Talking Trash: The Evolution of Garbage Collection on Android

Transcript

1. Talking Trash @chethaase & @romainguy

2. “Garbage in, garbage out”

3. “Garbage in, garbage out” But how fast?

4. Modern Android Development Chet Haase @chethaase Romain Guy @romainguy

5. Modern Android Development Chet Haase @chethaase Romain Guy @romainguy

6. Modern Android Development Chet Haase @chethaase Romain Guy @romainguy Blah

   blah blah memory blah blah...

7. Optimized for size 
 | 
 +- JIT optimizations not

   
 | as powerful 
 | 
 +- Allocation/collection slow 
 | 
 +- Heap fragmentation Dalvik

8. So: _ Avoid allocation whenever possible > For example: enums

   _ Primitive types are cool 
 (autoboxing is not)

9. ART Optimized for performance JIT + AOT Faster allocation/collection Heap

   defragmentation Large object heap

10. ART Optimized for performance JIT + AOT Faster allocation/collection Heap

    defragmentation Large object heap So:

11. ART Optimized for performance JIT + AOT Faster allocation/collection Heap

    defragmentation Large object heap So: Allocate as necessary (yes, even enums) Use appropriate types But: phones are still constrained batteries are, too be aware of inner-loop bottlenecks

12. Memories int foo = 5; MyObject thing = new MyObject();

13. Memories Stack int foo = 5; MyObject thing = new

    MyObject();

14. Memories Stack Registers int foo = 5; MyObject thing =

    new MyObject();

15. Memories Stack Registers int foo = 5; MyObject thing =

    new MyObject(); foo

16. Memories Stack Registers int foo = 5; MyObject thing =

    new MyObject(); foo

17. Memories Stack Registers int foo = 5; MyObject thing =

    new MyObject(); Heap foo

18. Memories Stack Registers int foo = 5; MyObject thing =

    new MyObject(); Heap foo thing

19. Manual Garbage Collection MyObject* thing = new MyObject; // code

    using thing... delete thing; // code using thing C++

20. Manual Garbage Collection MyObject* thing = new MyObject; // code

    using thing... delete thing; // code using thing Leak! C++

21. Manual Garbage Collection MyObject* thing = new MyObject; // code

    using thing... delete thing; // code using thing C++

22. Manual Garbage Collection MyObject* thing = new MyObject; // code

    using thing... delete thing; // code using thing C++

23. Manual Garbage Collection MyObject* thing = new MyObject; // code

    using thing... delete thing; // code using thing Crash! C++

24. Manual Garbage Collection MyObject* thing = new MyObject; // code

    using thing... delete thing; // code using thing Crash! C++ (maybe)

25. Automatic Garbage Collection MyObject thing = new MyObject(); // code

    using thing… Java

26. Automatic Garbage Collection MyObject thing = new MyObject(); // code

    using thing… No leak! Java // eventually freed

27. Automatic Garbage Collection MyObject thing = new MyObject(); // code

    using thing… No leak! Java // eventually freed // code using thing…

28. Automatic Garbage Collection MyObject thing = new MyObject(); // code

    using thing… No leak! No crash! Java // eventually freed // code using thing…

29. Runtime GC Concerns

30. Runtime GC Concerns How long does allocation take?

31. Runtime GC Concerns How long does allocation take? 
 How

    long does collection take?

32. Runtime GC Concerns How long does allocation take? 
 How

    long does collection take? What impact does this have across all threads?

33. Runtime GC Concerns How long does allocation take? 
 How

    long does collection take? What impact does this have across all threads? When do collections happen?

34. Runtime GC Concerns How long does allocation take? 
 How

    long does collection take? What impact does this have across all threads? When do collections happen? 
 How efficient is heap usage?

