diff options
author | Carlo Bertolli <cbertol@us.ibm.com> | 2016-04-04 15:55:02 +0000 |
---|---|---|
committer | Carlo Bertolli <cbertol@us.ibm.com> | 2016-04-04 15:55:02 +0000 |
commit | c687225b436cd0ff0a6061a6f79f13c35e6b6228 (patch) | |
tree | 71f1428bdf6f4138fd2c53ebe76960b814fc4ec2 /clang/lib/CodeGen/CGStmtOpenMP.cpp | |
parent | 1eec3f01f07c88325f9958b85dee8d33f548af52 (diff) | |
download | bcm5719-llvm-c687225b436cd0ff0a6061a6f79f13c35e6b6228.tar.gz bcm5719-llvm-c687225b436cd0ff0a6061a6f79f13c35e6b6228.zip |
[OPENMP] Codegen for teams directive for NVPTX
This patch implements the teams directive for the NVPTX backend. It is different from the host code generation path as it:
Does not call kmpc_fork_teams. All necessary teams and threads are started upon touching the target region, when launching a CUDA kernel, and their execution is coordinated through sequential and parallel regions within the target region.
Does not call kmpc_push_num_teams even if a num_teams of thread_limit clause is present. Setting the number of teams and the thread limit is implemented by the nvptx-related runtime.
Please note that I am now passing a Clang Expr * to emitPushNumTeams instead of the originally chosen llvm::Value * type. The reason for that is that I want to avoid emitting expressions for num_teams and thread_limit if they are not needed in the target region.
http://reviews.llvm.org/D17963
llvm-svn: 265304
Diffstat (limited to 'clang/lib/CodeGen/CGStmtOpenMP.cpp')
-rw-r--r-- | clang/lib/CodeGen/CGStmtOpenMP.cpp | 17 |
1 files changed, 5 insertions, 12 deletions
diff --git a/clang/lib/CodeGen/CGStmtOpenMP.cpp b/clang/lib/CodeGen/CGStmtOpenMP.cpp index 84059ab2912..bd208cb4df5 100644 --- a/clang/lib/CodeGen/CGStmtOpenMP.cpp +++ b/clang/lib/CodeGen/CGStmtOpenMP.cpp @@ -3098,18 +3098,11 @@ static void emitCommonOMPTeamsDirective(CodeGenFunction &CGF, const OMPNumTeamsClause *NT = TD.getSingleClause<OMPNumTeamsClause>(); const OMPThreadLimitClause *TL = TD.getSingleClause<OMPThreadLimitClause>(); if (NT || TL) { - llvm::Value *NumTeamsVal = (NT) ? CGF.Builder.CreateIntCast( - CGF.EmitScalarExpr(NT->getNumTeams()), CGF.CGM.Int32Ty, - /* isSigned = */ true) : - CGF.Builder.getInt32(0); - - llvm::Value *ThreadLimitVal = (TL) ? CGF.Builder.CreateIntCast( - CGF.EmitScalarExpr(TL->getThreadLimit()), CGF.CGM.Int32Ty, - /* isSigned = */ true) : - CGF.Builder.getInt32(0); - - CGF.CGM.getOpenMPRuntime().emitNumTeamsClause(CGF, NumTeamsVal, - ThreadLimitVal, S.getLocStart()); + Expr *NumTeams = (NT) ? NT->getNumTeams() : nullptr; + Expr *ThreadLimit = (TL) ? TL->getThreadLimit() : nullptr; + + CGF.CGM.getOpenMPRuntime().emitNumTeamsClause(CGF, NumTeams, ThreadLimit, + S.getLocStart()); } OMPLexicalScope Scope(CGF, S); |