From 455c2ee39463ca0779849c9248e10c765ad11a77 Mon Sep 17 00:00:00 2001 From: Matthew Simpson Date: Thu, 2 Mar 2017 13:55:05 +0000 Subject: [PATCH] [LV] Considier non-consecutive but vectorizable accesses for VF selection When computing the smallest and largest types for selecting the maximum vectorization factor, we currently ignore loads and stores of pointer types if the memory access is non-consecutive. We do this because such accesses must be scalarized regardless of vectorization factor, and thus shouldn't be considered when determining the factor. This patch makes this check less aggressive by also considering non-consecutive accesses that may be vectorized, such as interleaved accesses. Because we don't know at the time of the check if an accesses will certainly be vectorized (this is a cost model decision given a particular VF), we consider all accesses that can potentially be vectorized. Differential Revision: https://reviews.llvm.org/D30305 llvm-svn: 296747 --- .../Transforms/Vectorize/LoopVectorize.cpp | 13 ++++++-- .../AArch64/smallest-and-widest-types.ll | 33 +++++++++++++++++++ 2 files changed, 43 insertions(+), 3 deletions(-) create mode 100644 llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index 36570b49bb0b..763ce0838377 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -6326,9 +6326,16 @@ LoopVectorizationCostModel::getSmallestAndWidestTypes() { T = ST->getValueOperand()->getType(); // Ignore loaded pointer types and stored pointer types that are not - // consecutive. However, we do want to take consecutive stores/loads of - // pointer vectors into account. - if (T->isPointerTy() && !isConsecutiveLoadOrStore(&I)) + // vectorizable. + // + // FIXME: The check here attempts to predict whether a load or store will + // be vectorized. We only know this for certain after a VF has + // been selected. Here, we assume that if an access can be + // vectorized, it will be. We should also look at extending this + // optimization to non-pointer types. + // + if (T->isPointerTy() && !isConsecutiveLoadOrStore(&I) && + !Legal->isAccessInterleaved(&I) && !Legal->isLegalGatherOrScatter(&I)) continue; MinWidth = std::min(MinWidth, diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll b/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll new file mode 100644 index 000000000000..1ae7dadeffd7 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll @@ -0,0 +1,33 @@ +; REQUIRES: asserts +; RUN: opt < %s -loop-vectorize -debug-only=loop-vectorize -disable-output 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: Checking a loop in "interleaved_access" +; CHECK: The Smallest and Widest types: 64 / 64 bits +; +define void @interleaved_access(i8** %A, i64 %N) { +for.ph: + br label %for.body + +for.body: + %i = phi i64 [ %i.next.3, %for.body ], [ 0, %for.ph ] + %tmp0 = getelementptr inbounds i8*, i8** %A, i64 %i + store i8* null, i8** %tmp0, align 8 + %i.next.0 = add nuw nsw i64 %i, 1 + %tmp1 = getelementptr inbounds i8*, i8** %A, i64 %i.next.0 + store i8* null, i8** %tmp1, align 8 + %i.next.1 = add nsw i64 %i, 2 + %tmp2 = getelementptr inbounds i8*, i8** %A, i64 %i.next.1 + store i8* null, i8** %tmp2, align 8 + %i.next.2 = add nsw i64 %i, 3 + %tmp3 = getelementptr inbounds i8*, i8** %A, i64 %i.next.2 + store i8* null, i8** %tmp3, align 8 + %i.next.3 = add nsw i64 %i, 4 + %cond = icmp slt i64 %i.next.3, %N + br i1 %cond, label %for.body, label %for.end + +for.end: + ret void +}