From 8d26f0a602f8f21f99d38d12fd0f2fb21da1409f Mon Sep 17 00:00:00 2001 From: Ayal Zaks Date: Fri, 30 Jun 2017 08:02:35 +0000 Subject: [LV] Optimize for size when vectorizing loops with tiny trip count It may be detrimental to vectorize loops with very small trip count, as various costs of the vectorized loop body as well as enclosing overheads including runtime tests and scalar iterations may outweigh the gains of vectorizing. The current cost model measures the cost of the vectorized loop body only, expecting it will amortize other costs, and loops with known or expected very small trip counts are not vectorized at all. This patch allows loops with very small trip counts to be vectorized, but under OptForSize constraints, which ensure the cost of the loop body is dominant, having no runtime guards nor scalar iterations. Patch inspired by D32451. Differential Revision: https://reviews.llvm.org/D34373 llvm-svn: 306803 --- llvm/test/Transforms/LoopVectorize/small-loop.ll | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'llvm/test/Transforms/LoopVectorize/small-loop.ll') diff --git a/llvm/test/Transforms/LoopVectorize/small-loop.ll b/llvm/test/Transforms/LoopVectorize/small-loop.ll index 9a5dc4aa1b7..378283b464b 100644 --- a/llvm/test/Transforms/LoopVectorize/small-loop.ll +++ b/llvm/test/Transforms/LoopVectorize/small-loop.ll @@ -7,7 +7,7 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3 @c = common global [2048 x i32] zeroinitializer, align 16 ;CHECK-LABEL: @example1( -;CHECK-NOT: load <4 x i32> +;CHECK: load <4 x i32> ;CHECK: ret void define void @example1() nounwind uwtable ssp { br label %1 @@ -23,8 +23,8 @@ define void @example1() nounwind uwtable ssp { store i32 %6, i32* %7, align 4 %indvars.iv.next = add i64 %indvars.iv, 1 %lftr.wideiv = trunc i64 %indvars.iv.next to i32 - %exitcond = icmp eq i32 %lftr.wideiv, 8 ; <----- A really small trip count. - br i1 %exitcond, label %8, label %1 + %exitcond = icmp eq i32 %lftr.wideiv, 8 ; <----- A really small trip count + br i1 %exitcond, label %8, label %1 ; w/o scalar iteration overhead. ;