[llvm-branch-commits] [llvm] 9833a55 - [OpenMP] Run an extra 'OpenMPOpt' pass in LTO-mode

[Tom Stellard via llvm-branch-commits]

Author: Joseph Huber
Date: 2023-01-27T20:44:34-08:00
New Revision: 9833a552e36c3a9fb6491d00a2b22830fad91bef

URL: https://github.com/llvm/llvm-project/commit/9833a552e36c3a9fb6491d00a2b22830fad91bef
DIFF: https://github.com/llvm/llvm-project/commit/9833a552e36c3a9fb6491d00a2b22830fad91bef.diff

LOG: [OpenMP] Run an extra 'OpenMPOpt' pass in LTO-mode

The `OpenMPOpt` pass is pivotal to the performance of many OpenMP
offloading programs. When we perform non-LTO builds with OpenMP we used
to link the OpenMP deviceRTL individually for each TU. This lead to us
getting an additional attributor run on the combined runtime and user
code. When we used LTO we lost a run and suffered a large performance
degradation. This patch simply adds in the extra `OpenMPOpt` pass that
we miss into the LTO pipeline. This patch fixes the performance
regression shown in applications that used OpenMP offloading in LTO
mode.

Previously, this wasn't legal to do as we could emit new runtime calls
into the module. That was fixed by D142646.

Depends on D142646

Fixes https://github.com/llvm/llvm-project/issues/60300

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D142650

(cherry picked from commit 6185246f4f62345d0cfdaef62da7e15b01d52557)

Added: 
    

Modified: 
    clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
    llvm/lib/Passes/PassBuilderPipelines.cpp
    llvm/test/Other/new-pm-lto-defaults.ll

Removed: 
    


################################################################################
diff  --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
index 587e7f3043ded..361179ad8a3b2 100644
--- a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
+++ b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -513,8 +513,6 @@ std::unique_ptr<lto::LTO> createLTO(
   assert(CGOptLevelOrNone && "Invalid optimization level");
   Conf.CGOptLevel = *CGOptLevelOrNone;
   Conf.OptLevel = OptLevel[1] - '0';
-  if (Conf.OptLevel > 0)
-    Conf.UseDefaultPipeline = true;
   Conf.DefaultTriple = Triple.getTriple();
 
   LTOError = false;

diff  --git a/llvm/lib/Passes/PassBuilderPipelines.cpp b/llvm/lib/Passes/PassBuilderPipelines.cpp
index 0762c535f7f58..75b34b81b5fed 100644
--- a/llvm/lib/Passes/PassBuilderPipelines.cpp
+++ b/llvm/lib/Passes/PassBuilderPipelines.cpp
@@ -1712,6 +1712,9 @@ PassBuilder::buildLTODefaultPipeline(OptimizationLevel Level,
   // Optimize globals again after we ran the inliner.
   MPM.addPass(GlobalOptPass());
 
+  // Run the OpenMPOpt pass again after global optimizations.
+  MPM.addPass(OpenMPOptPass(ThinOrFullLTOPhase::FullLTOPostLink));
+
   // Garbage collect dead functions.
   MPM.addPass(GlobalDCEPass());
 

diff  --git a/llvm/test/Other/new-pm-lto-defaults.ll b/llvm/test/Other/new-pm-lto-defaults.ll
index e7b054b6311ed..55b4ad0526a0a 100644
--- a/llvm/test/Other/new-pm-lto-defaults.ll
+++ b/llvm/test/Other/new-pm-lto-defaults.ll
@@ -78,6 +78,7 @@
 ; CHECK-O23SZ-NEXT: Running pass: InlinerPass
 ; CHECK-O23SZ-NEXT: Invalidating analysis: InlineAdvisorAnalysis
 ; CHECK-O23SZ-NEXT: Running pass: GlobalOptPass
+; CHECK-O23SZ-NEXT: Running pass: OpenMPOptPass
 ; CHECK-O23SZ-NEXT: Running pass: GlobalDCEPass
 ; CHECK-O23SZ-NEXT: Running pass: ArgumentPromotionPass
 ; CHECK-O23SZ-NEXT: Running pass: DeadArgumentEliminationPass