[PATCH] D40492: Handle Top-Level-Regions in polly::isHoistableLoad

Lukas Böhm via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon Nov 27 07:13:51 PST 2017


lksbhm updated this revision to Diff 124375.
lksbhm added a comment.

Remove attribute from memcpy decl and add newline at end of file


Repository:
  rL LLVM

https://reviews.llvm.org/D40492

Files:
  lib/Support/ScopHelper.cpp
  test/ScopDetect/tlr_is_hoistable_load.ll


Index: test/ScopDetect/tlr_is_hoistable_load.ll
===================================================================
--- /dev/null
+++ test/ScopDetect/tlr_is_hoistable_load.ll
@@ -0,0 +1,55 @@
+; RUN: opt %loadPolly -analyze -polly-scops  -polly-process-unprofitable \
+; RUN:     -polly-invariant-load-hoisting -polly-scops                   \
+; RUN:     -polly-detect-full-functions < %s | FileCheck %s
+;
+;    void test() {
+;      int A[] = {1, 2, 3, 4, 5};
+;      int len = (sizeof A) / sizeof(int);
+;      for (int i = 0; i < len; ++i) {
+;        A[i] = A[i] * 2;
+;      }
+;    }
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+
+ at test.A = private unnamed_addr constant [5 x i32] [i32 1, i32 2, i32 3, i32 4, i32 5], align 16
+
+define void @test() {
+entry:
+  %A = alloca [5 x i32], align 16
+  %len = alloca i32, align 4
+  %i = alloca i32, align 4
+  %0 = bitcast [5 x i32]* %A to i8*
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast ([5 x i32]* @test.A to i8*), i64 20, i32 16, i1 false)
+  store i32 5, i32* %len, align 4
+  store i32 0, i32* %i, align 4
+  br label %for.cond
+
+for.cond:                                         ; preds = %for.inc, %entry
+  %1 = load i32, i32* %i, align 4
+  %2 = load i32, i32* %len, align 4
+  %cmp = icmp slt i32 %1, %2
+  br i1 %cmp, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.cond
+  %3 = load i32, i32* %i, align 4
+  %idxprom = sext i32 %3 to i64
+  %arrayidx = getelementptr inbounds [5 x i32], [5 x i32]* %A, i64 0, i64 %idxprom
+  %4 = load i32, i32* %arrayidx, align 4
+  %mul = mul nsw i32 %4, 2
+  %5 = load i32, i32* %i, align 4
+  %idxprom1 = sext i32 %5 to i64
+  %arrayidx2 = getelementptr inbounds [5 x i32], [5 x i32]* %A, i64 0, i64 %idxprom1
+  store i32 %mul, i32* %arrayidx2, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body
+  %6 = load i32, i32* %i, align 4
+  %inc = add nsw i32 %6, 1
+  store i32 %inc, i32* %i, align 4
+  br label %for.cond
+
+for.end:                                          ; preds = %for.cond
+  ret void
+}
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1)
Index: lib/Support/ScopHelper.cpp
===================================================================
--- lib/Support/ScopHelper.cpp
+++ lib/Support/ScopHelper.cpp
@@ -473,9 +473,15 @@
       return false;
 
     bool DominatesAllPredecessors = true;
-    for (auto Pred : predecessors(R.getExit()))
-      if (R.contains(Pred) && !DT.dominates(&BB, Pred))
-        DominatesAllPredecessors = false;
+    if (R.isTopLevelRegion()) {
+      for (BasicBlock &I : *R.getEntry()->getParent())
+        if (isa<ReturnInst>(I.getTerminator()) && !DT.dominates(&BB, &I))
+          DominatesAllPredecessors = false;
+    } else {
+      for (auto Pred : predecessors(R.getExit()))
+        if (R.contains(Pred) && !DT.dominates(&BB, Pred))
+          DominatesAllPredecessors = false;
+    }
 
     if (!DominatesAllPredecessors)
       continue;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D40492.124375.patch
Type: text/x-patch
Size: 3092 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20171127/e6fe1b15/attachment.bin>


More information about the llvm-commits mailing list