[OpenMP] Add flag for preventing the extension to 64 bits for the collapse loop counter

Summary: Introduce a compiler flag for cases when the user knows that the collapsed loop counter can be safely represented using at most 32 bits. This will prevent the emission of expensive mathematical operations (such as the div operation) on the iteration variable using 64 bits where 32 bit operations are sufficient.

Reviewers: ABataev, caomhin

Reviewed By: ABataev

Subscribers: hfinkel, kkwli0, guansong, cfe-commits

Differential Revision: https://reviews.llvm.org/D55928

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@350758 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/docs/OpenMPSupport.rst b/docs/OpenMPSupport.rst
index 5ca3613cdea27df49aa431ec266ec9564b1e4c75..04a9648ca29420c0d89f41bc6dd2904dd451ae30 100644 (file)
--- a/docs/OpenMPSupport.rst
+++ b/docs/OpenMPSupport.rst
@@ -108,6 +108,16 @@ are stored in the global memory. In `Cuda` mode local variables are not shared
 between the threads and it is user responsibility to share the required data
 between the threads in the parallel regions.
 
+Collapsed loop nest counter
+---------------------------
+
+When using the collapse clause on a loop nest the default behaviour is to
+automatically extend the representation of the loop counter to 64 bits for
+the cases where the sizes of the collapsed loops are not known at compile
+time. To prevent this conservative choice and use at most 32 bits,
+compile your program with the `-fopenmp-optimistic-collapse`.
+
+
 Features not supported or with limited support for Cuda devices
 ---------------------------------------------------------------
 

diff --git a/include/clang/Basic/LangOptions.def b/include/clang/Basic/LangOptions.def
index 512baa463bccefc67ce044893a12a31322b6231d..49961856c9650d89208f1f62298848c26ccc5dbc 100644 (file)
--- a/include/clang/Basic/LangOptions.def
+++ b/include/clang/Basic/LangOptions.def
@@ -207,6 +207,7 @@ LANGOPT(OpenMPCUDAForceFullRuntime , 1, 0, "Force to use full runtime in all con
 LANGOPT(OpenMPHostCXXExceptions    , 1, 0, "C++ exceptions handling in the host code.")
 LANGOPT(OpenMPCUDANumSMs  , 32, 0, "Number of SMs for CUDA devices.")
 LANGOPT(OpenMPCUDABlocksPerSM  , 32, 0, "Number of blocks per SM for CUDA devices.")
+LANGOPT(OpenMPOptimisticCollapse  , 1, 0, "Use at most 32 bits to represent the collapsed loop nest counter.")
 LANGOPT(RenderScript      , 1, 0, "RenderScript")
 
 LANGOPT(CUDAIsDevice      , 1, 0, "compiling for CUDA device")

diff --git a/include/clang/Driver/Options.td b/include/clang/Driver/Options.td
index 1c5cae683a1b493af898791309fa54e7bd2e3abf..9e6b1afde4bfd558de2e7dfa1d4e4ed8ebfd2f02 100644 (file)
--- a/include/clang/Driver/Options.td
+++ b/include/clang/Driver/Options.td
@@ -1574,6 +1574,10 @@ def fopenmp_cuda_number_of_sm_EQ : Joined<["-"], "fopenmp-cuda-number-of-sm=">,
   Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
 def fopenmp_cuda_blocks_per_sm_EQ : Joined<["-"], "fopenmp-cuda-blocks-per-sm=">, Group<f_Group>,
   Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
+def fopenmp_optimistic_collapse : Flag<["-"], "fopenmp-optimistic-collapse">, Group<f_Group>,
+  Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
+def fno_openmp_optimistic_collapse : Flag<["-"], "fno-openmp-optimistic-collapse">, Group<f_Group>,
+  Flags<[NoArgumentUnused, HelpHidden]>;
 def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">, Group<f_Group>;
 def foptimize_sibling_calls : Flag<["-"], "foptimize-sibling-calls">, Group<f_Group>;
 def fno_escaping_block_tail_calls : Flag<["-"], "fno-escaping-block-tail-calls">, Group<f_Group>, Flags<[CC1Option]>;

diff --git a/lib/Driver/ToolChains/Clang.cpp b/lib/Driver/ToolChains/Clang.cpp
index 7df95649bd1585607b42810c0ebb88a1e272bc0f..eb88a71e492646b31867e44d5e7bc37367058519 100644 (file)
--- a/lib/Driver/ToolChains/Clang.cpp
+++ b/lib/Driver/ToolChains/Clang.cpp
@@ -4434,6 +4434,10 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
       Args.AddAllArgs(CmdArgs, options::OPT_fopenmp_version_EQ);
       Args.AddAllArgs(CmdArgs, options::OPT_fopenmp_cuda_number_of_sm_EQ);
       Args.AddAllArgs(CmdArgs, options::OPT_fopenmp_cuda_blocks_per_sm_EQ);
+      if (Args.hasFlag(options::OPT_fopenmp_optimistic_collapse,
+                       options::OPT_fno_openmp_optimistic_collapse,
+                       /*Default=*/false))
+        CmdArgs.push_back("-fopenmp-optimistic-collapse");
 
