Use continuous boosting factor for complete unroll.

Summary:
The current loop complete unroll algorithm checks if unrolling complete will reduce the runtime by a certain percentage. If yes, it will apply a fixed boosting factor to the threshold (by discounting cost). The problem for this approach is that the threshold abruptly. This patch makes the boosting factor a function of runtime reduction percentage, capped by a fixed threshold. In this way, the threshold changes continuously.

The patch also simplified the code by reducing one parameter in UP.

The patch only affects code-gen of two speccpu2006 benchmark:

445.gobmk binary size decreases 0.08%, no performance change.
464.h264ref binary size increases 0.24%, no performance change.

Reviewers: mzolotukhin, chandlerc

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D26989

llvm-svn: 290737

9 files changed, 15 insertions, 18 deletions

diff --git a/llvm/test/Transforms/LoopUnroll/full-unroll-crashers.ll b/llvm/test/Transforms/LoopUnroll/full-unroll-crashers.ll
index f5c7734de96..9f1529139de 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-crashers.ll
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-crashers.ll
@@ -1,5 +1,5 @@
 ; 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-percent-dynamic-cost-saved-threshold=20 -o /dev/null
+; 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
 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 11c9f9635ca..26124fb32ca 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10  -unroll-percent-dynamic-cost-saved-threshold=70 -unroll-dynamic-cost-savings-discount=90 | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -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 12ad4f26bf8..8bddb1b225c 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-cmp.ll
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-cmp.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-dynamic-cost-savings-discount=1000 -unroll-threshold=10 -unroll-percent-dynamic-cost-saved-threshold=40 | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -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 6ee73b6fe4f..83c105ca23f 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-dce.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-dynamic-cost-savings-discount=1000 -unroll-threshold=10 -unroll-percent-dynamic-cost-saved-threshold=60 | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -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 723a384ea2d..230912538d2 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-geps.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-dynamic-cost-savings-discount=1000 -unroll-threshold=10 -unroll-percent-dynamic-cost-saved-threshold=60 | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -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 dd8582e6877..a1fab3cc71e 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-phi-prop.ll
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics-phi-prop.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=100 -unroll-dynamic-cost-savings-discount=1000 -unroll-threshold=10 -unroll-percent-dynamic-cost-saved-threshold=50 | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -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 904a65a1bc0..7189fbb3483 100644
--- a/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics.ll
+++ b/llvm/test/Transforms/LoopUnroll/full-unroll-heuristics.ll
@@ -17,21 +17,18 @@
 ; optimizations to remove ~55% of the instructions, the loop body size is 9,
 ; and unrolled size is 65.
 
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10  -unroll-percent-dynamic-cost-saved-threshold=20 -unroll-dynamic-cost-savings-discount=0 | FileCheck %s -check-prefix=TEST1
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10  -unroll-percent-dynamic-cost-saved-threshold=20 -unroll-dynamic-cost-savings-discount=90 | FileCheck %s -check-prefix=TEST2
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10  -unroll-percent-dynamic-cost-saved-threshold=80 -unroll-dynamic-cost-savings-discount=90 | FileCheck %s -check-prefix=TEST3
-; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=100 -unroll-percent-dynamic-cost-saved-threshold=80 -unroll-dynamic-cost-savings-discount=0 | FileCheck %s -check-prefix=TEST4
+; RUN: opt < %s -S -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 -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
 
-; If the absolute threshold is too low, or if we can't optimize away requested
-; percent of instructions, we shouldn't unroll:
+; 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
-; TEST3: %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @known_constant, i64 0, i64 %iv
 
 ; Otherwise, we should:
 ; TEST2-NOT: %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @known_constant, i64 0, i64 %iv
 
-; Also, we should unroll if the 'unroll-threshold' is big enough:
-; TEST4-NOT: %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @known_constant, i64 0, i64 %iv
+; If we do not boost threshold, the unroll will not happen:
+; TEST3: %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @known_constant, i64 0, i64 %iv
 
 ; 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
diff --git a/llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll b/llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
index a68a9ef2730..49c823a28c7 100644
--- a/llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
+++ b/llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -unroll-threshold=20 -loop-unroll -unroll-allow-partial -unroll-runtime -unroll-allow-remainder -unroll-dynamic-cost-savings-discount=0 | FileCheck %s
+; RUN: opt < %s -S -unroll-threshold=20 -loop-unroll -unroll-allow-partial -unroll-runtime -unroll-allow-remainder -unroll-max-percent-threshold-boost=100 | FileCheck %s
 
 ; 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.
@@ -21,7 +21,7 @@ for.body:                                         ; preds = %for.body, %entry
   %st = trunc i64 %indvars.iv to i32
   store i32 %st, i32* %arrayidx2, align 4
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %exitcond = icmp eq i64 %indvars.iv.next, 10
+  %exitcond = icmp eq i64 %indvars.iv.next, 20
   br i1 %exitcond, label %for.end, label %for.body
 
 for.end:                                          ; preds = %for.body
diff --git a/llvm/test/Transforms/LoopUnroll/unroll-heuristics-pgo.ll b/llvm/test/Transforms/LoopUnroll/unroll-heuristics-pgo.ll
index 57bac8560d4..f7add40b9d1 100644
--- a/llvm/test/Transforms/LoopUnroll/unroll-heuristics-pgo.ll
+++ b/llvm/test/Transforms/LoopUnroll/unroll-heuristics-pgo.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -loop-unroll -unroll-runtime -unroll-threshold=40 -unroll-dynamic-cost-savings-discount=0 | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -unroll-runtime -unroll-threshold=40 -unroll-max-percent-threshold-boost=100 | FileCheck %s
 
 @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