[PM] Simplify the new PM interface to the loop unroller and expose two

factory functions for the two modes the loop unroller is actually used
in in-tree: simplified full-unrolling and the entire thing including
partial unrolling.

I've also wired these up to nice names so you can express both of these
being in a pipeline easily. This is a precursor to actually enabling
these parts of the O2 pipeline.

Differential Revision: https://reviews.llvm.org/D28897

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@293136 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/Transforms/Scalar/LoopUnrollPass.h b/include/llvm/Transforms/Scalar/LoopUnrollPass.h
index 9da95ef81fad48a70dc827d78220e7d684eb96ee..0b22080284e5e344e538c8b0ee9f4297edbb7ae0 100644 (file)
--- a/include/llvm/Transforms/Scalar/LoopUnrollPass.h
+++ b/include/llvm/Transforms/Scalar/LoopUnrollPass.h
@@ -16,12 +16,29 @@
 
 namespace llvm {
 
-struct LoopUnrollPass : public PassInfoMixin<LoopUnrollPass> {
-  Optional<unsigned> ProvidedCount;
-  Optional<unsigned> ProvidedThreshold;
-  Optional<bool> ProvidedAllowPartial;
-  Optional<bool> ProvidedRuntime;
-  Optional<bool> ProvidedUpperBound;
+class LoopUnrollPass : public PassInfoMixin<LoopUnrollPass> {
+  const bool AllowPartialUnrolling;
+
+  explicit LoopUnrollPass(bool AllowPartialUnrolling)
+      : AllowPartialUnrolling(AllowPartialUnrolling) {}
+
+public:
+  /// Create an instance of the loop unroll pass that will support both full
+  /// and partial unrolling.
+  ///
+  /// This uses the target information (or flags) to control the thresholds for
+  /// different unrolling stategies but supports all of them.
+  static LoopUnrollPass create() {
+    return LoopUnrollPass(/*AllowPartialUnrolling*/ true);
+  }
+
+  /// Create an instance of the loop unroll pass that only does full loop
+  /// unrolling.
+  ///
+  /// This will disable any runtime or partial unrolling.
+  static LoopUnrollPass createFull() {
+    return LoopUnrollPass(/*AllowPartialUnrolling*/ false);
+  }
 
   PreservedAnalyses run(Loop &L, LoopAnalysisManager &AM,
                         LoopStandardAnalysisResults &AR, LPMUpdater &U);

diff --git a/lib/Passes/PassRegistry.def b/lib/Passes/PassRegistry.def
index bfa1868692d586c902c646d5d961d6b543a70382..23a932fe1a817684ebd49ca1b786d390dd995153 100644 (file)
--- a/lib/Passes/PassRegistry.def
+++ b/lib/Passes/PassRegistry.def
@@ -224,7 +224,8 @@ LOOP_PASS("loop-deletion", LoopDeletionPass())
 LOOP_PASS("simplify-cfg", LoopSimplifyCFGPass())
 LOOP_PASS("strength-reduce", LoopStrengthReducePass())
 LOOP_PASS("indvars", IndVarSimplifyPass())
-LOOP_PASS("unroll", LoopUnrollPass())
+LOOP_PASS("unroll", LoopUnrollPass::create())
+LOOP_PASS("unroll-full", LoopUnrollPass::createFull())
 LOOP_PASS("print-access-info", LoopAccessInfoPrinterPass(dbgs()))
 LOOP_PASS("print<ivusers>", IVUsersPrinterPass(dbgs()))
 LOOP_PASS("loop-predication", LoopPredicationPass())

diff --git a/lib/Transforms/Scalar/LoopUnrollPass.cpp b/lib/Transforms/Scalar/LoopUnrollPass.cpp
index 305122511f5b80fd986dc178f5d9957851facba5..d827db680d213bffb1529f878b218be4f02406d3 100644 (file)
--- a/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -1146,10 +1146,17 @@ PreservedAnalyses LoopUnrollPass::run(Loop &L, LoopAnalysisManager &AM,
   else
     OldLoops.insert(AR.LI.begin(), AR.LI.end());
 
+  // The API here is quite complex to call, but there are only two interesting
+  // states we support: partial and full (or "simple") unrolling. However, to
+  // enable these things we actually pass "None" in for the optional to avoid
+  // providing an explicit choice.
+  Optional<bool> AllowPartialParam, RuntimeParam, UpperBoundParam;
+  if (!AllowPartialUnrolling)
+    AllowPartialParam = RuntimeParam = UpperBoundParam = false;
   bool Changed = tryToUnrollLoop(&L, AR.DT, &AR.LI, &AR.SE, AR.TTI, AR.AC, *ORE,
-                                 /*PreserveLCSSA*/ true, ProvidedCount,
-                                 ProvidedThreshold, ProvidedAllowPartial,
-                                 ProvidedRuntime, ProvidedUpperBound);
+                                 /*PreserveLCSSA*/ true, /*Count*/ None,
+                                 /*Threshold*/ None, AllowPartialParam,
+                                 RuntimeParam, UpperBoundParam);
   if (!Changed)
     return PreservedAnalyses::all();
 