       // When in OpenMP offloading mode with NVPTX target, forward
       // cuda-mode flag

diff --git a/lib/Frontend/CompilerInvocation.cpp b/lib/Frontend/CompilerInvocation.cpp
index 04105f0980e61bd639dc94384f4a84ab497bcac8..1e857355b33fab6ce52e71d7ddddb4ebf82a37be 100644 (file)
--- a/lib/Frontend/CompilerInvocation.cpp
+++ b/lib/Frontend/CompilerInvocation.cpp
@@ -2846,6 +2846,11 @@ static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK,
                            Opts.OpenMPCUDABlocksPerSM, Diags);
   }
 
+  // Prevent auto-widening the representation of loop counters during an
+  // OpenMP collapse clause.
+  Opts.OpenMPOptimisticCollapse =
+      Args.hasArg(options::OPT_fopenmp_optimistic_collapse) ? 1 : 0;
+
   // Get the OpenMP target triples if any.
   if (Arg *A = Args.getLastArg(options::OPT_fopenmp_targets_EQ)) {
 

diff --git a/lib/Sema/SemaOpenMP.cpp b/lib/Sema/SemaOpenMP.cpp
index 1166de752e395a5edd7b28acdd66c77758eb016f..89eb2e2645201c5e41fc8666049fcf18f31278d6 100644 (file)
--- a/lib/Sema/SemaOpenMP.cpp
+++ b/lib/Sema/SemaOpenMP.cpp
@@ -4136,7 +4136,7 @@ bool OpenMPIterationSpaceChecker::setStep(Expr *NewStep, bool Subtract) {
     if (!TestIsLessOp.hasValue())
       TestIsLessOp = IsConstPos || (IsUnsigned && !Subtract);
     if (UB && (IsConstZero ||
-               (TestIsLessOp.getValue() ? 
+               (TestIsLessOp.getValue() ?
                   (IsConstNeg || (IsUnsigned && Subtract)) :
                   (IsConstPos || (IsUnsigned && !Subtract))))) {
       SemaRef.Diag(NewStep->getExprLoc(),
@@ -4311,7 +4311,7 @@ bool OpenMPIterationSpaceChecker::checkAndSetCond(Expr *S) {
                        Op == OO_Less || Op == OO_Greater, CE->getSourceRange(),
                        CE->getOperatorLoc());
         break;
-      case OO_ExclaimEqual: 
+      case OO_ExclaimEqual:
         return setUB(getInitLCDecl(CE->getArg(0)) == LCDecl ?
                      CE->getArg(1) : CE->getArg(0),
                      /*LessOp=*/llvm::None,
@@ -4569,7 +4569,7 @@ Expr *OpenMPIterationSpaceChecker::buildPreCond(
 
   ExprResult CondExpr =
       SemaRef.BuildBinOp(S, DefaultLoc,
-                         TestIsLessOp.getValue() ? 
+                         TestIsLessOp.getValue() ?
                            (TestIsStrictOp ? BO_LT : BO_LE) :
                            (TestIsStrictOp ? BO_GT : BO_GE),
                          NewLB.get(), NewUB.get());
@@ -5270,13 +5270,14 @@ checkOpenMPLoop(OpenMPDirectiveKind DKind, Expr *CollapseLoopCountExpr,
 
   // Choose either the 32-bit or 64-bit version.
   ExprResult LastIteration = LastIteration64;
-  if (LastIteration32.isUsable() &&
-      C.getTypeSize(LastIteration32.get()->getType()) == 32 &&
-      (AllCountsNeedLessThan32Bits || NestedLoopCount == 1 ||
-       fitsInto(
-           /*Bits=*/32,
-           LastIteration32.get()->getType()->hasSignedIntegerRepresentation(),
-           LastIteration64.get(), SemaRef)))
+  if (SemaRef.getLangOpts().OpenMPOptimisticCollapse ||
+      (LastIteration32.isUsable() &&
+       C.getTypeSize(LastIteration32.get()->getType()) == 32 &&
+       (AllCountsNeedLessThan32Bits || NestedLoopCount == 1 ||
+        fitsInto(
+            /*Bits=*/32,
+            LastIteration32.get()->getType()->hasSignedIntegerRepresentation(),
+            LastIteration64.get(), SemaRef))))
     LastIteration = LastIteration32;
   QualType VType = LastIteration.get()->getType();
   QualType RealVType = VType;
@@ -13116,7 +13117,7 @@ Sema::ActOnOpenMPMapClause(ArrayRef<OpenMPMapModifierKind> MapTypeModifiers,
       continue;
     }
     assert(Count < OMPMapClause::NumberOfModifiers &&
-           "Modifiers exceed the allowed number of map type modifiers"); 
+           "Modifiers exceed the allowed number of map type modifiers");
     Modifiers[Count] = MapTypeModifiers[I];
     ModifiersLoc[Count] = MapTypeModifiersLoc[I];
     ++Count;

