[PowerPC] Do not produce invalid CTR loop with an FRem

An FRem instruction inside a loop should prevent the loop from being converted
into a CTR loop since this is not an operation that is legal on any PPC
subtarget. This will always be a call to a library function which means the
loop will be invalid if this instruction is in the body.

Fixes PR36292.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@325739 91177308-0d34-0410-b5e6-96231b3b80d8

Author: nemanjai

lib/Target/PowerPC/PPCCTRLoops.cpp

@@ -455,13 +455,16 @@ bool PPCCTRLoops::mightUseCTR(BasicBlock *BB) {
         return true;
     }
 
+    // FREM is always a call.
+    if (J->getOpcode() == Instruction::FRem)
+      return true;
+
     if (STI->useSoftFloat()) {
       switch(J->getOpcode()) {
       case Instruction::FAdd:
       case Instruction::FSub:
       case Instruction::FMul:
       case Instruction::FDiv:
-      case Instruction::FRem:
       case Instruction::FPTrunc:
       case Instruction::FPExt:
       case Instruction::FPToUI:

test/CodeGen/PowerPC/pr36292.ll

@@ -0,0 +1,46 @@
+; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-unknown < %s  | \
+; RUN:   FileCheck %s --implicit-check-not=mtctr --implicit-check-not=bdnz
+$test = comdat any
+
+; No CTR loop due to frem (since it is always a call).
+define void @test() #0 comdat {
+; CHECK-LABEL: test:
+; CHECK:    ld 29, 0(3)
+; CHECK:    ld 30, 40(1)
+; CHECK:    xxlxor 31, 31, 31
+; CHECK:    cmpld 30, 29
+; CHECK-NEXT:    bge- 0, .LBB0_2
+; CHECK-NEXT:    .p2align 5
+; CHECK-NEXT:  .LBB0_1: # %bounds.ok
+; CHECK:    fmr 1, 31
+; CHECK-NEXT:    lfsx 2, 0, 3
+; CHECK-NEXT:    bl fmodf
+; CHECK-NEXT:    nop
+; CHECK-NEXT:    addi 30, 30, 1
+; CHECK-NEXT:    stfsx 1, 0, 3
+; CHECK-NEXT:    cmpld 30, 29
+; CHECK-NEXT:    blt+ 0, .LBB0_1
+; CHECK-NEXT:  .LBB0_2: # %bounds.fail
+; CHECK-NEXT:    std 30, 40(1)
+  %pos = alloca i64, align 8
+  br label %forcond
+
+forcond:                                          ; preds = %bounds.ok, %0
+  %1 = load i64, i64* %pos
+  %.len1 = load i64, i64* undef
+  %bounds.cmp = icmp ult i64 %1, %.len1
+  br i1 %bounds.cmp, label %bounds.ok, label %bounds.fail
+
+bounds.ok:                                        ; preds = %forcond
+  %2 = load float, float* undef
+  %3 = frem float 0.000000e+00, %2
+  store float %3, float* undef
+  %4 = load i64, i64* %pos
+  %5 = add i64 %4, 1
+  store i64 %5, i64* %pos
+  br label %forcond
+
+bounds.fail:                                      ; preds = %forcond
+  unreachable
+}
+