmd mode and L0 parallel.
+  // TODO: If in Spmd mode and L1 parallel emit the clause.
+  if (isInSpmdExecutionMode())
+return;
+
+  CGOpenMPRuntime::emitProcBindClause(CGF, ProcBind, Loc);
+}
+
 void CGOpenMPRuntimeNVPTX::emitNumThreadsClause(CodeGenFunction ,
 llvm::Value *NumThreads,
 SourceLocation Loc) {
Index: cfe/trunk/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
===
--- cfe/trunk/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
+++ cfe/trunk/lib/CodeGen/CGOpenMPRuntimeNVPTX.h
@@ -170,6 +170,12 @@
 public:
   explicit CGOpenMPRuntimeNVPTX(CodeGenModule );
 
+  /// \brief Emit call to void __kmpc_push_proc_bind(ident_t *loc, kmp_int32
+  /// global_tid, int proc_bind) to generate code for 'proc_bind' clause.
+  virtual void emitProcBindClause(CodeGenFunction ,
+  OpenMPProcBindClauseKind ProcBind,
+  SourceLocation Loc) override;
+
   /// \brief Emits call to void __kmpc_push_num_threads(ident_t *loc, kmp_int32
   /// global_tid, kmp_int32 num_threads) to generate code for 'num_threads'
   /// clause.
Index: cfe/trunk/test/OpenMP/nvptx_target_parallel_proc_bind_codegen.cpp
===
--- cfe/trunk/test/OpenMP/nvptx_target_parallel_proc_bind_codegen.cpp
+++ cfe/trunk/test/OpenMP/nvptx_target_parallel_proc_bind_codegen.cpp
@@ -0,0 +1,106 @@
+// Test target codegen - host bc file has to be created first.
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// expected-no-diagnostics
+#ifndef HEADER
+#define HEADER
+
+// Check that the execution mode of all 3 target regions on the gpu is set to SPMD Mode.
+// CHECK-DAG: {{@__omp_offloading_.+l22}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l26}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l31}}_exec_mode = weak constant i8 0
+
+template
+tx ftemplate(int n) {
+  tx a = 0;
+  short aa = 0;
+  tx b[10];
+
+  #pragma omp target parallel proc_bind(master)
+  {
+  }
+
+  #pragma omp target parallel proc_bind(spread)
+  {
+aa += 1;
+  }
+
+  #pragma omp target parallel proc_bind(close)
+  {
+a += 1;
+aa += 1;
+b[2] += 1;
+  }
+
+  return a;
+}
+
+int bar(int n){
+  int a = 0;
+
+  a += ftemplate(n);
+
+  return a;
+}
+
+  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l22}}(
+  // CHECK: call void @__kmpc_spmd_kernel_init(
+  // CHECK: br label {{%?}}[[EXEC:.+]]
+  //
+  // CHECK: [[EXEC]]
+  // CHECK-NOT: call void @__kmpc_push_proc_bind
+  // CHECK: {{call|invoke}} void [[OP1:@.+]](i32* null, i32* null
+  // CHECK: br label {{%?}}[[DONE:.+]]
+  //
+  // CHECK: 

[PATCH] D29128: [OpenMP] Support for the proc_bind-clause on 'target parallel' on the NVPTX device.

[Alexey Bataev via Phabricator via cfe-commits]

ABataev accepted this revision.
ABataev added a comment.
This revision is now accepted and ready to land.

LG


https://reviews.llvm.org/D29128



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D29128: [OpenMP] Support for the proc_bind-clause on 'target parallel' on the NVPTX device.

[Arpith Jacob via Phabricator via cfe-commits]

arpith-jacob created this revision.
Herald added a subscriber: jholewinski.

