[PowerPC] Do not emit HW loop if the body contains calls to lrint/lround

These two intrinsics are lowered to calls so should prevent the formation of
CTR loops. In a subsequent patch, we will handle all currently known intrinsics
and prevent the formation of HW loops if any unknown intrinsics are encountered.

Differential revision: https://reviews.llvm.org/D68841

(cherry picked from commit 97e36260709c541044f30092b420238511e13e5b)

2 files changed, 79 insertions, 0 deletions

diff --git a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
index ff3dfbf..9e9997d 100644
--- a/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ b/llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -331,8 +331,12 @@ bool PPCTTIImpl::mightUseCTR(BasicBlock *BB,
           case Intrinsic::ceil:               Opcode = ISD::FCEIL;      break;
           case Intrinsic::trunc:              Opcode = ISD::FTRUNC;     break;
           case Intrinsic::rint:               Opcode = ISD::FRINT;      break;
+          case Intrinsic::lrint:              Opcode = ISD::LRINT;      break;
+          case Intrinsic::llrint:             Opcode = ISD::LLRINT;     break;
           case Intrinsic::nearbyint:          Opcode = ISD::FNEARBYINT; break;
           case Intrinsic::round:              Opcode = ISD::FROUND;     break;
+          case Intrinsic::lround:             Opcode = ISD::LROUND;     break;
+          case Intrinsic::llround:            Opcode = ISD::LLROUND;    break;
           case Intrinsic::minnum:             Opcode = ISD::FMINNUM;    break;
           case Intrinsic::maxnum:             Opcode = ISD::FMAXNUM;    break;
           case Intrinsic::umul_with_overflow: Opcode = ISD::UMULO;      break;
diff --git a/llvm/test/CodeGen/PowerPC/pr43527.ll b/llvm/test/CodeGen/PowerPC/pr43527.ll
new file mode 100644
index 0000000..7c3e438
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/pr43527.ll
@@ -0,0 +1,75 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -ppc-asm-full-reg-names -verify-machineinstrs \
+; RUN:   -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 < %s | FileCheck %s
+; We don't want to produce a CTR loop due to the call to lrint in the body.
+define dso_local void @test(i64 %arg, i64 %arg1) {
+; CHECK-LABEL: test:
+; CHECK:       # %bb.0: # %bb
+; CHECK-NEXT:    bc 4, 4*cr5+lt, .LBB0_5
+; CHECK-NEXT:  # %bb.1: # %bb3
+; CHECK-NEXT:    bc 12, 4*cr5+lt, .LBB0_6
+; CHECK-NEXT:  # %bb.2: # %bb4
+; CHECK-NEXT:    mflr r0
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
+; CHECK-NEXT:    .cfi_offset lr, 16
+; CHECK-NEXT:    .cfi_offset r29, -24
+; CHECK-NEXT:    .cfi_offset r30, -16
+; CHECK-NEXT:    std r29, -24(r1) # 8-byte Folded Spill
+; CHECK-NEXT:    std r30, -16(r1) # 8-byte Folded Spill
+; CHECK-NEXT:    std r0, 16(r1)
+; CHECK-NEXT:    stdu r1, -64(r1)
+; CHECK-NEXT:    sub r30, r4, r3
+; CHECK-NEXT:    li r29, 0
+; CHECK-NEXT:    .p2align 5
+; CHECK-NEXT:  .LBB0_3: # %bb5
+; CHECK-NEXT:    #
+; CHECK-NEXT:    lfsx f1, 0, r29
+; CHECK-NEXT:    bl lrint
+; CHECK-NEXT:    nop
+; CHECK-NEXT:    addi r30, r30, -1
+; CHECK-NEXT:    addi r29, r29, 4
+; CHECK-NEXT:    cmpldi r30, 0
+; CHECK-NEXT:    bne cr0, .LBB0_3
+; CHECK-NEXT:  # %bb.4: # %bb15
+; CHECK-NEXT:    stb r3, 0(r3)
+; CHECK-NEXT:    addi r1, r1, 64
+; CHECK-NEXT:    ld r0, 16(r1)
+; CHECK-NEXT:    mtlr r0
+; CHECK-NEXT:    ld r30, -16(r1) # 8-byte Folded Reload
+; CHECK-NEXT:    ld r29, -24(r1) # 8-byte Folded Reload
+; CHECK-NEXT:    blr
+; CHECK-NEXT:  .LBB0_5: # %bb2
+; CHECK-NEXT:  .LBB0_6: # %bb14
+bb:
+  br i1 undef, label %bb3, label %bb2
+
+bb2:                                              ; preds = %bb
+  unreachable
+
+bb3:                                              ; preds = %bb
+  %tmp = sub i64 %arg1, %arg
+  br i1 undef, label %bb4, label %bb14
+
+bb4:                                              ; preds = %bb3
+  br label %bb5
+
+bb5:                                              ; preds = %bb5, %bb4
+  %tmp6 = phi i64 [ %tmp12, %bb5 ], [ 0, %bb4 ]
+  %tmp7 = getelementptr inbounds float, float* null, i64 %tmp6
+  %tmp8 = load float, float* %tmp7, align 4
+  %tmp9 = fpext float %tmp8 to double
+  %tmp10 = tail call i64 @llvm.lrint.i64.f64(double %tmp9) #2
+  %tmp11 = trunc i64 %tmp10 to i8
+  store i8 %tmp11, i8* undef, align 1
+  %tmp12 = add nuw i64 %tmp6, 1
+  %tmp13 = icmp eq i64 %tmp12, %tmp
+  br i1 %tmp13, label %bb15, label %bb5
+
+bb14:                                             ; preds = %bb3
+  unreachable
+
+bb15:                                             ; preds = %bb5
+  ret void
+}
+
+declare i64 @llvm.lrint.i64.f64(double)