[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

llvm-svn: 293136

10 files changed, 26 insertions, 8 deletions

diff --git a/llvm/test/Transforms/LoopUnroll/full-unroll-bad-cost.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-bad-cost.ll
index 9b6da8b6203..9bbd21accc8 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-bad-cost.ll
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/full-unroll-crashers.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-crashers.ll
index 64a01a74359..d83e56635e8 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-crashers.ll
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
index b83913b1818..a143056affe 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-cmp.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-cmp.ll
index 31b91972fdc..e65f794286e 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-cmp.ll
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
index 5a3123df507..57de3041f57 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
index 3e5fe1d889e..238869d120b 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-phi-prop.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-phi-prop.ll
index bfcd9208d8c..aa517cb1589 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-phi-prop.ll
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics.ll
index 7189fbb3483..a2fe1f5e3fd 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics.ll
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/full-unroll-keep-first-exit.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-keep-first-exit.ll
index 27cef367c37..682d1b35c1f 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-keep-first-exit.ll
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll b/llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
index 62124ce3876..8e5a866f8ca 100644
--- a/llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
+++ b/llvm/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