Download as PDF, PPTX
![Ruby Challenges
• Dynamic dispatch for most things
• Dynamic possibly-mutating constants
• Fixnum to Bignum promotion
• Literals for arrays, hashes: [a, b, c].sort[1]
• Stack access via closures, bindings
• Rich inheritance model](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-3-2048.jpg)
![JRuby 9000
• Mixed mode runtime (now with tiers!)
• Lazy JIT to JVM bytecode
• byte[] strings and regular expressions
• Lots of native integration via FFI
• 9.0.5.0 is current](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-6-2048.jpg)
![def foo(a, b)
c = 1
d = a + c
end
0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
2 b = recv_pre_reqd_arg(1)
3 %block = recv_closure
4 thread_poll
5 line_num(1)
6 c = 1
7 line_num(2)
8 %v_0 = call(:+, a, [c])
9 d = copy(%v_0)
10 return(%v_0)
Register-based
3 address format
IR InstructionsSemantic
Analysis](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-9-2048.jpg)
![-Xir.passes=LocalOptimizationPass,
DeadCodeElimination
def foo(a, b)
c = 1
d = a + c
end
0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
2 b = recv_pre_reqd_arg(1)
3 %block = recv_closure
4 thread_poll
5 line_num(1)
6 c = 1
7 line_num(2)
8 %v_0 = call(:+, a, [c])
9 d = copy(%v_0)
10 return(%v_0)
Optimization](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-10-2048.jpg)
![-Xir.passes=LocalOptimizationPass,
DeadCodeElimination
def foo(a, b)
c = 1
d = a + c
end
0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
2 b = recv_pre_reqd_arg(1)
3 %block = recv_closure
4 thread_poll
5 line_num(1)
6 c = 1
7 line_num(2)
8 %v_0 = call(:+, a, [c])
9 d = copy(%v_0)
10 return(%v_0)
Optimization](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-11-2048.jpg)
![-Xir.passes=LocalOptimizationPass,
DeadCodeElimination
def foo(a, b)
c = 1
d = a + c
end
0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
2 b = recv_pre_reqd_arg(1)
3 %block = recv_closure
4 thread_poll
5 line_num(1)
6 c = 1
7 line_num(2)
8 %v_0 = call(:+, a, [c])
9 d = copy(%v_0)
10 return(%v_0)
Optimization](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-12-2048.jpg)
![def foo(a, b)
c = 1
d = a + c
end
0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
4 thread_poll
5 line_num(1)
6 c = 1
7 line_num(2)
8 %v_0 = call(:+, a, [c])
9 d = copy(%v_0)
10 return(%v_0)
Optimization -Xir.passes=LocalOptimizationPass,
DeadCodeElimination](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-13-2048.jpg)
![def foo(a, b)
c = 1
d = a + c
end
0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
4 thread_poll
5 line_num(1)
6 c = 1
7 line_num(2)
8 %v_0 = call(:+, a, [c])
9 d = copy(%v_0)
10 return(%v_0)
Optimization -Xir.passes=LocalOptimizationPass,
DeadCodeElimination](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-14-2048.jpg)
![def foo(a, b)
c = 1
d = a + c
end
0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
4 thread_poll
5 line_num(1)
6 c = 1
7 line_num(2)
8 %v_0 = call(:+, a, [c])
9 d = copy(%v_0)
10 return(%v_0)
Optimization -Xir.passes=LocalOptimizationPass,
DeadCodeElimination](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-15-2048.jpg)
![def foo(a, b)
c = 1
d = a + c
end
0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
4 thread_poll
5 line_num(1)
6 c =
7 line_num(2)
8 %v_0 = call(:+, a, [ ])
9 d = copy(%v_0)
10 return(%v_0)
1
Optimization -Xir.passes=LocalOptimizationPass,
