K Nearest Neighbourhood on GPU

K Nearest Neighbourhood using inverted list on GPU

Transcript

1. Genie-and- Lamp-GPU Yiwei Gong K Nearest Neighbourhood using inverted list on GPU
2. K Nearest Neighbourhood Fundamental Operator in Data Mining Classification 0 5 10 15 20 0 3 6 9 12 Regression Collaborative Filtering You may like * Apple * Google * Amazon
3. SELECT SEX M AGE 18 SALARY 2900 Sex Age Salary … M 20 3000 … F 17 3600 … M 18 4000 … F 19 2900 … K Nearest Neighbourhood A running example
4. SELECT SEX M AGE 18 SALARY 2900 K Nearest Neighbourhood Sex Age Salary … M 20 3000 … F 17 3600 … M 18 4000 … F 19 2900 … A running example
5. DIM + VALUE SEX+M SEX+F AGE+18 AGE+19 … 2 0 3 1 2 Invert list: row_id SELECT SEX M AGE 18 SALARY 2900 3 How do we store the inverted list table on GPU?
6. DIM + VALUE Inverted List … … AGE+17 1 AGE+18 2, 3 AGE+19 4 AGE+20 9, 10 AGE+21 11 … … Row ID Count AGG … … … 1 0 0 2 0 0 3 0 0 4 0 0 … … … SELECT AGE 18±1 Step 1: Matching & Aggregation
7. DIM + VALUE Inverted List … … AGE+17 1 AGE+18 2, 3 AGE+19 4 AGE+20 9, 10 AGE+21 11 … … Row ID Count AGG … … … 1 0 0 2 1 1*0.5 3 1 1*0.5 4 0 0 … … … SELECT AGE 18±1 Step 1: Matching & Aggregation
8. DIM + VALUE Inverted List … … AGE+17 1 AGE+18 2, 3 AGE+19 4 AGE+20 9, 10 AGE+21 11 … … Row ID Count AGG … … … 1 1 1*0.5 2 1 1*0.5 3 1 1*0.5 4 1 1*0.5 … … … SELECT AGE 18±1 Step 1: Matching & Aggregation
9. DIM + VALUE Inverted List … … SALARY+2500 NULL SALARY+3000 0, 3 SALARY+3500 1 SALARY+4000 2 SALARY+4500 4,5 … … SELECT SALARY 2900±1000 Row ID Count AGG … … … 1 1 0.5 2 1 0.5 3 1 0.5 4 1 0.5 … … … Step 1: Matching & Aggregation
10. DIM + VALUE Inverted List … … SALARY+2500 NULL SALARY+3000 0, 3 SALARY+3500 1 SALARY+4000 2 SALARY+4500 4,5 … … Row ID Count AGG … … … 1 1 0.5 2 1 0.5 3 2 1*0.3+0.5 4 1 0.5 … … … SELECT SALARY 2900±1000 Step 1: Matching & Aggregation
11. Block 1 Block 2 Block 2 SEX AGE SALARY GPU Parallel Matching
12. Row ID Count AGG … … … 1 1 0.5 2 1 0.5 3 2 0.8 4 1 0.5 … … … K Selection What is the fast K Selection algorithm? Step 2: K Selection
13. R_id R_id R_id R_id R_id R_id R_id D+V1 D+V2 D+V3 invert_list_idx invert_list_table end_index First approach to store the inverted list table on GPU GPU
14. Host Device Map Main Memory ! KEY GPU Memory ! VALUE
15. dimension + value1 dimension + value2 Invert_list_idx Invert_list_table
17. Mapping C P U ! M E M O R Y
18. Mapping C P U ! M E M O R Y
19. Mapping C P U ! M E M O R Y MAP(KEY, INDEX) device_vector
20. Mapping C P U ! M E M O R Y raw_pointer get(key) map(key, value) freeze() ratio()
21. Bucket Top K Selection Algorithm 2 4 1 5 2 1 K = 10 First 7 results Bucket_Num = (Value - MIN) / (MAX - MIN) * Number_Of_Buckets
22. Bucket Top K Selection Algorithm Accept Multi Queries K = 2 K = 5 K = 6 K = 3
23. #define NAME “YIWEI GONG” #define UNIVERSITY “NTU” #define EMAIL “imwithye@gmail.com” #define BLOG “http://ciel.im” #define ME “A stupid programmer” THANK YOU
24. Block 1 Block 2 Block 3 Block 4 Block 5 Block 6 GPU Thread 1 Thread 2 Thread 3 Thread 4 Thread 5 Thread 6 Block