From d6f179cad6c93a517d3ab62ed61680678365cde3 Mon Sep 17 00:00:00 2001 From: Matthew Simpson Date: Wed, 24 May 2017 15:26:15 +0000 Subject: [LV] Update type in cost model for scalarization For non-uniform instructions marked for scalarization, we should update `VectorTy` when computing instruction costs to reflect the scalar type. In addition to determining instruction costs, this type is also used to signal that all instructions in the loop will be scalarized. This currently affects memory instructions and non-pointer induction variables and their updates. (We also mark GEPs scalar after vectorization, but their cost is computed together with memory instructions.) For scalarized induction updates, this patch also scales the scalar cost by the vectorization factor, corresponding to each induction step. llvm-svn: 303763 --- .../AArch64/no_vector_instructions.ll | 26 ++++++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll (limited to 'llvm/test') diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll b/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll new file mode 100644 index 00000000000..a7f414b8694 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll @@ -0,0 +1,26 @@ +; REQUIRES: asserts +; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -S -debug-only=loop-vectorize 2>&1 | FileCheck %s + +target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128" +target triple = "aarch64--linux-gnu" + +; CHECK-LABEL: all_scalar +; CHECK: LV: Found scalar instruction: %i.next = add nuw nsw i64 %i, 2 +; CHECK: LV: Found an estimated cost of 2 for VF 2 For instruction: %i.next = add nuw nsw i64 %i, 2 +; CHECK: LV: Not considering vector loop of width 2 because it will not generate any vector instructions +; +define void @all_scalar(i64* %a, i64 %n) { +entry: + br label %for.body + +for.body: + %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ] + %tmp0 = getelementptr i64, i64* %a, i64 %i + store i64 0, i64* %tmp0, align 1 + %i.next = add nuw nsw i64 %i, 2 + %cond = icmp eq i64 %i.next, %n + br i1 %cond, label %for.end, label %for.body + +for.end: + ret void +} -- cgit v1.2.3