DeadCodeElimination](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-16-2048.jpg)
![def foo(a, b)
c = 1
d = a + c
end
0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
4 thread_poll
5 line_num(1)
7 line_num(2)
8 %v_0 = call(:+, a, [1])
9 d = copy(%v_0)
10 return(%v_0)
Optimization -Xir.passes=LocalOptimizationPass,
DeadCodeElimination](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-17-2048.jpg)
![0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
4 thread_poll
5 line_num(1)
7 line_num(2)
8 %v_0 = call(:+, a, [1])
9 d = copy(%v_0)
10 return(%v_0)
Optimization -Xir.passes=LocalOptimizationPass,
DeadCodeElimination](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-18-2048.jpg)
![0 check_arity(2, 0, -1)
1 a = recv_pre_reqd_arg(0)
4 thread_poll
7 line_num(2)
8 %v_0 = call(:+, a, [1])
9 d = copy(%v_0)
10 return(%v_0)
Optimization -Xir.passes=LocalOptimizationPass,
DeadCodeElimination](https://image.slidesharecdn.com/jfokus2016-optimizingjruby-160208134151/75/JRuby-9000-Optimizing-Above-the-JVM-19-2048.jpg)
Uploaded byCharles Nutter
JRuby 9000 - Optimizing Above the JVM
JRuby 9000 optimizes Ruby on the JVM with features like dynamic dispatch, mutable literals, and a rich inheritance model. It introduces a mixed-mode runtime with JIT compilation, block JITs, and optimizations for method calls and closures. Current efforts focus on enhancing performance through numerical specialization, profiling, and inlining, while addressing the limitations of JVM for Ruby's unique features.
More Related Content
Similar to JRuby 9000 - Optimizing Above the JVM
JRuby 9000 - Optimizing Above the JVM
- 1. JRuby 9000 Optimizing Abovethe JVM
- 2. Me • Charles OliverNutter (@headius) • Red Hat • Based in Minneapolis, Minnesota • Ten years working on JRuby (uff da!)
- 3. Ruby Challenges • Dynamicdispatch for most things • Dynamic possibly-mutating constants • Fixnum to Bignum promotion • Literals for arrays, hashes: [a, b, c].sort[1] • Stack access via closures, bindings • Rich inheritance model
- 4. module SayHello def say_hello "Hello," + to_s end end class Foo include SayHello def initialize @my_data = {bar: 'baz', quux: 'widget'} end def to_s @my_data.map do |k,v| "#{k} = #{v}" end.join(', ') end end Foo.new.say_hello # => "Hello, bar = baz, quux = widget"
- 5. More Challenges • "Everything'san object" • Tracing and debugging APIs • Pervasive use of closures • Mutable literal strings
- 6. JRuby 9000 • Mixedmode runtime (now with tiers!) • Lazy JIT to JVM bytecode • byte[] strings and regular expressions • Lots of native integration via FFI • 9.0.5.0 is current
- 7. New IR • Optimizableintermediate representation • AST to semantic IR • Traditional compiler design • Register machine • SSA-ish where it's useful
- 8. Lexical Analysis Parsing Semantic Analysis Optimization Bytecode Generation Interpret AST IR Instructions CFG DFG... JRuby 1.7.x 9000+ Bytecode Generation Interpret
- 9. def foo(a, b) c= 1 d = a + c end 0 check_arity(2, 0, -1) 1 a = recv_pre_reqd_arg(0) 2 b = recv_pre_reqd_arg(1) 3 %block = recv_closure 4 thread_poll 5 line_num(1) 6 c = 1 7 line_num(2) 8 %v_0 = call(:+, a, [c]) 9 d = copy(%v_0) 10 return(%v_0) Register-based 3 address format IR InstructionsSemantic Analysis
