Merge 24c3980 into e4b29f7

Author: vtjnash

base/compiler/abstractinterpretation.jl

@@ -251,6 +251,7 @@ mutable struct InferenceState
     stmt_info::Vector{CallInfo}
 
     #= intermediate states for interprocedural abstract interpretation =#
+    tasks::Vector{WorkThunk}
     pclimitations::IdSet{InferenceState} # causes of precision restrictions (LimitedAccuracy) on currpc ssavalue
     limitations::IdSet{InferenceState} # causes of precision restrictions (LimitedAccuracy) on return
     cycle_backedges::Vector{Tuple{InferenceState, Int}} # call-graph backedges connecting from callee to caller
@@ -328,6 +329,7 @@ mutable struct InferenceState
         limitations = IdSet{InferenceState}()
         cycle_backedges = Vector{Tuple{InferenceState,Int}}()
         callstack = AbsIntState[]
+        tasks = WorkThunk[]
 
         valid_worlds = WorldRange(1, get_world_counter())
         bestguess = Bottom
@@ -351,7 +353,7 @@ mutable struct InferenceState
         this = new(
             mi, world, mod, sptypes, slottypes, src, cfg, method_info,
             currbb, currpc, ip, handler_info, ssavalue_uses, bb_vartables, ssavaluetypes, stmt_edges, stmt_info,
-            pclimitations, limitations, cycle_backedges, callstack, 0, 0, 0,
+            tasks, pclimitations, limitations, cycle_backedges, callstack, 0, 0, 0,
             result, unreachable, valid_worlds, bestguess, exc_bestguess, ipo_effects,
             restrict_abstract_call_sites, cache_mode, insert_coverage,
             interp)
@@ -800,6 +802,7 @@ mutable struct IRInterpretationState
     const ssa_refined::BitSet
     const lazyreachability::LazyCFGReachability
     valid_worlds::WorldRange
+    const tasks::Vector{WorkThunk}
     const edges::Vector{Any}
     callstack #::Vector{AbsIntState}
     frameid::Int
@@ -825,10 +828,11 @@ mutable struct IRInterpretationState
         ssa_refined = BitSet()
         lazyreachability = LazyCFGReachability(ir)
         valid_worlds = WorldRange(min_world, max_world == typemax(UInt) ? get_world_counter() : max_world)
+        tasks = WorkThunk[]
         edges = Any[]
         callstack = AbsIntState[]
         return new(method_info, ir, mi, world, curridx, argtypes_refined, ir.sptypes, tpdum,
-                ssa_refined, lazyreachability, valid_worlds, edges, callstack, 0, 0)
+                ssa_refined, lazyreachability, valid_worlds, tasks, edges, callstack, 0, 0)
     end
 end
 
@@ -870,6 +874,7 @@ function print_callstack(frame::AbsIntState)
         print(frame_instance(sv))
         is_cached(sv) || print("  [uncached]")
         sv.parentid == idx - 1 || print(" [parent=", sv.parentid, "]")
+        isempty(callers_in_cycle(sv)) || print(" [cycle=", sv.cycleid, "]")
         println()
         @assert sv.frameid == idx
     end
@@ -994,7 +999,10 @@ of the same cycle, only if it is part of a cycle with multiple frames.
 function callers_in_cycle(sv::InferenceState)
     callstack = sv.callstack::Vector{AbsIntState}
     cycletop = cycleid = sv.cycleid
-    while cycletop < length(callstack) && (callstack[cycletop + 1]::InferenceState).cycleid == cycleid
+    while cycletop < length(callstack)
+        frame = callstack[cycletop + 1]
+        frame isa InferenceState || break
+        frame.cycleid == cycleid || break
         cycletop += 1
     end
     return AbsIntCycle(callstack, cycletop == cycleid ? 0 : cycleid, cycletop)
@@ -1054,6 +1062,7 @@ function merge_effects!(::AbstractInterpreter, caller::InferenceState, effects::
         effects = Effects(effects; effect_free=ALWAYS_TRUE)
     end
     caller.ipo_effects = merge_effects(caller.ipo_effects, effects)
+    nothing
 end
 merge_effects!(::AbstractInterpreter, ::IRInterpretationState, ::Effects) = return
 
