From e190f77f91b1a1aeb675a23794aeb3162566305d Mon Sep 17 00:00:00 2001 From: Suyog Sarda Date: Tue, 11 Nov 2014 07:39:27 +0000 Subject: [PATCH] Addition to r216371 (SLP and Loop Vectorization) and r218607 where cost model for signed division by power of 2 was improved for AArch64. The revision r218607 missed test case for Loop Vectorization. Adding it in this revision. Differential Revision: http://reviews.llvm.org/D6181 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@221674 91177308-0d34-0410-b5e6-96231b3b80d8 --- .../LoopVectorize/AArch64/sdiv-pow2.ll | 31 +++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll diff --git a/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll b/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll new file mode 100644 index 00000000000..a01d54312a6 --- /dev/null +++ b/test/Transforms/LoopVectorize/AArch64/sdiv-pow2.ll @@ -0,0 +1,31 @@ +; RUN: opt < %s -loop-vectorize -mtriple=aarch64-unknown-linux-gnu -mcpu=cortex-a57 -S | FileCheck %s +target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128" +target triple = "aarch64--linux-gnu" + +%struct.anon = type { [100 x i32], i32, [100 x i32] } + +@Foo = common global %struct.anon zeroinitializer, align 4 + +; CHECK-LABEL: @foo( +; CHECK: load <4 x i32>* +; CHECK: sdiv <4 x i32> +; CHECK: store <4 x i32> + +define void @foo(){ +entry: + br label %for.body + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ] + %arrayidx = getelementptr inbounds %struct.anon* @Foo, i64 0, i32 2, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %div = sdiv i32 %0, 2 + %arrayidx2 = getelementptr inbounds %struct.anon* @Foo, i64 0, i32 0, i64 %indvars.iv + store i32 %div, i32* %arrayidx2, align 4 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + %exitcond = icmp eq i64 %indvars.iv.next, 100 + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body + ret void +} -- 2.40.0