35. Dalvik GC ? Allocation

36. Dalvik GC ? Allocation

37. Dalvik GC ? Allocation

38. Dalvik GC Allocation

39. Dalvik GC Collection

40. Dalvik GC Collection Mark root set (pause)

41. Dalvik GC Collection Mark root set (pause) Mark reachable I

    (concurrent)

42. Dalvik GC Collection Mark root set (pause) Mark reachable I

    (concurrent)

43. Dalvik GC Collection Mark root set (pause) Mark reachable I

    (concurrent) Mark reachable II (pause)

44. Dalvik GC Collection Mark root set (pause) Mark reachable I

    (concurrent) Mark reachable II (pause)

45. Dalvik GC Collection Mark root set (pause) Mark reachable I

    (concurrent) Mark reachable II (pause) Collect (concurrent)

46. Dalvik GC ? Allocation, Take II

47. Dalvik GC ? Allocation, Take II

48. Dalvik GC ? Allocation, Take II

49. Collection: GC_FOR_ALLOC Dalvik GC ?

50. Collection: GC_FOR_ALLOC Dalvik GC ?

51. Allocation Dalvik GC ?

52. Allocation Dalvik GC

53. Dalvik GC ? Allocation, Take III

54. Dalvik GC ? Allocation, Take III

55. Dalvik GC ? Grow the Heap

56. Dalvik GC ? Out of Memory Error Grow the Heap

    or…

57. Fragmentation! (Kitkat) Heap

58. Fragmentation! (Kitkat) Heap

59. Fragmentation! (Kitkat) Heap

60. Fragmentation! (Kitkat) Heap

61. Fragmentation! (Kitkat) Heap

62. Fragmentation! (Kitkat) Heap

63. Fragmentation! (Kitkat) Heap ?

64. Fragmentation! (Kitkat) Heap ?

65. D/dalvikvm: GC_FOR_ALLOC freed 2K, 50% free 197613K/392536K, paused 6ms, total

    6ms I/dalvikvm-heap: Forcing collection of SoftReferences for 2000012-byte allocation D/dalvikvm: GC_BEFORE_OOM freed 0K, 50% free 197613K/392536K, paused 6ms, total 6ms E/dalvikvm-heap: Out of memory on a 2000012-byte allocation. Sad Logcat

66. D/dalvikvm: GC_FOR_ALLOC freed 2K, 50% free 197613K/392536K, paused 6ms, total

    6ms I/dalvikvm-heap: Forcing collection of SoftReferences for 2000012-byte allocation D/dalvikvm: GC_BEFORE_OOM freed 0K, 50% free 197613K/392536K, paused 6ms, total 6ms E/dalvikvm-heap: Out of memory on a 2000012-byte allocation. Sad Logcat

67. D/dalvikvm: GC_FOR_ALLOC freed 2K, 50% free 197613K/392536K, paused 6ms, total

    6ms I/dalvikvm-heap: Forcing collection of SoftReferences for 2000012-byte allocation D/dalvikvm: GC_BEFORE_OOM freed 0K, 50% free 197613K/392536K, paused 6ms, total 6ms E/dalvikvm-heap: Out of memory on a 2000012-byte allocation. Sad Logcat

68. D/dalvikvm: GC_FOR_ALLOC freed 2K, 50% free 197613K/392536K, paused 6ms, total

    6ms I/dalvikvm-heap: Forcing collection of SoftReferences for 2000012-byte allocation D/dalvikvm: GC_BEFORE_OOM freed 0K, 50% free 197613K/392536K, paused 6ms, total 6ms E/dalvikvm-heap: Out of memory on a 2000012-byte allocation. Sad Logcat

69. D/dalvikvm: GC_FOR_ALLOC freed 2K, 50% free 197613K/392536K, paused 6ms, total

    6ms I/dalvikvm-heap: Forcing collection of SoftReferences for 2000012-byte allocation D/dalvikvm: GC_BEFORE_OOM freed 0K, 50% free 197613K/392536K, paused 6ms, total 6ms E/dalvikvm-heap: Out of memory on a 2000012-byte allocation. Sad Logcat

70. ART (Lollipop) Faster allocation! 
 Faster collection! 
 Faster runtime!

71. ART Allocation

72. ART Allocation RosAlloc

73. ART Allocation RosAlloc Replacement for dlmalloc

74. ART Allocation RosAlloc Replacement for dlmalloc Thread-local allocations

75. ART Allocation RosAlloc Replacement for dlmalloc Thread-local allocations Grouped small

    allocations, page-aligned large allocations

76. ART Allocation RosAlloc Replacement for dlmalloc Thread-local allocations Grouped small

    allocations, page-aligned large allocations Finer-grained locks

77. ART Allocation RosAlloc Replacement for dlmalloc Thread-local allocations Grouped small

    allocations, page-aligned large allocations Finer-grained locks 4-5x faster than Dalvik!

