Index: llvm/test/Transforms/SimplifyCFG/branch-fold-multiple.ll =================================================================== --- /dev/null +++ llvm/test/Transforms/SimplifyCFG/branch-fold-multiple.ll @@ -0,0 +1,151 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py +; RUN: opt %s -S -o - -simplifycfg | FileCheck %s + +%struct.S = type { [4 x i32] } + +; Check the second, third, and fourth basic blocks are folded into +; the first basic block since each has one bonus intruction, which +; does not exceed the default bouns instruction threshold 1. + +define zeroext i1 @test1(i32 %0, i32 %1, i32 %2, i32 %3) unnamed_addr align 2 { +; CHECK-LABEL: @test1( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[MUL0:%.*]] = mul i32 [[TMP0:%.*]], [[TMP0]] +; CHECK-NEXT: [[CMP2:%.*]] = icmp sgt i32 [[MUL0]], 0 +; CHECK-NEXT: [[MUL1:%.*]] = mul i32 [[TMP1:%.*]], [[TMP1]] +; CHECK-NEXT: [[CMP2_1:%.*]] = icmp sgt i32 [[MUL1]], 0 +; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[CMP2]], i1 true, i1 [[CMP2_1]] +; CHECK-NEXT: [[MUL2:%.*]] = mul i32 [[TMP2:%.*]], [[TMP2]] +; CHECK-NEXT: [[CMP2_2:%.*]] = icmp sgt i32 [[MUL2]], 0 +; CHECK-NEXT: [[OR_COND1:%.*]] = select i1 [[OR_COND]], i1 true, i1 [[CMP2_2]] +; CHECK-NEXT: [[MUL3:%.*]] = mul i32 [[TMP3:%.*]], [[TMP3]] +; CHECK-NEXT: [[CMP2_3:%.*]] = icmp sgt i32 [[MUL3]], 0 +; CHECK-NEXT: [[OR_COND2:%.*]] = select i1 [[OR_COND1]], i1 true, i1 [[CMP2_3]] +; CHECK-NEXT: [[SPEC_SELECT:%.*]] = select i1 [[OR_COND2]], i1 false, i1 true +; CHECK-NEXT: ret i1 [[SPEC_SELECT]] +; +entry: + %mul0 = mul i32 %0, %0 + %cmp2 = icmp sgt i32 %mul0, 0 + br i1 %cmp2, label %cleanup, label %for.cond + +for.cond: + %mul1 = mul i32 %1, %1 + %cmp2.1 = icmp sgt i32 %mul1, 0 + br i1 %cmp2.1, label %cleanup, label %for.cond.1 + +for.cond.1: + %mul2 = mul i32 %2, %2 + %cmp2.2 = icmp sgt i32 %mul2, 0 + br i1 %cmp2.2, label %cleanup, label %for.cond.2 + +for.cond.2: + %mul3 = mul i32 %3, %3 + %cmp2.3 = icmp sgt i32 %mul3, 0 + br i1 %cmp2.3, label %cleanup, label %for.cond.3 + +for.cond.3: + br label %cleanup + +cleanup: + %cmp = phi i1 [ false, %entry ], [ false, %for.cond ], [ false, %for.cond.1 ], [ false, %for.cond.2 ], [ true, %for.cond.3 ] + ret i1 %cmp +} + +; Check the second, third, and forth basic blocks are folded into the first +; basi block since each has no bonus instruction. + +define zeroext i1 @test2(i32 %0, i32 %1, i32 %2, i32 %3) unnamed_addr align 2 { +; CHECK-LABEL: @test2( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[CMP2:%.*]] = icmp sgt i32 [[TMP0:%.*]], 0 +; CHECK-NEXT: [[CMP2_1:%.*]] = icmp sgt i32 [[TMP1:%.*]], 0 +; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[CMP2]], i1 true, i1 [[CMP2_1]] +; CHECK-NEXT: [[CMP2_2:%.*]] = icmp sgt i32 [[TMP2:%.*]], 0 +; CHECK-NEXT: [[OR_COND1:%.*]] = select i1 [[OR_COND]], i1 true, i1 [[CMP2_2]] +; CHECK-NEXT: [[CMP2_3:%.*]] = icmp sgt i32 [[TMP3:%.*]], 0 +; CHECK-NEXT: [[OR_COND2:%.*]] = select i1 [[OR_COND1]], i1 true, i1 [[CMP2_3]] +; CHECK-NEXT: [[SPEC_SELECT:%.