[LICM] Hoisting of widenable conditions out of loops

[reames]

Summary

The change itself is straight forward and obvious, but ... there's an existing test checking for exactly the opposite. I can't identify a reason *why* hoisting of a WC is illegal or undesirable, anyone else see one?

[apilipenko]

Yeah, this limitation seems arbitrary and overly conservative.

llvm/include/llvm/IR/Intrinsics.td

def int_experimental_deoptimize : Intrinsic<[llvm_any_ty], [llvm_vararg_ty],
                                             [Throws]>;
 
 // Support for speculative runtime guards
 def int_experimental_guard : Intrinsic<[], [llvm_i1_ty, llvm_vararg_ty],
                                        [Throws]>;
 
 // Supports widenable conditions for guards represented as explicit branches.
 def int_experimental_widenable_condition : Intrinsic<[llvm_i1_ty], [],
-                                           [IntrInaccessibleMemOnly, IntrWillReturn]>;
+        [IntrInaccessibleMemOnly, IntrWillReturn, IntrSpeculatable]>;
 
 // NOP: calls/invokes to this intrinsic are removed by codegen
 def int_donothing : Intrinsic<[], [], [IntrNoMem, IntrWillReturn]>;
 
 // This instruction has no actual effect, though it is treated by the optimizer
 // has having opaque side effects. This may be inserted into loops to ensure
 // that they are not removed even if they turn out to be empty, for languages
 // which specify that infinite loops must be preserved.

llvm/lib/Transforms/Scalar/LICM.cpp

if (LoadInst *LI = dyn_cast<LoadInst>(&I)) {
     if (CI->mayThrow())
       return false;
 
     using namespace PatternMatch;
     if (match(CI, m_Intrinsic<Intrinsic::assume>()))
       // Assumes don't actually alias anything or throw
       return true;
 
+    if (match(CI, m_Intrinsic<Intrinsic::experimental_widenable_condition>()))
+      // Widenable conditions don't actually alias anything or throw
+      return true;
+
     // Handle simple cases by querying alias analysis.
     FunctionModRefBehavior Behavior = AA->getModRefBehavior(CI);
     if (Behavior == FMRB_DoesNotAccessMemory)
       return true;
     if (AliasAnalysis::onlyReadsMemory(Behavior)) {
       // A readonly argmemonly function only reads from memory pointed to by
       // it's arguments with arbitrary offsets.  If we can prove there are no
       // writes to this memory in the loop, we can hoist or sink.

llvm/test/Transforms/LICM/explicit_guards.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -S -make-guards-explicit -basicaa -licm < %s        | FileCheck %s
 ; RUN: opt -S -aa-pipeline=basic-aa -passes='require<opt-remark-emit>,make-guards-explicit,loop(licm)' < %s | FileCheck %s
 
-; Test interaction between explicit guards and LICM: make sure that we do not
-; hoist explicit conditions while we can hoist invariant loads in presence of
-; explicit guards.
-
 declare void @llvm.experimental.guard(i1,...)
+declare void @maythrow()
 
 ; Make sure that we do not hoist widenable_cond out of loop.
-define void @do_not_hoist_widenable_cond(i1 %cond, i32 %N, i32 %M) {
-; CHECK-LABEL: @do_not_hoist_widenable_cond(
+define void @hoist_widenable_cond(i1 %cond, i32 %N, i32 %M) {
+; CHECK-LABEL: @hoist_widenable_cond(
 ; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[GUARDED:%.*]] ]
 ; CHECK-NEXT:    [[GUARD_COND:%.*]] = icmp slt i32 [[IV]], [[N:%.*]]
+; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[GUARD_COND]], [[WIDENABLE_COND]]
+; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[GUARDED]], label [[DEOPT:%.*]], !prof !0
+; CHECK:       deopt:
+; CHECK-NEXT:    call void (...) @llvm.experimental.deoptimize.isVoid() [ "deopt"() ]
+; CHECK-NEXT:    ret void
+; CHECK:       guarded:
+; CHECK-NEXT:    [[LOOP_COND:%.*]] = icmp slt i32 [[IV]], [[M:%.*]]
+; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
+; CHECK-NEXT:    br i1 [[LOOP_COND]], label [[LOOP]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
+  %guard_cond = icmp slt i32 %iv, %N
+  call void(i1, ...) @llvm.experimental.guard(i1 %guard_cond) [ "deopt"() ]
+  %loop_cond = icmp slt i32 %iv, %M
+  %iv.next = add i32 %iv, 1
+  br i1 %loop_cond, label %loop, label %exit
+
+exit:
+  ret void
+}
+
+define void @hoist_widenable_cond_speculate(i1 %cond, i32 %N, i32 %M) {
+; CHECK-LABEL: @hoist_widenable_cond_speculate(
+; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
+; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK:       loop:
+; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[GUARDED:%.*]] ]
+; CHECK-NEXT:    [[GUARD_COND:%.*]] = icmp slt i32 [[IV]], [[N:%.*]]
+; CHECK-NEXT:    call void @maythrow()
 ; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[GUARD_COND]], [[WIDENABLE_COND]]
 ; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[GUARDED]], label [[DEOPT:%.*]], !prof !0
 ; CHECK:       deopt:
 ; CHECK-NEXT:    call void (...) @llvm.experimental.deoptimize.isVoid() [ "deopt"() ]
 ; CHECK-NEXT:    ret void
 ; CHECK:       guarded:
 ; CHECK-NEXT:    [[LOOP_COND:%.*]] = icmp slt i32 [[IV]], [[M:%.*]]
 ; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
 ; CHECK-NEXT:    br i1 [[LOOP_COND]], label [[LOOP]], label [[EXIT:%.*]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    ret void
 ;
 entry:
   br label %loop
 
 loop:
   %iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
   %guard_cond = icmp slt i32 %iv, %N
+  call void @maythrow()
   call void(i1, ...) @llvm.experimental.guard(i1 %guard_cond) [ "deopt"() ]
   %loop_cond = icmp slt i32 %iv, %M
   %iv.next = add i32 %iv, 1
   br i1 %loop_cond, label %loop, label %exit
 
 exit:
   ret void
 }
 
+
 define void @hoist_invariant_load(i1 %cond, i32* %np, i32 %M) {
 ; CHECK-LABEL: @hoist_invariant_load(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[N:%.*]] = load i32, i32* [[NP:%.*]]
+; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[GUARDED:%.*]] ]
 ; CHECK-NEXT:    [[GUARD_COND:%.*]] = icmp slt i32 [[IV]], [[N]]
-; CHECK-NEXT:    [[WIDENABLE_COND:%.*]] = call i1 @llvm.experimental.widenable.condition()
 ; CHECK-NEXT:    [[EXIPLICIT_GUARD_COND:%.*]] = and i1 [[GUARD_COND]], [[WIDENABLE_COND]]
 ; CHECK-NEXT:    br i1 [[EXIPLICIT_GUARD_COND]], label [[GUARDED]], label [[DEOPT:%.*]], !prof !0
 ; CHECK:       deopt:
 ; CHECK-NEXT:    call void (...) @llvm.experimental.deoptimize.isVoid() [ "deopt"() ]
 ; CHECK-NEXT:    ret void
 ; CHECK:       guarded:
 ; CHECK-NEXT:    [[LOOP_COND:%.*]] = icmp slt i32 [[IV]], [[M:%.*]]
 ; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1