- 10. -Xir.passes=LocalOptimizationPass, DeadCodeElimination def foo(a, b) c= 1 d = a + c end 0 check_arity(2, 0, -1) 1 a = recv_pre_reqd_arg(0) 2 b = recv_pre_reqd_arg(1) 3 %block = recv_closure 4 thread_poll 5 line_num(1) 6 c = 1 7 line_num(2) 8 %v_0 = call(:+, a, [c]) 9 d = copy(%v_0) 10 return(%v_0) Optimization
- 11. -Xir.passes=LocalOptimizationPass, DeadCodeElimination def foo(a, b) c= 1 d = a + c end 0 check_arity(2, 0, -1) 1 a = recv_pre_reqd_arg(0) 2 b = recv_pre_reqd_arg(1) 3 %block = recv_closure 4 thread_poll 5 line_num(1) 6 c = 1 7 line_num(2) 8 %v_0 = call(:+, a, [c]) 9 d = copy(%v_0) 10 return(%v_0) Optimization
- 12. -Xir.passes=LocalOptimizationPass, DeadCodeElimination def foo(a, b) c= 1 d = a + c end 0 check_arity(2, 0, -1) 1 a = recv_pre_reqd_arg(0) 2 b = recv_pre_reqd_arg(1) 3 %block = recv_closure 4 thread_poll 5 line_num(1) 6 c = 1 7 line_num(2) 8 %v_0 = call(:+, a, [c]) 9 d = copy(%v_0) 10 return(%v_0) Optimization
- 13. def foo(a, b) c= 1 d = a + c end 0 check_arity(2, 0, -1) 1 a = recv_pre_reqd_arg(0) 4 thread_poll 5 line_num(1) 6 c = 1 7 line_num(2) 8 %v_0 = call(:+, a, [c]) 9 d = copy(%v_0) 10 return(%v_0) Optimization -Xir.passes=LocalOptimizationPass, DeadCodeElimination
- 14. def foo(a, b) c= 1 d = a + c end 0 check_arity(2, 0, -1) 1 a = recv_pre_reqd_arg(0) 4 thread_poll 5 line_num(1) 6 c = 1 7 line_num(2) 8 %v_0 = call(:+, a, [c]) 9 d = copy(%v_0) 10 return(%v_0) Optimization -Xir.passes=LocalOptimizationPass, DeadCodeElimination
- 15. def foo(a, b) c= 1 d = a + c end 0 check_arity(2, 0, -1) 1 a = recv_pre_reqd_arg(0) 4 thread_poll 5 line_num(1) 6 c = 1 7 line_num(2) 8 %v_0 = call(:+, a, [c]) 9 d = copy(%v_0) 10 return(%v_0) Optimization -Xir.passes=LocalOptimizationPass, DeadCodeElimination
- 16. def foo(a, b) c= 1 d = a + c end 0 check_arity(2, 0, -1) 1 a = recv_pre_reqd_arg(0) 4 thread_poll 5 line_num(1) 6 c = 7 line_num(2) 8 %v_0 = call(:+, a, [ ]) 9 d = copy(%v_0) 10 return(%v_0) 1 Optimization -Xir.passes=LocalOptimizationPass, DeadCodeElimination
- 17. def foo(a, b) c= 1 d = a + c end 0 check_arity(2, 0, -1) 1 a = recv_pre_reqd_arg(0) 4 thread_poll 5 line_num(1) 7 line_num(2) 8 %v_0 = call(:+, a, [1]) 9 d = copy(%v_0) 10 return(%v_0) Optimization -Xir.passes=LocalOptimizationPass, DeadCodeElimination
- 18. 0 check_arity(2, 0,-1) 1 a = recv_pre_reqd_arg(0) 4 thread_poll 5 line_num(1) 7 line_num(2) 8 %v_0 = call(:+, a, [1]) 9 d = copy(%v_0) 10 return(%v_0) Optimization -Xir.passes=LocalOptimizationPass, DeadCodeElimination
- 19. 0 check_arity(2, 0,-1) 1 a = recv_pre_reqd_arg(0) 4 thread_poll 7 line_num(2) 8 %v_0 = call(:+, a, [1]) 9 d = copy(%v_0) 10 return(%v_0) Optimization -Xir.passes=LocalOptimizationPass, DeadCodeElimination
- 20. Tiers in theRain • Tier 1: Simple interpreter (no passes run) • Tier 2: Full interpreter (static optimization) • Tier 3: Full interpreter (profiled optz) • Tier 4: JVM bytecode (static) • Tier 5: JVM bytecode (profiled) • Tiers 6+:Whatever JVM does from there
- 21. Truffle? • Write yourAST + specializations • AST rewrites as it runs • Eventually emits Graal IR (i.e. not JVM) • Very fast peak perf on benchmarks • Poor startup, warmup, memory use • Year(s) left until generally usable
- 22. Red/black tree benchmark 0 2.25 4.5 6.75 9 JRubyint JRuby no indy JRuby with indy JRuby+Truffle CRuby 2.3
- 23. Why Not JustJVM? • JVM is great, but missing many things • I'll mention some along the way
- 24.
