[llvm] 3de9e3e - [DSE] Precommit test case with loop carried dependence.
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Sat Sep 12 11:06:56 PDT 2020
Author: Florian Hahn
Date: 2020-09-12T18:51:08+01:00
New Revision: 3de9e3e493baed93e1aa0e99b04a0b11f370a939
URL: https://github.com/llvm/llvm-project/commit/3de9e3e493baed93e1aa0e99b04a0b11f370a939
DIFF: https://github.com/llvm/llvm-project/commit/3de9e3e493baed93e1aa0e99b04a0b11f370a939.diff
LOG: [DSE] Precommit test case with loop carried dependence.
Added:
llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-loop-carried-dependence.ll
Modified:
Removed:
################################################################################
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-loop-carried-dependence.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-loop-carried-dependence.ll
new file mode 100644
index 000000000000..76292374e1f9
--- /dev/null
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-loop-carried-dependence.ll
@@ -0,0 +1,140 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+
+; RUN: opt -dse -S %s | FileCheck %s
+
+target datalayout = "e-m:e-i64:64-n32:64-v256:256:256-v512:512:512"
+
+declare void @use(i32)
+
+; Test cases with a loop carried dependence in %loop.2, where %l.2 reads the
+; value stored by the previous iteration. Hence, the store in %loop.2 is not
+; dead at the end of the function or after the call to lifetime.end().
+
+define void @test.1() {
+; CHECK-LABEL: @test.1(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[A:%.*]] = alloca [100 x i32], align 4
+; CHECK-NEXT: br label [[LOOP_1:%.*]]
+; CHECK: loop.1:
+; CHECK-NEXT: [[IV_1:%.*]] = phi i64 [ 1, [[ENTRY:%.*]] ], [ [[IV_1_NEXT:%.*]], [[LOOP_1]] ]
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[A]], i64 0, i64 [[IV_1]]
+; CHECK-NEXT: store i32 0, i32* [[ARRAYIDX1]], align 4
+; CHECK-NEXT: [[IV_1_NEXT]] = add nsw i64 [[IV_1]], 1
+; CHECK-NEXT: [[C_1:%.*]] = icmp slt i64 [[IV_1_NEXT]], 100
+; CHECK-NEXT: br i1 [[C_1]], label [[LOOP_1]], label [[LOOP_2_PH:%.*]]
+; CHECK: loop.2.ph:
+; CHECK-NEXT: br label [[LOOP_2:%.*]]
+; CHECK: loop.2:
+; CHECK-NEXT: [[IV_2:%.*]] = phi i64 [ [[IV_2_NEXT:%.*]], [[LOOP_2]] ], [ 0, [[LOOP_2_PH]] ]
+; CHECK-NEXT: [[PTR_IV_2:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[A]], i64 0, i64 [[IV_2]]
+; CHECK-NEXT: [[L_0:%.*]] = load i32, i32* [[PTR_IV_2]], align 4
+; CHECK-NEXT: call void @use(i32 [[L_0]])
+; CHECK-NEXT: [[L_1:%.*]] = load i32, i32* [[PTR_IV_2]], align 4
+; CHECK-NEXT: call void @use(i32 [[L_1]])
+; CHECK-NEXT: [[IV_2_NEXT]] = add nsw i64 [[IV_2]], 1
+; CHECK-NEXT: [[C_2:%.*]] = icmp slt i64 [[IV_2_NEXT]], 100
+; CHECK-NEXT: br i1 [[C_2]], label [[LOOP_2]], label [[EXIT:%.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret void
+;
+entry:
+ %A = alloca [100 x i32], align 4
+ br label %loop.1
+
+loop.1:
+ %iv.1 = phi i64 [ 1, %entry ], [ %iv.1.next, %loop.1 ]
+ %arrayidx1 = getelementptr inbounds [100 x i32], [100 x i32]* %A, i64 0, i64 %iv.1
+ store i32 0, i32* %arrayidx1, align 4
+ %iv.1.next = add nsw i64 %iv.1, 1
+ %c.1 = icmp slt i64 %iv.1.next, 100
+ br i1 %c.1, label %loop.1, label %loop.2.ph
+
+loop.2.ph:
+ br label %loop.2
+
+loop.2:
+ %iv.2 = phi i64 [ %iv.2.next, %loop.2 ], [ 0, %loop.2.ph ]
+ %ptr.iv.2 = getelementptr inbounds [100 x i32], [100 x i32]* %A, i64 0, i64 %iv.2