diff --git a/test/Transforms/LoopUnroll/full-unroll-bad-cost.ll b/test/Transforms/LoopUnroll/full-unroll-bad-cost.ll
index 9b6da8b62035fa97bd4e395ddec8eaa941c91a0d..9bbd21accc8efb5fd63ffd1d1914a7494bae0b3c 100644 (file)
--- a/test/Transforms/LoopUnroll/full-unroll-bad-cost.ll
+++ b/test/Transforms/LoopUnroll/full-unroll-bad-cost.ll
@@ -1,5 +1,5 @@
 ; RUN: opt -S -loop-unroll < %s | FileCheck %s
-; RUN: opt < %s -passes='require<opt-remark-emit>,loop(unroll)' -S | FileCheck %s
+; RUN: opt < %s -passes='require<opt-remark-emit>,loop(unroll-full)' -S | FileCheck %s
 
 ; LLVM should not try to fully unroll this loop.
 

diff --git a/test/Transforms/LoopUnroll/full-unroll-crashers.ll b/test/Transforms/LoopUnroll/full-unroll-crashers.ll
index 64a01a74359f2ccc465d21008aecc9993d3a30a3..d83e56635e8cff3a4bdaf10492cef23492b60d0b 100644 (file)
--- a/test/Transforms/LoopUnroll/full-unroll-crashers.ll
+++ b/test/Transforms/LoopUnroll/full-unroll-crashers.ll
@@ -1,6 +1,6 @@
 ; Check that we don't crash on corner cases.
 ; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=1 -unroll-max-percent-threshold-boost=200 -o /dev/null
-; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=1 -unroll-max-percent-threshold-boost=200 -o /dev/null
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=1 -unroll-max-percent-threshold-boost=200 -o /dev/null
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 @known_constant = internal unnamed_addr constant [10 x i32] [i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1], align 16

diff --git a/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll b/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
index b83913b1818a8ada3faaad4a7006fbdffc09eb7a..a143056affe777f5c872f93b63283ea7743893d7 100644 (file)
--- a/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
+++ b/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
@@ -1,5 +1,5 @@
 ; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
-; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 @unknown_global = internal unnamed_addr global [9 x i32] [i32 0, i32 -1, i32 0, i32 -1, i32 5, i32 -1, i32 0, i32 -1, i32 0], align 16

diff --git a/test/Transforms/LoopUnroll/full-unroll-heuristics-cmp.ll b/test/Transforms/LoopUnroll/full-unroll-heuristics-cmp.ll
index 31b91972fdc70426b09ec670824e1cf8c20c2ace..e65f794286ee9d393724ba8f970416669515df7d 100644 (file)
--- a/test/Transforms/LoopUnroll/full-unroll-heuristics-cmp.ll
+++ b/test/Transforms/LoopUnroll/full-unroll-heuristics-cmp.ll
@@ -1,5 +1,5 @@
 ; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
-; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 @known_constant = internal unnamed_addr constant [10 x i32] [i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1], align 16

diff --git a/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll b/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
index 5a3123df5077d2cbd47c51138a63ed80cc16474f..57de3041f5713681b270a7334039e90768ad3ec7 100644 (file)
--- a/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
+++ b/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
@@ -1,5 +1,5 @@
 ; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=12 -unroll-max-percent-threshold-boost=400 | FileCheck %s
-; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=12 -unroll-max-percent-threshold-boost=400 | FileCheck %s
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=12 -unroll-max-percent-threshold-boost=400 | FileCheck %s
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 @known_constant = internal unnamed_addr constant [10 x i32] [i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0, i32 0], align 16

diff --git a/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll b/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
index 3e5fe1d889e9aabd9ead22ff9f35bcaf09fc2344..238869d120ba8a874a9c807289f479874a508ff7 100644 (file)
--- a/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
+++ b/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
@@ -1,5 +1,5 @@
 ; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
-; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 ; When examining gep-instructions we shouldn't consider them simplified if the

diff --git a/test/Transforms/LoopUnroll/full-unroll-heuristics-phi-prop.ll b/test/Transforms/LoopUnroll/full-unroll-heuristics-phi-prop.ll
index bfcd9208d8cb6146b1b05aa5460b67cb1e2850fc..aa517cb1589daa8076183d51baf5dbd92f00b2f0 100644 (file)
--- a/test/Transforms/LoopUnroll/full-unroll-heuristics-phi-prop.ll
+++ b/test/Transforms/LoopUnroll/full-unroll-heuristics-phi-prop.ll
@@ -1,5 +1,5 @@
 ; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
-; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=100 -unroll-threshold=10 -unroll-max-percent-threshold-boost=200 | FileCheck %s
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 define i64 @propagate_loop_phis() {