@@ -1116,3 +1125,90 @@ function get_max_methods_for_module(mod::Module)
     max_methods < 0 && return nothing
     return max_methods
 end
+
+"""
+    Future{T}
+
+Delayed return value for a value of type `T`, similar to RefValue{T}, but
+explicitly represents completed as a `Bool` rather than as `isdefined`.
+Set once with `f[] = v` and accessed with `f[]` afterwards.
+
+Can also be constructed with the `completed` flag value and a closure to
+produce `x`, as well as the additional arguments to avoid always capturing the
+same couple of values.
+"""
+struct Future{T}
+    later::Union{Nothing,RefValue{T}}
+    now::Union{Nothing,T}
+    Future{T}() where {T} = new{T}(RefValue{T}(), nothing)
+    Future{T}(x) where {T} = new{T}(nothing, x)
+    Future(x::T) where {T} = new{T}(nothing, x)
+end
+isready(f::Future) = f.later === nothing
+getindex(f::Future{T}) where {T} = (later = f.later; later === nothing ? f.now::T : later[])
+setindex!(f::Future, v) = something(f.later)[] = v
+convert(::Type{Future{T}}, x) where {T} = Future{T}(x) # support return type conversion
+convert(::Type{Future{T}}, x::Future) where {T} = x::Future{T}
+function Future{T}(f, immediate::Bool, interp::AbstractInterpreter, sv::AbsIntState) where {T}
+    if immediate
+        return Future{T}(f(interp, sv))
+    else
+        @assert applicable(f, interp, sv)
+        result = Future{T}()
+        push!(sv.tasks, function (interp, sv)
+            result[] = f(interp, sv)
+            return true
+        end)
+        return result
+    end
+end
+function Future{T}(f, prev::Future{S}, interp::AbstractInterpreter, sv::AbsIntState) where {T, S}
+    later = prev.later
+    if later === nothing
+        return Future{T}(f(prev[], interp, sv))
+    else
+        @assert Core._hasmethod(Tuple{Core.Typeof(f), S, typeof(interp), typeof(sv)})
+        result = Future{T}()
+        push!(sv.tasks, function (interp, sv)
+            result[] = f(later[], interp, sv) # capture just later, instead of all of prev
+            return true
+        end)
+        return result
+    end
+end
+
+
+"""
+    doworkloop(args...)
+
+Run a tasks inside the abstract interpreter, returning false if there are none.
+Tasks will be run in DFS post-order tree order, such that all child tasks will
+be run in the order scheduled, prior to running any subsequent tasks. This
+allows tasks to generate more child tasks, which will be run before anything else.
+Each task will be run repeatedly when returning `false`, until it returns `true`.
+"""
+function doworkloop(interp::AbstractInterpreter, sv::AbsIntState)
+    tasks = sv.tasks
+    prev = length(tasks)
+    prev == 0 && return false
+    task = pop!(tasks)
+    completed = task(interp, sv)
+    tasks = sv.tasks # allow dropping gc root over the previous call
+    completed isa Bool || throw(TypeError(:return, "", Bool, task)) # print the task on failure as part of the error message, instead of just "@ workloop:line"
+    completed || push!(tasks, task)
+    # efficient post-order visitor: items pushed are executed in reverse post order such
+    # that later items are executed before earlier ones, but are fully executed
+    # (including any dependencies scheduled by them) before going on to the next item
+    reverse!(tasks, #=start=#prev)
+    return true
+end
+
+
+#macro workthunk(name::Symbol, body)
+#    name = esc(name)
+#    body = esc(body)
+#    return replace_linenums!(
+#        :(function $name($(esc(interp)), $(esc(sv)))
+#              $body
+#          end), __source__)
+#end

base/compiler/inferencestate.jl

@@ -1432,6 +1432,7 @@ function process_node!(compact::IncrementalCompact, result_idx::Int, inst::Instr
     elseif isa(stmt, OldSSAValue)
         ssa_rename[idx] = ssa_rename[stmt.id]
     elseif isa(stmt, GotoNode) && cfg_transforms_enabled
+        stmt.label < 0 && (println(stmt); println(compact))
         label = bb_rename_succ[stmt.label]
         @assert label > 0
         ssa_rename[idx] = SSAValue(result_idx)

base/compiler/ssair/ir.jl

@@ -51,8 +51,11 @@ end
 
 function abstract_call(interp::AbstractInterpreter, arginfo::ArgInfo, irsv::IRInterpretationState)
     si = StmtInfo(true) # TODO better job here?
-    call = abstract_call(interp, arginfo, si, irsv)
-    irsv.ir.stmts[irsv.curridx][:info] = call.info
+    call = abstract_call(interp, arginfo, si, irsv)::Future
+    Future{Nothing}(call, interp, irsv) do call, interp, irsv
+        irsv.ir.stmts[irsv.curridx][:info] = call.info
+        nothing
+    end
     return call
 end
 
