From 0f8f177682ddd91e7fe84595170d8e4986516e3b Mon Sep 17 00:00:00 2001 From: Hongbin Zheng Date: Thu, 27 Apr 2017 06:42:14 +0000 Subject: [PATCH] [Polly] Do not introduce address space cast Do not introduce address space cast in IslNodeBuilder::preloadUnconditionally. Differential Revision: https://reviews.llvm.org/D32581 llvm-svn: 301519 --- polly/lib/CodeGen/IslNodeBuilder.cpp | 3 +- .../Isl/CodeGen/invariant_load_address_space.ll | 40 ++++++++++++++++++++++ 2 files changed, 42 insertions(+), 1 deletion(-) create mode 100644 polly/test/Isl/CodeGen/invariant_load_address_space.ll diff --git a/polly/lib/CodeGen/IslNodeBuilder.cpp b/polly/lib/CodeGen/IslNodeBuilder.cpp index d8a13d8..14fea3d 100644 --- a/polly/lib/CodeGen/IslNodeBuilder.cpp +++ b/polly/lib/CodeGen/IslNodeBuilder.cpp @@ -1028,7 +1028,8 @@ Value *IslNodeBuilder::preloadUnconditionally(isl_set *AccessRange, auto *Ptr = AddressValue; auto Name = Ptr->getName(); - Ptr = Builder.CreatePointerCast(Ptr, Ty->getPointerTo(), Name + ".cast"); + auto AS = Ptr->getType()->getPointerAddressSpace(); + Ptr = Builder.CreatePointerCast(Ptr, Ty->getPointerTo(AS), Name + ".cast"); PreloadVal = Builder.CreateLoad(Ptr, Name + ".load"); if (LoadInst *PreloadInst = dyn_cast(PreloadVal)) PreloadInst->setAlignment(dyn_cast(AccInst)->getAlignment()); diff --git a/polly/test/Isl/CodeGen/invariant_load_address_space.ll b/polly/test/Isl/CodeGen/invariant_load_address_space.ll new file mode 100644 index 0000000..5ed73dc --- /dev/null +++ b/polly/test/Isl/CodeGen/invariant_load_address_space.ll @@ -0,0 +1,40 @@ +; RUN: opt %loadPolly -polly-codegen -polly-invariant-load-hoisting=true -S < %s | FileCheck %s +; +; CHECK-LABEL: polly.preload.begin: +; CHECK-NEXT: %polly.access.B = getelementptr i32, i32 addrspace(1)* %B, i64 0 +; CHECK-NOT: addrspacecast +; CHECK-NEXT: %polly.access.B.load = load i32, i32 addrspace(1)* %polly.access.B +; +; CHECK-LABEL: polly.stmt.bb2: +; CHECK-NEXT: %scevgep = getelementptr i32, i32* %A, i64 %polly.indvar +; CHECK-NEXT: store i32 %polly.access.B.load, i32* %scevgep, align 4 +; +; void f(int *restrict A, int *restrict B) { +; for (int i = 0; i < 1024; i++) +; A[i] = *B; +; } +; +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" + +define void @f(i32* noalias %A, i32 addrspace(1)* noalias %B) { +bb: + br label %bb1 + +bb1: ; preds = %bb4, %bb + %indvars.iv = phi i64 [ %indvars.iv.next, %bb4 ], [ 0, %bb ] + %exitcond = icmp ne i64 %indvars.iv, 1024 + br i1 %exitcond, label %bb2, label %bb5 + +bb2: ; preds = %bb1 + %tmp = load i32, i32 addrspace(1)* %B, align 4 + %tmp3 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv + store i32 %tmp, i32* %tmp3, align 4 + br label %bb4 + +bb4: ; preds = %bb2 + %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1 + br label %bb1 + +bb5: ; preds = %bb1 + ret void +} -- 2.7.4