78. ART Allocation RosAlloc Replacement for dlmalloc Thread-local allocations Grouped small

    allocations, page-aligned large allocations Finer-grained locks 4-5x faster than Dalvik!

79. ART Allocation

80. ART Allocation Large object space

81. ART Allocation Large object space

82. ART Allocation Large object space

83. ART Allocation Large object space

84. ART Allocation Large object space In Dalvik

85. ART Allocation Large object space ? In Dalvik

86. ART Allocation Large object space In ART

87. ART Allocation Large object space In ART

88. ART Allocation Large object space Moving collector! In ART

89. ART Allocation Large object space Moving collector! No more fragmentation!

    In ART

90. ART Allocation Large object space Moving collector! No more fragmentation!

    In ART * * Eventually

91. ART Allocation Large object space Moving collector! No more fragmentation!

    In ART * * Eventually

92. Fragmentation! (L+) Heap

93. Fragmentation! (L+) Heap

94. Fragmentation! (L+) Heap

95. Fragmentation! (L+) Heap ?

96. Fragmentation! (L+) Heap ?

97. Dalvik GC Mark root set (pause) Mark reachable I (concurrent)

    Mark reachable II (pause) Collect (concurrent)

98. ~10ms Dalvik GC Mark root set (pause) Mark reachable I

    (concurrent) Mark reachable II (pause) Collect (concurrent)

99. ~10ms Mark root set (pause) Mark reachable I (concurrent) Mark

    reachable II (pause) Collect (concurrent) ART GC

100. Mark root set (pause) Mark reachable I (concurrent) Mark reachable

     II (pause) Collect (concurrent) ART GC

101. Mark root set (concurrent) Mark reachable I (concurrent) Mark reachable

     II (pause) Collect (concurrent) ART GC

102. Mark root set (concurrent) Mark reachable I (concurrent) Mark reachable

     II (pause) Collect (concurrent) ART GC Faster!

103. ~3ms Mark root set (concurrent) Mark reachable I (concurrent) Mark

     reachable II (pause) Collect (concurrent) ART GC Faster!

104. ART Collection

105. ART Collection Minor GC

106. ART Collection Minor GC Fast collection of “young generation”

107. ART Collection Minor GC Fast collection of “young generation” Temporary

     objects less expensive

108. ART Collection Minor GC Fast collection of “young generation” Temporary

     objects less expensive 
 Large object heap

109. ART Collection Minor GC Fast collection of “young generation” Temporary

     objects less expensive 
 Large object heap Less fragmentation

110. ART Collection Minor GC Fast collection of “young generation” Temporary

     objects less expensive 
 Large object heap Less fragmentation Less heap resizing

111. ART Collection Minor GC Fast collection of “young generation” Temporary

     objects less expensive 
 Large object heap Less fragmentation Less heap resizing Fewer GC_FOR_ALLOC pauses

112. ART Collection Minor GC Fast collection of “young generation” Temporary

     objects less expensive 
 Large object heap Less fragmentation Less heap resizing Fewer GC_FOR_ALLOC pauses 
 Faster runtime

113. ART in Marshmallow Optimizing compiler Allocation optimizations

114. ART in Nougat

115. ART in Nougat More inlining and optimizations

116. ART in Nougat More inlining and optimizations

117. ART in Nougat More inlining and optimizations Allocation

118. ART in Nougat More inlining and optimizations Allocation Rewritten in

     assembly

119. ART in Nougat More inlining and optimizations Allocation Rewritten in

     assembly 10x faster than Dalvik (Kitkat)

120. ART in Oreo

121. ART in Oreo Concurrent heap compaction

122. ART in Oreo Concurrent heap compaction Defragmentation in foreground!

123. ART in Oreo Concurrent heap compaction Defragmentation in foreground! Less

     heap resizing, GC_FOR_ALLOC

124. ART in Oreo Concurrent heap compaction Defragmentation in foreground! Less

     heap resizing, GC_FOR_ALLOC

125. ART in Oreo Concurrent heap compaction Defragmentation in foreground! Less

     heap resizing, GC_FOR_ALLOC Device-wide memory savings

126. ART in Oreo Concurrent heap compaction Defragmentation in foreground! Less

     heap resizing, GC_FOR_ALLOC Device-wide memory savings System and Google Play Services

127. ART in Oreo Concurrent heap compaction Defragmentation in foreground! Less

     heap resizing, GC_FOR_ALLOC Device-wide memory savings System and Google Play Services Smaller heaps for all

128. ART in Oreo Concurrent heap compaction Defragmentation in foreground! Less

     heap resizing, GC_FOR_ALLOC Device-wide memory savings System and Google Play Services Smaller heaps for all

129. Concurrent Compaction Heap ... T0 Region T1 Region T2 Region

     T3 Region Tn Region ... ...