@@ -143,7 +146,19 @@ function reprocess_instruction!(interp::AbstractInterpreter, inst::Instruction,
         head = stmt.head
         if (head === :call || head === :foreigncall || head === :new || head === :splatnew ||
             head === :static_parameter || head === :isdefined || head === :boundscheck)
-            (; rt, effects) = abstract_eval_statement_expr(interp, stmt, nothing, irsv)
+            @assert isempty(irsv.tasks) # TODO: this whole function needs to be converted to a stackless design to be a valid AbsIntState, but this should work here for now
+            result = abstract_eval_statement_expr(interp, stmt, nothing, irsv)
+            reverse!(irsv.tasks)
+            while true
+                if length(irsv.callstack) > irsv.frameid
+                    typeinf(interp, irsv.callstack[irsv.frameid + 1])
+                elseif !doworkloop(interp, irsv)
+                    break
+                end
+            end
+            @assert length(irsv.callstack) == irsv.frameid && isempty(irsv.tasks)
+            result isa Future && (result = result[])
+            (; rt, effects) = result
             add_flag!(inst, flags_for_effects(effects))
         elseif head === :invoke
             rt, (nothrow, noub) = abstract_eval_invoke_inst(interp, inst, irsv)
@@ -293,7 +308,7 @@ function is_all_const_call(@nospecialize(stmt), interp::AbstractInterpreter, irs
     return true
 end
 
-function _ir_abstract_constant_propagation(interp::AbstractInterpreter, irsv::IRInterpretationState;
+function ir_abstract_constant_propagation(interp::AbstractInterpreter, irsv::IRInterpretationState;
         externally_refined::Union{Nothing,BitSet} = nothing)
     (; ir, tpdum, ssa_refined) = irsv
 
@@ -449,18 +464,3 @@ function _ir_abstract_constant_propagation(interp::AbstractInterpreter, irsv::IR
 
     return Pair{Any,Tuple{Bool,Bool}}(maybe_singleton_const(ultimate_rt), (nothrow, noub))
 end
-
-function ir_abstract_constant_propagation(interp::NativeInterpreter, irsv::IRInterpretationState)
-    if __measure_typeinf__[]
-        inf_frame = Timings.InferenceFrameInfo(irsv.mi, irsv.world, VarState[], Any[], length(irsv.ir.argtypes))
-        Timings.enter_new_timer(inf_frame)
-        ret = _ir_abstract_constant_propagation(interp, irsv)
-        append!(inf_frame.slottypes, irsv.ir.argtypes)
-        Timings.exit_current_timer(inf_frame)
-        return ret
-    else
-        return _ir_abstract_constant_propagation(interp, irsv)
-    end
-end
-ir_abstract_constant_propagation(interp::AbstractInterpreter, irsv::IRInterpretationState) =
-    _ir_abstract_constant_propagation(interp, irsv)

base/compiler/ssair/irinterp.jl

@@ -1,9 +1,11 @@
 # This file is a part of Julia. License is MIT: https://julialang.org/license
 
 function maybe_show_ir(ir::IRCode)
-    if isdefined(Core, :Main)
+    if isdefined(Core, :Main) && isdefined(Core.Main, :Base)
         # ensure we use I/O that does not yield, as this gets called during compilation
         invokelatest(Core.Main.Base.show, Core.stdout, "text/plain", ir)
+    else
+        Core.show(ir)
     end
 end
 
@@ -25,6 +27,7 @@ is_toplevel_expr_head(head::Symbol) = head === :global || head === :method || he
 is_value_pos_expr_head(head::Symbol) = head === :static_parameter
 function check_op(ir::IRCode, domtree::DomTree, @nospecialize(op), use_bb::Int, use_idx::Int, printed_use_idx::Int, print::Bool, isforeigncall::Bool, arg_idx::Int, allow_frontend_forms::Bool)
     if isa(op, SSAValue)
+        op.id > 0 || @verify_error "Def ($(op.id)) is invalid in final IR"
         if op.id > length(ir.stmts)
             def_bb = block_for_inst(ir.cfg, ir.new_nodes.info[op.id - length(ir.stmts)].pos)
         else