C:\blcutil_devel-018>gcc\blcutil.exe -verbose generators\256-32-96-magma.txt -opencl
OpenCL implementation 1: AMD Accelerated Parallel Processing
Device 1 gpu: Pitcairn
Device 2 gpu: BeaverCreek
Device 3 cpu: AMD A6-3650 APU with Radeon(tm) HD Graphics

C:\blcutil_devel-018>gcc\blcutil.exe -verbose generators\256-32-96-magma.txt -opencl=2
OpenCL implementation 1: AMD Accelerated Parallel Processing
Device 1 gpu: Pitcairn
--->Device 2 gpu: BeaverCreek
OpenCL just-in-time compile...
determining simultaneous computation count (global_work_size)...2^6=64
determining codeword count for each computation...2^22=4M
Device 3 cpu: AMD A6-3650 APU with Radeon(tm) HD Graphics
[256, 32, ?]
estimated running time: 19 seconds
running...
2 -96- 222222222222222
0 1
96 377910
100 2227680
104 11860560
108 42570720
112 129450240
116 305877600
120 555624464
124 774718560
128 859276815
132 727765920
136 490256880
140 253441440
144 100683520
148 31065120
152 8115120
156 1428000
160 226746
[256, 32, 96]
elapsed time: 19.11 seconds

C:\blcutil_devel-018>gcc\blcutil.exe -verbose generators\256-32-96-magma.txt -opencl=3
OpenCL implementation 1: AMD Accelerated Parallel Processing
Device 1 gpu: Pitcairn
Device 2 gpu: BeaverCreek
--->Device 3 cpu: AMD A6-3650 APU with Radeon(tm) HD Graphics
OpenCL just-in-time compile...
determining simultaneous computation count (global_work_size)...2^2=4
determining codeword count for each computation...2^26=64M
[256, 32, ?]
estimated running time: 23 seconds
running...
3 -96- 333333333333333
0 1
96 377910
100 2227680
104 11860560
108 42570720
112 129450240
116 305877600
120 555624464
124 774718560
128 859276815
132 727765920
136 490256880
140 253441440
144 100683520
148 31065120
152 8115120
156 1428000
160 226746
[256, 32, 96]
elapsed time: 23.1 seconds

C:\blcutil_devel-018>gcc\blcutil.exe -verbose generators\256-32-96-magma.txt -opencl=2,3
OpenCL implementation 1: AMD Accelerated Parallel Processing
Device 1 gpu: Pitcairn
--->Device 2 gpu: BeaverCreek
OpenCL just-in-time compile...
determining simultaneous computation count (global_work_size)...2^6=64
determining codeword count for each computation...2^22=4M
--->Device 3 cpu: AMD A6-3650 APU with Radeon(tm) HD Graphics
OpenCL just-in-time compile...
determining simultaneous computation count (global_work_size)...2^2=4
determining codeword count for each computation...2^26=64M
[256, 32, ?]
running...
23 -96- 23232323232322
0 1
96 377910
100 2227680
104 11860560
108 42570720
112 129450240
116 305877600
120 555624464
124 774718560
128 859276815
132 727765920
136 490256880
140 253441440
144 100683520
148 31065120
152 8115120
156 1428000
160 226746
[256, 32, 96]
elapsed time: 11.29 seconds

C:\blcutil_devel-018>