130. Concurrent Compaction Heap ... T0 Region T1 Region T2 Region

     T3 Region Tn Region ... ... Compaction Phase

131. Concurrent Compaction Heap ... T0 Region T1 Region T2 Region

     T3 Region Tn Region ... ... Compaction Phase

132. Concurrent Compaction Heap ... T0 Region T1 Region T2 Region

     T3 Region Tn Region ... ... Compaction Phase

133. Concurrent Compaction Heap ... T0 Region T1 Region T2 Region

     T3 Region Tn Region ... ... Compaction Phase

134. ART in Oreo Thread-local bump allocator 70% faster allocations than

     Nougat 18x faster than Dalvik (Kitkat)

135. Concurrent Compaction — Allocation Heap ... T0 Region T1 Region

     T2 Region T3 Region Tn Region All-thread Heap ... ...

136. Concurrent Compaction — Allocation Heap ... T0 Region T1 Region

     T2 Region T3 Region Tn Region All-thread Heap ... ...

137. Concurrent Compaction — Allocation Heap ... T0 Region T1 Region

     T2 Region T3 Region Tn Region All-thread Heap ... ... T1 Region Free Pointer

138. Concurrent Compaction — Allocation Heap ... T0 Region T1 Region

     T2 Region T3 Region Tn Region All-thread Heap ... ... T1 Region Free Pointer

139. Concurrent Compaction — Allocation Heap ... T0 Region T1 Region

     T2 Region T3 Region Tn Region All-thread Heap ... ... T1 Region Free Pointer

140. Concurrent Compaction — Allocation Heap ... T0 Region T1 Region

     T2 Region T3 Region Tn Region All-thread Heap ... ... T1 Region Free Pointer

141. Concurrent Compaction — Allocation Heap ... T0 Region T1 Region

     T2 Region T3 Region Tn Region All-thread Heap ... ... T1 Region Free Pointer

142. Concurrent Compaction — Allocation Heap ... T0 Region T1 Region

     T2 Region T3 Region Tn Region All-thread Heap ... ... T1 Region Free Pointer

143. Allocation Improvements

144. ART in O+

145. ART in O+ Young generation collections gone in O

146. ART in O+ Young generation collections gone in O Enabled

     in AOSP

147. ART in O+ Young generation collections gone in O Enabled

     in AOSP Watch for that future release…

148. Object Pools

149. Object Pools Conventional wisdom

150. Object Pools Conventional wisdom Reusing objects is faster (saves on

     allocation/collection time)


151. Object Pools Conventional wisdom Reusing objects is faster (saves on

     allocation/collection time)
 Actual wisdom

152. Object Pools Conventional wisdom Reusing objects is faster (saves on

     allocation/collection time)
 Actual wisdom As of Oreo, synchronized object pools are generally slower

153. Soooo… What Now? Creating garbage is okay (and so is

     collecting it)
 Use the types and objects you need Even enums
 GC is still overhead But not as critical to avoid as it was in Dalvik Make the right choices for your architecture Avoid overhead in critical sections when possible

154. Jank Test Autoboxing

155. Jank Test Autoboxing private Float[] mHolder = new Float[100_000];

156. Jank Test Autoboxing public void run() { long startTime =

     System.currentTimeMillis(); float f = 0f; for (int i = 0; i < mHolder.length; ++i, f += 1.0f) { mHolder[i] = f; } System.out.println("Alloc time = " + (System.currentTimeMillis() - startTime)); } private Float[] mHolder = new Float[100_000];

157. Jank Test Autoboxing public void run() { long startTime =

     System.currentTimeMillis(); float f = 0f; for (int i = 0; i < mHolder.length; ++i, f += 1.0f) { mHolder[i] = f; } System.out.println("Alloc time = " + (System.currentTimeMillis() - startTime)); } private Float[] mHolder = new Float[100_000]; I/System.out: Alloc time = 28 D/dalvikvm: GC_FOR_ALLOC freed 2047K, 1% free 337371K/339492K, paused 10ms, total 10ms I/System.out: Alloc time = 29