- 25. Block Jitting • JRuby1.7 only jitted methods • Not free-standing procs/lambdas • Not define_method blocks • Easier to do now with 9000's IR • Blocks JIT as of 9.0.4.0
- 26. define_method Convenient for metaprogramming, butblocks have more overhead than methods. define_method(:add) do |a, b| a + b end names.each do |name| define_method(name) { send :"do_#{name}" } end
- 27. Optimizing define_method • Noncapturing •Treat as method in compiler • Ignore surrounding scope • Capturing (future work) • Lift read-only variables as constant
- 28. Getting Better! 0k iters/s 1000kiters/s 2000k iters/s 3000k iters/s 4000k iters/s def define_method define_method w/ capture MRI JRuby 9.0.1.0 JRuby 9.0.4.0
- 29. JVM? • Missing feature:access to call frames • No way to expose local variables • Therefore, have to use heap • Allocation, loss of locality
- 30. Low-cost Exceptions • Backtracecost isVERY high on JVM • Lots of work to construct • Exceptions frequently ignored • ...or used as flow control (shame!) • If ignored, backtrace is not needed!
- 31. Postfix Antipattern foo rescuenil Exception raised StandardError rescued Exception ignored Result is simple expression, so exception is never visible.
- 32. csv.rb Converters Converters ={ integer: lambda { |f| Integer(f) rescue f }, float: lambda { |f| Float(f) rescue f }, ... All trivial rescues, no traces needed.
- 33. Strategy • Inspect rescueblock • If simple expression... • Thread-local requiresBacktrace = false • Backtrace generation short circuited • Reset to true on exit or nontrivial rescue
- 34.
- 35.
- 36. JVM? • Horrific costfor stack traces • Only eliminated if inlined • Disabling is not really an option
- 37.
- 38. Object Shaping • Rubyinstance vars allocated dynamically • JRuby currently grows an array • We have code to specialize as fields • Working, tested • Probably next release
- 39. public class RubyObjectVar2extends ReifiedRubyObject { private Object var0; private Object var1; private Object var2; public RubyObjectVar2(Ruby runtime, RubyClass metaClass) { super(runtime, metaClass); } @Override public Object getVariable(int i) { switch (i) { case 0: return var0; case 1: return var1; case 2: return var2; default: return super.getVariable(i); } } public Object getVariable0() { return var0; } ... public void setVariable0(Object value) { ensureInstanceVariablesSettable(); var0 = value; } ... }
- 40. JVM? • No wayto truly generify fields • Valhalla will be useful here • No way to grow an object
- 41. Inlining • 900 poundgorilla of optimization • shove method/closure back to callsite • specialize closure-receiving methods • eliminate call protocol • We know Ruby better than the JVM
- 42. JVM? • JVM willinline for us, but... • only if we use invokedynamic • and the code isn't too big • and it's not polymorphic • and we're not a closure (lambdas too!) • and it feels like it
- 43. Today’s Inliner def decrement_one(i) i- 1 end i = 1_000_000 while i > 0 i = decrement_one(i) end def decrement_one(i) i - 1 end i = 1_000_000 while i < 0 if guard_same? self i = i - 1 else i = decrement_one(i) end end
- 44. Today’s Inliner def decrement_one(i) i- 1 end i = 1_000_000 while i > 0 i = decrement_one(i) end def decrement_one(i) i - 1 end i = 1_000_000 while i < 0 if guard_same? self i = i - 1 else i = decrement_one(i) end end
- 45. Today’s Inliner def decrement_one(i) i- 1 end i = 1_000_000 while i > 0 i = decrement_one(i) end def decrement_one(i) i - 1 end i = 1_000_000 while i < 0 if guard_same? self i = i - 1 else i = decrement_one(i) end end
- 46. Today’s Inliner def decrement_one(i) i- 1 end i = 1_000_000 while i > 0 i = decrement_one(i) end def decrement_one(i) i - 1 end i = 1_000_000 while i < 0 if guard_same? self i = i - 1 else i = decrement_one(i) end end
- 47. Profiling • You can'tinline if you can't profile! • For each call site record call info • Which method(s) called • How frequently • Inline most frequently-called method
- 48. Inlining a Closure defsmall_loop(i) k = 10 while k > 0 k = yield(k) end i - 1 end def big_loop(i) i = 100_000 while true i = small_loop(i) { |j| j - 1 } return 0 if i < 0 end end 900.times { |i| big_loop i } hot & monomorphic Like an Array#each May see many blocks JVM will not inline this
- 49. Inlining FTW! 0 15 30 45 60 Time inseconds 14.1 56.9
- 50. Profiling • <2% overhead(to be reduced more) • Working* (interpreter AND JIT) • Feeds directly into inlining • Deopt coming soon * Fragile and buggy!