This patch adds support for the proc_bind clause on the Spmd construct
'target parallel' on the NVPTX device.  Since the parallel region is created
upon kernel launch, this clause can be safely ignored on the NVPTX device at
codegen time for level 0 parallelism.


https://reviews.llvm.org/D29128

Files:
  lib/CodeGen/CGOpenMPRuntimeNVPTX.cpp
  lib/CodeGen/CGOpenMPRuntimeNVPTX.h
  test/OpenMP/nvptx_target_parallel_proc_bind_codegen.cpp

Index: test/OpenMP/nvptx_target_parallel_proc_bind_codegen.cpp
===
--- /dev/null
+++ test/OpenMP/nvptx_target_parallel_proc_bind_codegen.cpp
@@ -0,0 +1,106 @@
+// Test target codegen - host bc file has to be created first.
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32
+// expected-no-diagnostics
+#ifndef HEADER
+#define HEADER
+
+// Check that the execution mode of all 3 target regions on the gpu is set to SPMD Mode.
+// CHECK-DAG: {{@__omp_offloading_.+l22}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l26}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l31}}_exec_mode = weak constant i8 0
+
+template
+tx ftemplate(int n) {
+  tx a = 0;
+  short aa = 0;
+  tx b[10];
+
+  #pragma omp target parallel proc_bind(master)
+  {
+  }
+
+  #pragma omp target parallel proc_bind(spread)
+  {
+aa += 1;
+  }
+
+  #pragma omp target parallel proc_bind(close)
+  {
+a += 1;
+aa += 1;
+b[2] += 1;
+  }
+
+  return a;
+}
+
+int bar(int n){
+  int a = 0;
+
+  a += ftemplate(n);
+
+  return a;
+}
+
+  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l22}}(
+  // CHECK: call void @__kmpc_spmd_kernel_init(
+  // CHECK: br label {{%?}}[[EXEC:.+]]
+  //
+  // CHECK: [[EXEC]]
+  // CHECK-NOT: call void @__kmpc_push_proc_bind
+  // CHECK: {{call|invoke}} void [[OP1:@.+]](i32* null, i32* null
+  // CHECK: br label {{%?}}[[DONE:.+]]
+  //
+  // CHECK: [[DONE]]
+  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: br label {{%?}}[[EXIT:.+]]
+  //
+  // CHECK: [[EXIT]]
+  // CHECK: ret void
+  // CHECK: }
+
+
+
+
+
+  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l26}}(
+  // CHECK: call void @__kmpc_spmd_kernel_init(
+  // CHECK: br label {{%?}}[[EXEC:.+]]
+  //
+  // CHECK: [[EXEC]]
+  // CHECK-NOT: call void @__kmpc_push_proc_bind
+  // CHECK: {{call|invoke}} void [[OP1:@.+]](i32* null, i32* null
+  // CHECK: br label {{%?}}[[DONE:.+]]
+  //
+  // CHECK: [[DONE]]
+  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: br label {{%?}}[[EXIT:.+]]
+  //
+  // CHECK: [[EXIT]]
+  // CHECK: ret void
+  // CHECK: }
+
+
+
+
+  // CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+template.+l31}}(
+  // CHECK: call void @__kmpc_spmd_kernel_init(
+  // CHECK: br label {{%?}}[[EXEC:.+]]
+  //
+  // CHECK: [[EXEC]]
+  // CHECK-NOT: call void @__kmpc_push_proc_bind
+  // CHECK: {{call|invoke}} void [[OP1:@.+]](i32* null, i32* null
+  // CHECK: br label {{%?}}[[DONE:.+]]
+  //
+  // CHECK: [[DONE]]
+  // CHECK: call void @__kmpc_spmd_kernel_deinit()
+  // CHECK: br label {{%?}}[[EXIT:.+]]
+  //
+  // CHECK: [[EXIT]]
+  // CHECK: ret void
+  // CHECK: }
+#endif
Index: lib/CodeGen/CGOpenMPRuntimeNVPTX.h
===
--- lib/CodeGen/CGOpenMPRuntimeNVPTX.h
+++ lib/CodeGen/CGOpenMPRuntimeNVPTX.h
@@ -170,6 +170,12 @@
 public:
   explicit CGOpenMPRuntimeNVPTX(CodeGenModule );
 
+  /// \brief Emit call to void __kmpc_push_proc_bind(ident_t *loc, kmp_int32
+  /// global_tid, int proc_bind) to generate code for 'proc_bind' clause.
+  virtual void emitProcBindClause(CodeGenFunction ,
+  OpenMPProcBindClauseKind ProcBind,
+  SourceLocation Loc)