diff --git a/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp b/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
index c4df348329f286e208c0f1b9ef1f518fdf387e70..fe0c8dfb63fd9ee579a9facd9337dbe4486822c7 100644 (file)
--- a/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
+++ b/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
@@ -1,6 +1,7 @@
 // Test target codegen - host bc file has to be created first.
 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -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 -fopenmp-cuda-mode -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 -fopenmp-cuda-mode -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 --check-prefix CHECK-DIV64
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -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 -fopenmp-optimistic-collapse -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-DIV32
 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-cuda-mode -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 -fopenmp-cuda-mode -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 -fopenmp-cuda-mode -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
@@ -9,11 +10,12 @@
 #define HEADER
 
 // Check that the execution mode of all 5 target regions on the gpu is set to SPMD Mode.
-// CHECK-DAG: {{@__omp_offloading_.+l32}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l38}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l43}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l48}}_exec_mode = weak constant i8 0
-// CHECK-DAG: {{@__omp_offloading_.+l56}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l34}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l40}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l45}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l50}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l58}}_exec_mode = weak constant i8 0
+// CHECK-DAG: {{@__omp_offloading_.+l65}}_exec_mode = weak constant i8 0
 
 #define N 1000
 #define M 10
@@ -80,7 +82,7 @@ int bar(int n){
 // CHECK-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
 // CHECK-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
-// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}_l32(
+// CHECK-LABEL: define {{.*}}void {{@__omp_offloading_.+}}_l34(
 // CHECK-DAG: [[THREAD_LIMIT:%.+]] = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
 // CHECK: call void @__kmpc_spmd_kernel_init(i32 [[THREAD_LIMIT]], i16 0, i16 0)
 // CHECK: call void @__kmpc_get_team_static_memory(i16 1, i8* addrspacecast (i8 addrspace(3)* getelementptr inbounds ([[MEM_TY]], [[MEM_TY]] addrspace(3)* [[SHARED_GLOBAL_RD]], i32 0, i32 0, i32 0) to i8*), i{{64|32}} 4, i16 1, i8** addrspacecast (i8* addrspace(3)* [[KERNEL_PTR]] to i8**))
@@ -214,16 +216,19 @@ int bar(int n){
 // CHECK: call void @__kmpc_spmd_kernel_deinit_v2(i16 0)
 // CHECK: ret void
 
-// CHECK: define internal void [[OUTL4]](
+// CHECK-32: define internal void [[OUTL4]](
+// CHECK-64: define internal void [[OUTL4]](
 // CHECK: call void @__kmpc_for_static_init_4({{.+}}, {{.+}}, {{.+}} 33,
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
-// CHECK: define weak void @__omp_offloading_{{.*}}_l56(i[[SZ:64|32]] %{{[^,]+}}, [10 x [10 x i32]]* dereferenceable{{.*}})
+// CHECK: define weak void @__omp_offloading_{{.*}}_l58(i[[SZ:64|32]] %{{[^,]+}}, [10 x [10 x i32]]* dereferenceable{{.*}})
 // CHECK: call void [[OUTLINED:@__omp_outlined.*]](i32* %{{.+}}, i32* %{{.+}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, [10 x [10 x i32]]* %{{.*}})
 // CHECK: define internal void [[OUTLINED]](i32* noalias %{{.*}}, i32* noalias %{{.*}} i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, [10 x [10 x i32]]* dereferenceable{{.*}})
+// CHECK-DIV64: div i64
+// CHECK-DIV32-NO: div i64
 
-// CHECK: define weak void @__omp_offloading_{{.*}}_l63(i[[SZ:64|32]] %{{[^,]+}}, [1000 x i32]* dereferenceable{{.*}}, i32* %{{[^)]+}})
+// CHECK: define weak void @__omp_offloading_{{.*}}_l65(i[[SZ:64|32]] %{{[^,]+}}, [1000 x i32]* dereferenceable{{.*}}, i32* %{{[^)]+}})
 // CHECK: call void [[OUTLINED:@__omp_outlined.*]](i32* %{{.+}}, i32* %{{.+}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, i[[SZ]] %{{.*}}, [1000 x i32]* %{{.*}}, i32* %{{.*}})
 // CHECK: define internal void [[OUTLINED]](i32* noalias %{{.*}}, i32* noalias %{{.*}} i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, i[[SZ]] %{{.+}}, [1000 x i32]* dereferenceable{{.*}}, i32* %{{.*}})