158. Jank Test Autoboxing public void run() { long startTime =

     System.currentTimeMillis(); float f = 0f; for (int i = 0; i < mHolder.length; ++i, f += 1.0f) { mHolder[i] = f; } System.out.println("Alloc time = " + (System.currentTimeMillis() - startTime)); } private Float[] mHolder = new Float[100_000]; I/System.out: Alloc time = 28 D/dalvikvm: GC_FOR_ALLOC freed 2047K, 1% free 337371K/339492K, paused 10ms, total 10ms I/System.out: Alloc time = 29 I/System.out: Alloc time = 3 I/System.out: Alloc time = 2 I/System.out: Alloc time = 4

159. Jank Test Bitmaps

160. Jank Test Bitmaps public void run() { long startTime =

     System.currentTimeMillis(); mBitmap = Bitmap.createBitmap(1_000, 1_000, Bitmap.Config.ARGB_8888); System.out.println("Alloc time = " + (System.currentTimeMillis() - startTime)); }

161. Jank Test Bitmaps public void run() { long startTime =

     System.currentTimeMillis(); mBitmap = Bitmap.createBitmap(1_000, 1_000, Bitmap.Config.ARGB_8888); System.out.println("Alloc time = " + (System.currentTimeMillis() - startTime)); } I/System.out: Alloc time = 16 D/dalvikvm: GC_FOR_ALLOC freed 3907K, 2% free 341280K/347244K, paused 7ms, total 7ms I/dalvikvm-heap: Grow heap (frag case) to 337.165MB for 4000012-byte allocation D/dalvikvm: GC_FOR_ALLOC freed <1K, 1% free 345186K/347244K, paused 7ms, total 7ms

162. Jank Test Bitmaps public void run() { long startTime =

     System.currentTimeMillis(); mBitmap = Bitmap.createBitmap(1_000, 1_000, Bitmap.Config.ARGB_8888); System.out.println("Alloc time = " + (System.currentTimeMillis() - startTime)); } I/System.out: Alloc time = 16 D/dalvikvm: GC_FOR_ALLOC freed 3907K, 2% free 341280K/347244K, paused 7ms, total 7ms I/dalvikvm-heap: Grow heap (frag case) to 337.165MB for 4000012-byte allocation D/dalvikvm: GC_FOR_ALLOC freed <1K, 1% free 345186K/347244K, paused 7ms, total 7ms I/System.out: Alloc time = 1 I/System.out: Alloc time = 0 I/System.out: Alloc time = 0 I/System.out: Alloc time = 1
163. None

164. data class Float3(x: Float, y: Float, z: Float) fun Tonemap_ACES(x:

     Float3): Float3 { val a = 2.51f val b = 0.03f val c = 2.43f val d = 0.59f val e = 0.14f return (x * (a * x + b)) / (x * (c * x + d) + e) }

165. inline operator fun Float.plus(v: Float3) = Float3(this + v.x, this

     + v.y, this + v.z) inline operator fun Float.times(v: Float3) = Float3(this * v.x, this * v.y, this * v.z)
166. None
167. None
168. None