+ %l.0 = load i32, i32* %ptr.iv.2, align 4
+ call void @use(i32 %l.0)
+ %add = add nsw i64 %iv.2, 1
+ %ptr.iv.2.add.1 = getelementptr inbounds [100 x i32], [100 x i32]* %A, i64 0, i64 %add
+ store i32 10, i32* %ptr.iv.2.add.1, align 4
+ %l.1 = load i32, i32* %ptr.iv.2, align 4
+ call void @use(i32 %l.1)
+ %iv.2.next = add nsw i64 %iv.2, 1
+ %c.2 = icmp slt i64 %iv.2.next, 100
+ br i1 %c.2, label %loop.2, label %exit
+
+exit:
+ ret void
+}
+
+define void @test.2() {
+; CHECK-LABEL: @test.2(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[A:%.*]] = alloca [100 x i32], align 4
+; CHECK-NEXT: [[A_CAST:%.*]] = bitcast [100 x i32]* [[A]] to i8*
+; CHECK-NEXT: br label [[LOOP_1:%.*]]
+; CHECK: loop.1:
+; CHECK-NEXT: [[IV_1:%.*]] = phi i64 [ 1, [[ENTRY:%.*]] ], [ [[IV_1_NEXT:%.*]], [[LOOP_1]] ]
+; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[A]], i64 0, i64 [[IV_1]]
+; CHECK-NEXT: store i32 0, i32* [[ARRAYIDX1]], align 4
+; CHECK-NEXT: [[IV_1_NEXT]] = add nsw i64 [[IV_1]], 1
+; CHECK-NEXT: [[C_1:%.*]] = icmp slt i64 [[IV_1_NEXT]], 100
+; CHECK-NEXT: br i1 [[C_1]], label [[LOOP_1]], label [[LOOP_2_PH:%.*]]
+; CHECK: loop.2.ph:
+; CHECK-NEXT: br label [[LOOP_2:%.*]]
+; CHECK: loop.2:
+; CHECK-NEXT: [[IV_2:%.*]] = phi i64 [ [[IV_2_NEXT:%.*]], [[LOOP_2]] ], [ 0, [[LOOP_2_PH]] ]
+; CHECK-NEXT: [[PTR_IV_2:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[A]], i64 0, i64 [[IV_2]]
+; CHECK-NEXT: [[L_0:%.*]] = load i32, i32* [[PTR_IV_2]], align 4
+; CHECK-NEXT: call void @use(i32 [[L_0]])
+; CHECK-NEXT: [[ADD:%.*]] = add nsw i64 [[IV_2]], 1
+; CHECK-NEXT: [[PTR_IV_2_ADD_1:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[A]], i64 0, i64 [[ADD]]
+; CHECK-NEXT: store i32 10, i32* [[PTR_IV_2_ADD_1]], align 4
+; CHECK-NEXT: [[L_1:%.*]] = load i32, i32* [[PTR_IV_2]], align 4
+; CHECK-NEXT: call void @use(i32 [[L_1]])
+; CHECK-NEXT: [[IV_2_NEXT]] = add nsw i64 [[IV_2]], 1
+; CHECK-NEXT: [[C_2:%.*]] = icmp slt i64 [[IV_2_NEXT]], 100
+; CHECK-NEXT: br i1 [[C_2]], label [[LOOP_2]], label [[EXIT:%.*]]
+; CHECK: exit:
+; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 400, i8* nonnull [[A_CAST]])
+; CHECK-NEXT: ret void
+;
+entry:
+ %A = alloca [100 x i32], align 4
+ %A.cast = bitcast [100 x i32]* %A to i8*
+ br label %loop.1
+
+loop.1:
+ %iv.1 = phi i64 [ 1, %entry ], [ %iv.1.next, %loop.1 ]
+ %arrayidx1 = getelementptr inbounds [100 x i32], [100 x i32]* %A, i64 0, i64 %iv.1
+ store i32 0, i32* %arrayidx1, align 4
+ %iv.1.next = add nsw i64 %iv.1, 1
+ %c.1 = icmp slt i64 %iv.1.next, 100
+ br i1 %c.1, label %loop.1, label %loop.2.ph
+
+loop.2.ph:
+ br label %loop.2
+
+loop.2:
+ %iv.2 = phi i64 [ %iv.2.next, %loop.2 ], [ 0, %loop.2.ph ]
+ %ptr.iv.2 = getelementptr inbounds [100 x i32], [100 x i32]* %A, i64 0, i64 %iv.2
+ %l.0 = load i32, i32* %ptr.iv.2, align 4
+ call void @use(i32 %l.0)
+ %add = add nsw i64 %iv.2, 1
+ %ptr.iv.2.add.1 = getelementptr inbounds [100 x i32], [100 x i32]* %A, i64 0, i64 %add
+ store i32 10, i32* %ptr.iv.2.add.1, align 4
+ %l.1 = load i32, i32* %ptr.iv.2, align 4
+ call void @use(i32 %l.1)
+ %iv.2.next = add nsw i64 %iv.2, 1
+ %c.2 = icmp slt i64 %iv.2.next, 100
+ br i1 %c.2, label %loop.2, label %exit
+
+exit:
+ call void @llvm.lifetime.end.p0i8(i64 400, i8* nonnull %A.cast) #5
+ ret void
+}
+
+declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture)
More information about the llvm-commits
mailing list