[llvm] Swap UnrollAndJam Pass to before the SLP Vectorizer Pass (PR #97029)

[via llvm-commits]

https://github.com/adprasad-nvidia updated https://github.com/llvm/llvm-project/pull/97029

>From b6e59756e13d999c15a68107c94f8f69b7b1a5df Mon Sep 17 00:00:00 2001
From: adprasad <adprasad at nvidia.com>
Date: Tue, 18 Jun 2024 13:36:01 +0530
Subject: [PATCH 1/2] [UnJ] Move LoopUnrollAndJamPass before SLPVectorizerPass

---
 llvm/lib/Passes/PassBuilderPipelines.cpp | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/llvm/lib/Passes/PassBuilderPipelines.cpp b/llvm/lib/Passes/PassBuilderPipelines.cpp
index 926515c9508a9..9fd36e92be981 100644
--- a/llvm/lib/Passes/PassBuilderPipelines.cpp
+++ b/llvm/lib/Passes/PassBuilderPipelines.cpp
@@ -1306,6 +1306,11 @@ void PassBuilder::addVectorPasses(OptimizationLevel Level,
     FPM.addPass(BDCEPass());
   }
 
+  // We do UnrollAndJam in a separate LPM to Unroll ensure it happens first.
+  if (EnableUnrollAndJam && PTO.LoopUnrolling) {
+    FPM.addPass(createFunctionToLoopPassAdaptor(
+        LoopUnrollAndJamPass(Level.getSpeedupLevel())));
+  }
   // Optimize parallel scalar instruction chains into SIMD instructions.
   if (PTO.SLPVectorization) {
     FPM.addPass(SLPVectorizerPass());
@@ -1324,11 +1329,6 @@ void PassBuilder::addVectorPasses(OptimizationLevel Level,
     // FIXME: It would be really good to use a loop-integrated instruction
     // combiner for cleanup here so that the unrolling and LICM can be pipelined
     // across the loop nests.
-    // We do UnrollAndJam in a separate LPM to ensure it happens before unroll
-    if (EnableUnrollAndJam && PTO.LoopUnrolling) {
-      FPM.addPass(createFunctionToLoopPassAdaptor(
-          LoopUnrollAndJamPass(Level.getSpeedupLevel())));
-    }
     FPM.addPass(LoopUnrollPass(LoopUnrollOptions(
         Level.getSpeedupLevel(), /*OnlyWhenForced=*/!PTO.LoopUnrolling,
         PTO.ForgetAllSCEVInLoopUnroll)));

>From be8ed07c7945eb02c3447ef77da9f9b3eb400460 Mon Sep 17 00:00:00 2001
From: adprasad <adprasad at nvidia.com>
Date: Tue, 25 Jun 2024 15:26:56 +0530
Subject: [PATCH 2/2] [UnJ] Add comments explaining new position of
 UnrollAndJam

---
 llvm/lib/Passes/PassBuilderPipelines.cpp | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/llvm/lib/Passes/PassBuilderPipelines.cpp b/llvm/lib/Passes/PassBuilderPipelines.cpp
index 9fd36e92be981..014df0e17c6a9 100644
--- a/llvm/lib/Passes/PassBuilderPipelines.cpp
+++ b/llvm/lib/Passes/PassBuilderPipelines.cpp
@@ -1234,6 +1234,7 @@ void PassBuilder::addVectorPasses(OptimizationLevel Level,
     // combiner for cleanup here so that the unrolling and LICM can be pipelined
     // across the loop nests.
     // We do UnrollAndJam in a separate LPM to ensure it happens before unroll
+    // In order for outer loop vectorization to be done, UnrollAndJam must occur before the SLPVectorizerPass.
     if (EnableUnrollAndJam && PTO.LoopUnrolling)
       FPM.addPass(createFunctionToLoopPassAdaptor(
           LoopUnrollAndJamPass(Level.getSpeedupLevel())));
@@ -1307,6 +1308,7 @@ void PassBuilder::addVectorPasses(OptimizationLevel Level,
   }
 
   // We do UnrollAndJam in a separate LPM to Unroll ensure it happens first.
+  // In order for outer loop vectorization to be done, UnrollAndJam must occur before the SLPVectorizerPass.
   if (EnableUnrollAndJam && PTO.LoopUnrolling) {
     FPM.addPass(createFunctionToLoopPassAdaptor(
         LoopUnrollAndJamPass(Level.getSpeedupLevel())));