From 6bed13c5514df06979eb49e096a6dc69942c8edf Mon Sep 17 00:00:00 2001 From: James Molloy Date: Mon, 28 Nov 2016 11:07:37 +0000 Subject: [PATCH] [InlineCost] Reduce inline thresholds to compensate for cost changes In r286814, the algorithm for calculating inline costs changed. This caused more inlining to take place which is especially apparent in optsize and minsize modes. As the cost calculation removed a skewed behaviour (we were inconsistent about the cost of calls) it isn't possible to update the thresholds to get exactly the same behaviour as before. However, this threshold change accounts for the very common case where an inline candidate has no calls within it. In this case, r286814 would inline around 5-6 more (IR) instructions. The changes to -Oz have been heavily benchmarked. The "obvious" value for the inline threshold at -Oz is zero, but due to inaccuracies in the inline heuristics this can actually cause code size increases due to not inlining key thunk functions (that then disappear). Experimentally, 5 was the sweet spot for code size over the test-suite. For -Os, this change removes the outlier results shown up by green dragon (http://104.154.54.203/db_default/v4/nts/13248). Fixes D26848. llvm-svn: 288024 --- llvm/include/llvm/Analysis/InlineCost.h | 6 +++--- llvm/test/Transforms/Inline/ephemeral.ll | 14 ++++++-------- llvm/test/Transforms/Inline/inline-fp.ll | 4 ++-- 3 files changed, 11 insertions(+), 13 deletions(-) diff --git a/llvm/include/llvm/Analysis/InlineCost.h b/llvm/include/llvm/Analysis/InlineCost.h index 10f1811..5e7b002 100644 --- a/llvm/include/llvm/Analysis/InlineCost.h +++ b/llvm/include/llvm/Analysis/InlineCost.h @@ -30,13 +30,13 @@ class TargetTransformInfo; namespace InlineConstants { // Various thresholds used by inline cost analysis. /// Use when optsize (-Os) is specified. -const int OptSizeThreshold = 75; +const int OptSizeThreshold = 50; /// Use when minsize (-Oz) is specified. -const int OptMinSizeThreshold = 25; +const int OptMinSizeThreshold = 5; /// Use when -O3 is specified. -const int OptAggressiveThreshold = 275; +const int OptAggressiveThreshold = 250; // Various magic constants used to adjust heuristics. const int InstrCost = 5; diff --git a/llvm/test/Transforms/Inline/ephemeral.ll b/llvm/test/Transforms/Inline/ephemeral.ll index 7e5ae03..6261d4b 100644 --- a/llvm/test/Transforms/Inline/ephemeral.ll +++ b/llvm/test/Transforms/Inline/ephemeral.ll @@ -2,10 +2,8 @@ @a = global i32 4 -define i1 @inner() { +define i32 @inner() { %a1 = load volatile i32, i32* @a - %x1 = add i32 %a1, %a1 - %c = icmp eq i32 %x1, 0 ; Here are enough instructions to prevent inlining, but because they are used ; only by the @llvm.assume intrinsic, they're free (and, thus, inlining will @@ -14,18 +12,18 @@ define i1 @inner() { %a3 = sub i32 %a1, 5 %a4 = udiv i32 %a3, -13 %a5 = mul i32 %a4, %a4 - %a6 = add i32 %a5, %x1 + %a6 = add i32 %a5, %a5 %ca = icmp sgt i32 %a6, -7 tail call void @llvm.assume(i1 %ca) - ret i1 %c + ret i32 %a1 } ; @inner() should be inlined for -Oz. ; CHECK-NOT: call i1 @inner -define i1 @outer() optsize { - %r = call i1 @inner() - ret i1 %r +define i32 @outer() optsize { + %r = call i32 @inner() + ret i32 %r } declare void @llvm.assume(i1) nounwind diff --git a/llvm/test/Transforms/Inline/inline-fp.ll b/llvm/test/Transforms/Inline/inline-fp.ll index cf42d82..59554cd 100644 --- a/llvm/test/Transforms/Inline/inline-fp.ll +++ b/llvm/test/Transforms/Inline/inline-fp.ll @@ -132,5 +132,5 @@ declare float @fabsf(float) optsize minsize declare float @llvm.pow.f32(float, float) optsize minsize -attributes #0 = { minsize optsize } -attributes #1 = { minsize optsize "use-soft-float"="true" } +attributes #0 = { optsize } +attributes #1 = { optsize "use-soft-float"="true" } -- 2.7.4