#include "llvm/IR/Module.h"
#include "llvm/Pass.h"
#include "llvm/Support/Debug.h"
+#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/LoopVersioning.h"
#include <forward_list>
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
+ AU.addRequiredID(LoopSimplifyID);
AU.addRequired<LoopInfoWrapperPass>();
AU.addPreserved<LoopInfoWrapperPass>();
AU.addRequired<LoopAccessAnalysis>();
INITIALIZE_PASS_DEPENDENCY(LoopAccessAnalysis)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(LoopSimplify)
INITIALIZE_PASS_END(LoopLoadElimination, LLE_OPTION, LLE_name, false, false)
namespace llvm {
--- /dev/null
+; RUN: opt -loop-load-elim -S < %s | FileCheck %s
+
+; Make sure we create a preheader if we dont' have one.
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+define void @f(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i64 %N, i1 %C) {
+entry:
+ br i1 %C, label %for.body, label %for.end
+
+; CHECK: for.body.preheader:
+; CHECK-NEXT: %load_initial = load i32, i32* %A
+; CHECK-NEXT: br label %for.body
+
+; CHECK: for.body:
+for.body:
+; CHECK-NEXT: %store_forwarded = phi i32 [ %load_initial, %for.body.preheader ], [ %add, %for.body ]
+ %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+ %arrayidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
+ %load = load i32, i32* %arrayidx, align 4
+ %arrayidx2 = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
+ %load_1 = load i32, i32* %arrayidx2, align 4
+; CHECK: %add = add i32 %load_1, %store_forwarded
+ %add = add i32 %load_1, %load
+ %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+ %arrayidx_next = getelementptr inbounds i32, i32* %A, i64 %indvars.iv.next
+ store i32 %add, i32* %arrayidx_next, align 4
+ %exitcond = icmp eq i64 %indvars.iv.next, %N
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end:
+ ret void
+}