- 51. Interpreter FTW! • Deoptis much simpler with interpreter • Collect local vars, instruction index • Raise exception to interpreter, keep going • Much cheaper than resuming bytecode
- 52. Numeric Specialization • "Unboxing" •Ruby: everything's an object • Tagged pointer for Fixnum, Float • JVM: references OR primitives • Need to optimize numerics as primitive
- 53. JVM? • Escape analysisis inadequate (today) • Hotspot will eliminate boxes if... • All code inlines • No (unfollowed?) branches in the code • Dynamic calls have type guards • Fixnum + Fixnum has overflow check
- 54. def looper(n) i =0 while i < n do_something(i) i += 1 end end def looper(long n) long i = 0 while i < n do_something(i) i += 1 end end Specialize n, i to long def looper(n) i = 0 while i < n do_something(i) i += 1 end end Deopt to object version if n or i + 1 is not Fixnum
- 55. Unboxing Today • Workingprototype • No deopt • No type guards • No overflow check for Fixnum/Bignum
- 56. Rendering * * * * * *** ***** ***** *** * ********* ************* *************** ********************* ********************* ******************* ******************* ******************* ******************* *********************** ******************* ******************* ********************* ******************* ******************* ***************** *************** ************* ********* * *************** *********************** * ************************* * ***************************** ******************************** * ********************************* *********************************** *************************************** *** ***************************************** *** ************************************************* *********************************************** ********************************************* ********************************************* *********************************************** *********************************************** *************************************************** ************************************************* ************************************************* *************************************************** *************************************************** * *************************************************** * ***** *************************************************** ***** ****** *************************************************** ****** ******* *************************************************** ******* *********************************************************************** ********* *************************************************** ********* ****** *************************************************** ****** ***** *************************************************** ***** *************************************************** *************************************************** *************************************************** *************************************************** ************************************************* ************************************************* *************************************************** *********************************************** *********************************************** ******************************************* ***************************************** ********************************************* **** ****************** ****************** **** *** **************** **************** *** * ************** ************** * *********** *********** ** ***** ***** ** * * * * 0.520000 0.020000 0.540000 ( 0.388744)
- 57. def iterate(x,y) cr =y-0.5 ci = x zi = 0.0 zr = 0.0 i = 0 bailout = 16.0 max_iterations = 1000 while true i += 1 temp = zr * zi zr2 = zr * zr zi2 = zi * zi zr = zr2 - zi2 + cr zi = temp + temp + ci return i if (zi2 + zr2 > bailout) return 0 if (i > max_iterations) end end
- 60.
- 61. Mandelbrot performance 0 0.075 0.15 0.225 0.3 JRuby JRuby+ truffle JRuby on Graal
- 62. Mandelbrot performance 0 0.035 0.07 0.105 0.14 JRuby +truffle JRuby on Graal JRuby unbox
- 63. When? • Object shapeshould be in 9.1 • Profiling, inlining mostly need testing • Specialization needs guards, deopt • Active work over next 6-12mo
- 64. Summary • JVM isgreat, but we need more • Partial EA, frame access, specialization • Gotta stay ahead of these youngsters! • JRuby 9000 is aVM on top of aVM • We believe we can match Truffle • (for a large range of optimizations)
- 65. ThankYou • Charles OliverNutter • @headius • [email protected]