169. Android O, 1 tile = 00.1~00.5s

170. Android O, 1 tile = 00.1~00.5s Android K, 1 tile

     = 40.0~50.0s

171. 10-23 14:40:04.997 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K,

     paused 4ms, total 4ms 10-23 14:40:05.067 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.147 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.177 3885-3907/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:05.207 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 3ms, total 3ms 10-23 14:40:05.277 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.307 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5125K/5912K, paused 3ms, total 3ms 10-23 14:40:05.357 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 713K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:05.397 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 3ms, total 3ms 10-23 14:40:05.447 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.517 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.607 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.677 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.707 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 4ms, total 4ms 10-23 14:40:05.767 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.837 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.867 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.897 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:05.957 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:05.997 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:06.037 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:06.107 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:06.157 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 3ms, total 3ms 10-23 14:40:06.227 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 4ms, total 4ms 10-23 14:40:06.267 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 3ms, total 3ms 10-23 14:40:06.337 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:06.367 3885-3907/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:06.437 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:06.527 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:06.597 3885-3907/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 4ms, total 4ms 10-23 14:40:06.617 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 4ms, total 4ms 10-23 14:40:06.697 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:06.717 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:06.767 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:06.817 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 713K, 14% free 5124K/5912K, paused 3ms, total 3ms 10-23 14:40:06.857 3885-3907/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 711K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:06.937 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:06.957 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.027 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.117 3885-3907/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.157 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.197 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:07.257 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.307 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 3ms, total 3ms 10-23 14:40:07.357 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.397 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 3ms, total 3ms 10-23 14:40:07.447 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.477 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.557 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.617 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.647 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.677 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:07.707 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.727 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:07.767 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.797 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:07.847 3885-3907/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:07.927 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5125K/5912K, paused 5ms, total 5ms 10-23 14:40:08.057 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 713K, 14% free 5124K/5912K, paused 4ms, total 4ms 10-23 14:40:08.077 3885-3907/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:08.107 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:08.147 3885-3908/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 4ms, total 4ms 10-23 14:40:08.207 3885-3901/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms 10-23 14:40:08.267 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 713K, 14% free 5124K/5912K, paused 4ms, total 4ms 10-23 14:40:08.287 3885-3907/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 711K, 14% free 5124K/5912K, paused 5ms, total 5ms 10-23 14:40:08.337 3885-3902/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 4ms, total 4ms

172. 10-23 14:40:24.847 3885-3909/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K,

     paused 3ms, total 3ms 10-23 14:40:24.917 3885-3903/com.google.ray_trasher D/dalvikvm: GC_FOR_ALLOC freed 712K, 14% free 5124K/5912K, paused 2ms, total 2ms
173. None

174. Benchmarks, GC and Caches

175. Core Core Core Core Kryo 385 (Pixel 3) “Gold” cores

176. Core Core Core Core L1 L1 L1 L1 Kryo 385

     (Pixel 3) 4x 32 KiB “Gold” cores

177. Core Core Core Core L2 L2 L2 L2 L1 L1

     L1 L1 Kryo 385 (Pixel 3) 4x 32 KiB “Gold” cores 4x 256 KiB

178. Core Core Core Core L2 L2 L2 L2 L3 L1

     L1 L1 L1 Kryo 385 (Pixel 3) 4x 32 KiB “Gold” cores 4x 256 KiB 1x 2 MiB

179. L2 L3 L1 private val data = FloatArray(16) // …

     val a = foo[0] RAM

180. L2 L3 L1 private val data = FloatArray(16) // …

     val a = foo[0] RAM

181. L2 L3 L1 private val data = FloatArray(16) // …

     val a = foo[0] RAM

182. L2 L3 L1 private val data = FloatArray(16) // …

     val a = foo[0] RAM

183. L2 L3 L1 private val data = FloatArray(16) // …

     val a = foo[0] RAM

184. 64 bytes

185. val m = ArrayList<FloatArray>(n) 64 bytes

186. m[0] = FloatArray(4) m[1] = FloatArray(4) m[2] = FloatArray(4) m[n]

     = FloatArray(4) val m = ArrayList<FloatArray>(n) 64 bytes

187. m[0] = FloatArray(4) m[1] = FloatArray(4) m[2] = FloatArray(4) m[n]

     = FloatArray(4) val m = ArrayList<FloatArray>(n) RAM 64 bytes

188. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

189. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

190. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

191. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

192. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

193. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

194. m[0] = FloatArray(4) m[1] = FloatArray(4) m[2] = FloatArray(4) m[n]

     = FloatArray(4) val m = ArrayList<FloatArray>(n) RAM 64 bytes

195. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

196. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

197. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

198. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

199. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

200. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

201. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

202. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

203. m[0] FloatArray(4) m[1] FloatArray(4) m[2] FloatArray(4) m[n] FloatArray(4) val m

     = ArrayList<FloatArray>(n) for (i in 0 until m.size - 3) { val a = m[i ] val b = m[i + 1] val c = m[i + 2] val d = m[i + 3] computeStuff(a, b, c, d) } L1 64 bytes

204. 0.0 1.0 2.0 3.0 4.0 5.0 6.0 No thrash L1

     thrash L2 thrash Relative computation times (Pixel 3)

205. On some workloads, the work of the GC will affect

     performance

206. You might be benchmarking perfect memory access patterns

207. Questions?