diff --git a/test/Transforms/LoopUnroll/full-unroll-heuristics.ll b/test/Transforms/LoopUnroll/full-unroll-heuristics.ll
index 7189fbb3483337c13a7f21c8082061a89dc690b0..a2fe1f5e3fdaadaa88ed2b6cce122a79cd44a444 100644 (file)
--- a/test/Transforms/LoopUnroll/full-unroll-heuristics.ll
+++ b/test/Transforms/LoopUnroll/full-unroll-heuristics.ll
@@ -21,6 +21,15 @@
 ; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=20 -unroll-max-percent-threshold-boost=200 | FileCheck %s -check-prefix=TEST2
 ; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=20 -unroll-max-percent-threshold-boost=100 | FileCheck %s -check-prefix=TEST3
 
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10 -unroll-max-percent-threshold-boost=100 | FileCheck %s -check-prefix=TEST1
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=20 -unroll-max-percent-threshold-boost=200 | FileCheck %s -check-prefix=TEST2
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=20 -unroll-max-percent-threshold-boost=100 | FileCheck %s -check-prefix=TEST3
+
+; Check that these work when the unroller has partial unrolling enabled too.
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10 -unroll-max-percent-threshold-boost=100 | FileCheck %s -check-prefix=TEST1
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=20 -unroll-max-percent-threshold-boost=200 | FileCheck %s -check-prefix=TEST2
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=20 -unroll-max-percent-threshold-boost=100 | FileCheck %s -check-prefix=TEST3
+
 ; If the absolute threshold is too low, we should not unroll:
 ; TEST1: %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @known_constant, i64 0, i64 %iv
 
@@ -32,6 +41,7 @@
 
 ; And check that we don't crash when we're not allowed to do any analysis.
 ; RUN: opt < %s -loop-unroll -unroll-max-iteration-count-to-analyze=0 -disable-output
+; RUN: opt < %s -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-max-iteration-count-to-analyze=0 -disable-output
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 @known_constant = internal unnamed_addr constant [9 x i32] [i32 0, i32 -1, i32 0, i32 -1, i32 5, i32 -1, i32 0, i32 -1, i32 0], align 16

diff --git a/test/Transforms/LoopUnroll/full-unroll-keep-first-exit.ll b/test/Transforms/LoopUnroll/full-unroll-keep-first-exit.ll
index 27cef367c376ea42d210538a60f1719b5e2f7592..682d1b35c1fae3b24b3d6c27e0094c2e50160653 100644 (file)
--- a/test/Transforms/LoopUnroll/full-unroll-keep-first-exit.ll
+++ b/test/Transforms/LoopUnroll/full-unroll-keep-first-exit.ll
@@ -1,5 +1,5 @@
 ; RUN: opt -S -loop-unroll < %s | FileCheck %s
-; RUN: opt -S -passes='require<opt-remark-emit>,loop(unroll)' < %s | FileCheck %s
+; RUN: opt -S -passes='require<opt-remark-emit>,loop(unroll-full)' < %s | FileCheck %s
 
 ; Unroll twice, with first loop exit kept
 ; CHECK-LABEL: @s32_max1

diff --git a/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll b/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
index 62124ce3876268495acb147606dedeac0271be89..8e5a866f8ca731c9d50f2bd1d44c555109ac3e11 100644 (file)
--- a/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
+++ b/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
@@ -1,4 +1,8 @@
 ; RUN: opt < %s -S -unroll-partial-threshold=20 -unroll-threshold=20 -loop-unroll -unroll-allow-partial -unroll-runtime -unroll-allow-remainder -unroll-max-percent-threshold-boost=100 | FileCheck %s
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll)' -unroll-partial-threshold=20 -unroll-threshold=20 -unroll-allow-partial -unroll-runtime -unroll-allow-remainder -unroll-max-percent-threshold-boost=100 | FileCheck %s
+;
+; Also check that the simple unroller doesn't allow the partial unrolling.
+; RUN: opt < %s -S -passes='require<opt-remark-emit>,loop(unroll-full)' -unroll-partial-threshold=20 -unroll-threshold=20 -unroll-allow-partial -unroll-runtime -unroll-allow-remainder -unroll-max-percent-threshold-boost=100 | FileCheck %s --check-prefix=CHECK-NO-UNROLL
 
 ; The Loop TripCount is 9. However unroll factors 3 or 9 exceed given threshold.
 ; The test checks that we choose a smaller, power-of-two, unroll count and do not give up on unrolling.
@@ -8,6 +12,10 @@
 ; CHECK: for.body.1:
 ; CHECK: store
 
+; CHECK-NO-UNROLL: for.body:
+; CHECK-NO-UNROLL: store
+; CHECK-NO-UNROLL-NOT: store
+
 define void @foo(i32* nocapture %a, i32* nocapture readonly %b) nounwind uwtable {
 entry:
   br label %for.body