[PATCH] D81924: [PowerPC] Allow constrained FP intrinsics in mightUseCTR

[Qiu Chaofan via Phabricator via llvm-commits]

qiucf created this revision.
qiucf added reviewers: ZhangKang, steven.zhang, nemanjai, jsji, hfinkel, PowerPC.
Herald added subscribers: llvm-commits, shchenz, kbarton, hiraditya.
Herald added a project: LLVM.

We may meet //Invalid CTR loop// crash when there's constrained ops inside. This patch adds constrained FP intrinsics to the list so that CTR loop verification doesn't complain about it.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D81924

Files:
  llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
  llvm/test/CodeGen/PowerPC/ctrloop-constrained-fp.ll


Index: llvm/test/CodeGen/PowerPC/ctrloop-constrained-fp.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/PowerPC/ctrloop-constrained-fp.ll
@@ -0,0 +1,21 @@
+; RUN: llc -mtriple powerpc64le < %s
+
+define void @test(double* %cast) {
+root:
+  br label %for.body
+
+exit:
+  ret void
+
+for.body:
+  %i = phi i64 [ 0, %root ], [ %next, %for.body ]
+  %idx = getelementptr inbounds double, double* %cast, i64 %i
+  %val = load double, double* %idx
+  %cos = tail call nnan ninf nsz arcp double @llvm.experimental.constrained.cos.f64(double %val, metadata !"round.dynamic", metadata !"fpexcept.strict")
+  store double %cos, double* %idx, align 8
+  %next = add nuw nsw i64 %i, 1
+  %cond = icmp eq i64 %next, 255
+  br i1 %cond, label %exit, label %for.body
+}
+
+declare double @llvm.experimental.constrained.cos.f64(double, metadata, metadata)
Index: llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
+++ llvm/lib/Target/PowerPC/PPCTargetTransformInfo.cpp
@@ -317,6 +317,15 @@
           case Intrinsic::pow:
           case Intrinsic::sin:
           case Intrinsic::cos:
+          case Intrinsic::experimental_constrained_powi:
+          case Intrinsic::experimental_constrained_log:
+          case Intrinsic::experimental_constrained_log2:
+          case Intrinsic::experimental_constrained_log10:
+          case Intrinsic::experimental_constrained_exp:
+          case Intrinsic::experimental_constrained_exp2:
+          case Intrinsic::experimental_constrained_pow:
+          case Intrinsic::experimental_constrained_sin:
+          case Intrinsic::experimental_constrained_cos:
             return true;
           case Intrinsic::copysign:
             if (CI->getArgOperand(0)->getType()->getScalarType()->
@@ -338,6 +347,48 @@
           case Intrinsic::llround:            Opcode = ISD::LLROUND;    break;
           case Intrinsic::minnum:             Opcode = ISD::FMINNUM;    break;
           case Intrinsic::maxnum:             Opcode = ISD::FMAXNUM;    break;
+          case Intrinsic::experimental_constrained_fma:
+            Opcode = ISD::STRICT_FMA;
+            break;
+          case Intrinsic::experimental_constrained_sqrt:
+            Opcode = ISD::STRICT_FSQRT;
+            break;
+          case Intrinsic::experimental_constrained_floor:
+            Opcode = ISD::STRICT_FFLOOR;
+            break;
+          case Intrinsic::experimental_constrained_ceil:
+            Opcode = ISD::STRICT_FCEIL;
+            break;
+          case Intrinsic::experimental_constrained_trunc:
+            Opcode = ISD::STRICT_FTRUNC;
+            break;
+          case Intrinsic::experimental_constrained_rint:
+            Opcode = ISD::STRICT_FRINT;
+            break;
+          case Intrinsic::experimental_constrained_lrint:
+            Opcode = ISD::STRICT_LRINT;
+            break;
+          case Intrinsic::experimental_constrained_llrint:
+            Opcode = ISD::STRICT_LLRINT;
+            break;
+          case Intrinsic::experimental_constrained_nearbyint:
+            Opcode = ISD::STRICT_FNEARBYINT;
+            break;
+          case Intrinsic::experimental_constrained_round:
+            Opcode = ISD::STRICT_FROUND;
+            break;
+          case Intrinsic::experimental_constrained_lround:
+            Opcode = ISD::STRICT_LROUND;
+            break;
+          case Intrinsic::experimental_constrained_llround:
+            Opcode = ISD::STRICT_LLROUND;
+            break;
+          case Intrinsic::experimental_constrained_minnum:
+            Opcode = ISD::STRICT_FMINNUM;
+            break;
+          case Intrinsic::experimental_constrained_maxnum:
+            Opcode = ISD::STRICT_FMAXNUM;
+            break;
           case Intrinsic::umul_with_overflow: Opcode = ISD::UMULO;      break;
           case Intrinsic::smul_with_overflow: Opcode = ISD::SMULO;      break;
           }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D81924.271034.patch
Type: text/x-patch
Size: 4036 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200616/4a2db336/attachment.bin>