*]] = select i1 [[OR_COND2]], i1 false, i1 true +; CHECK-NEXT: ret i1 [[SPEC_SELECT]] +; +entry: + %cmp2 = icmp sgt i32 %0, 0 + br i1 %cmp2, label %cleanup, label %for.cond + +for.cond: + %cmp2.1 = icmp sgt i32 %1, 0 + br i1 %cmp2.1, label %cleanup, label %for.cond.1 + +for.cond.1: + %cmp2.2 = icmp sgt i32 %2, 0 + br i1 %cmp2.2, label %cleanup, label %for.cond.2 + +for.cond.2: + %cmp2.3 = icmp sgt i32 %3, 0 + br i1 %cmp2.3, label %cleanup, label %for.cond.3 + +for.cond.3: + br label %cleanup + +cleanup: + %cmp = phi i1 [ false, %entry ], [ false, %for.cond ], [ false, %for.cond.1 ], [ false, %for.cond.2 ], [ true, %for.cond.3 ] + ret i1 %cmp +} + +; Check the second basic block is not folded into the first basic block +; since it has three bonus instructions, which exceeds the default bonus +; instruction threshold 1. The third and fourth basic blocks are folded +; into the second basic block since they do not have bonus instruction. + +define zeroext i1 @test3(i32 %0, i32 %1, i32 %2, i32 %3) unnamed_addr align 2 { +; CHECK-LABEL: @test3( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[CMP2:%.*]] = icmp sgt i32 [[TMP0:%.*]], 0 +; CHECK-NEXT: br i1 [[CMP2]], label [[CLEANUP:%.*]], label [[FOR_COND:%.*]] +; CHECK: for.cond: +; CHECK-NEXT: [[MUL1:%.*]] = mul i32 [[TMP0]], [[TMP1:%.*]] +; CHECK-NEXT: [[MUL2:%.*]] = mul i32 [[MUL1]], [[TMP2:%.*]] +; CHECK-NEXT: [[MUL3:%.*]] = mul i32 [[MUL2]], [[TMP3:%.*]] +; CHECK-NEXT: [[MUL4:%.*]] = mul i32 [[MUL3]], [[TMP3]] +; CHECK-NEXT: [[MUL5:%.*]] = mul i32 [[MUL4]], [[TMP3]] +; CHECK-NEXT: [[MUL6:%.*]] = mul i32 [[MUL5]], [[TMP3]] +; CHECK-NEXT: [[CMP2_1:%.*]] = icmp sgt i32 [[MUL5]], 0 +; CHECK-NEXT: [[CMP2_2:%.*]] = icmp sgt i32 [[TMP2]], 0 +; CHECK-NEXT: [[OR_COND:%.*]] = select i1 [[CMP2_1]], i1 true, i1 [[CMP2_2]] +; CHECK-NEXT: [[CMP2_3:%.*]] = icmp sgt i32 [[TMP3]], 0 +; CHECK-NEXT: [[OR_COND1:%.*]] = select i1 [[OR_COND]], i1 true, i1 [[CMP2_3]] +; CHECK-NEXT: [[SPEC_SELECT:%.*]] = select i1 [[OR_COND1]], i1 false, i1 true +; CHECK-NEXT: br label [[CLEANUP]] +; CHECK: cleanup: +; CHECK-NEXT: [[CMP:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[SPEC_SELECT]], [[FOR_COND]] ] +; CHECK-NEXT: ret i1 [[CMP]] +; +entry: + %cmp2 = icmp sgt i32 %0, 0 + br i1 %cmp2, label %cleanup, label %for.cond + +for.cond: + %mul1 = mul i32 %0, %1 + %mul2 = mul i32 %mul1, %2 + %mul3 = mul i32 %mul2, %3 + %mul4 = mul i32 %mul3, %3 + %mul5 = mul i32 %mul4, %3 + %mul6 = mul i32 %mul5, %3 + %cmp2.1 = icmp sgt i32 %mul5, 0 + br i1 %cmp2.1, label %cleanup, label %for.cond.1 + +for.cond.1: + %cmp2.2 = icmp sgt i32 %2, 0 + br i1 %cmp2.2, label %cleanup, label %for.cond.2 + +for.cond.2: + %cmp2.3 = icmp sgt i32 %3, 0 + br i1 %cmp2.3, label %cleanup, label %for.cond.3 + +for.cond.3: + br label %cleanup + +cleanup: + %cmp = phi i1 [ false, %entry ], [ false, %for.cond ], [ false, %for.cond.1 ], [ false, %for.cond.2 ], [ true, %for.cond.3 ] + ret i1 %cmp +}