Talking Trash: The Evolution of Garbage Collection on Android

Learn how the Android garbage collector has evolved from Dalvik to ART. This talk explains why you should worry more about good code than avoiding allocations.

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
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)
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
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?