StarPU has found :
32 STARPU_CPU_WORKER workers:
	CPU 0
	CPU 1
	CPU 2
	CPU 3
	CPU 4
	CPU 5
	CPU 6
	CPU 7
	CPU 8
	CPU 9
	CPU 10
	CPU 11
	CPU 12
	CPU 13
	CPU 14
	CPU 15
	CPU 16
	CPU 17
	CPU 18
	CPU 19
	CPU 20
	CPU 21
	CPU 22
	CPU 23
	CPU 24
	CPU 25
	CPU 26
	CPU 27
	CPU 28
	CPU 29
	CPU 30
	CPU 31
4 STARPU_CUDA_WORKER workers:
	CUDA 0.0 (Tesla V100-SXM2-16GB 14.2 GiB 1a:00.0)
	CUDA 1.0 (Tesla V100-SXM2-16GB 14.2 GiB 1c:00.0)
	CUDA 2.0 (Tesla V100-SXM2-16GB 14.2 GiB 1d:00.0)
	CUDA 3.0 (Tesla V100-SXM2-16GB 14.2 GiB 1e:00.0)
No STARPU_OPENCL_WORKER worker

topology ... (hwloc logical indexes)
numa  0	pack  0	core 0	PU 0	CPU 0	
		core 1	PU 1	CPU 1	
		core 2	PU 2	CPU 2	
		core 3	PU 3	CPU 3	
		core 4	PU 4	CPU 4	
		core 5	PU 5	CPU 5	
		core 6	PU 6	CPU 6	
		core 7	PU 7	CPU 7	
		core 8	PU 8	CPU 8	
		core 9	PU 9	CPU 9	
		core 10	PU 10	CPU 10	
		core 11	PU 11	CPU 11	
		core 12	PU 12	CPU 12	
		core 13	PU 13	CPU 13	
		core 14	PU 14	CPU 14	
		core 15	PU 15	CPU 15	
		core 16	PU 16	CPU 16	
		core 17	PU 17	CPU 17	
numa  1	pack  1	core 18	PU 18	CPU 18	
		core 19	PU 19	CPU 19	
		core 20	PU 20	CPU 20	
		core 21	PU 21	CPU 21	
		core 22	PU 22	CPU 22	
		core 23	PU 23	CPU 23	
		core 24	PU 24	CPU 24	
		core 25	PU 25	CPU 25	
		core 26	PU 26	CPU 26	
		core 27	PU 27	CPU 27	
		core 28	PU 28	CPU 28	
		core 29	PU 29	CPU 29	
		core 30	PU 30	CPU 30	
		core 31	PU 31	CPU 31	
		core 32	PU 32	CUDA 0.0 (Tesla V100-SXM2-16GB 14.2 GiB 1a:00.0)	
		core 33	PU 33	CUDA 1.0 (Tesla V100-SXM2-16GB 14.2 GiB 1c:00.0)	
		core 34	PU 34	CUDA 2.0 (Tesla V100-SXM2-16GB 14.2 GiB 1d:00.0)	
		core 35	PU 35	CUDA 3.0 (Tesla V100-SXM2-16GB 14.2 GiB 1e:00.0)	

bandwidth (MB/s) and latency (us)...
from/to	NUMA 0	CUDA 0	CUDA 1	CUDA 2	CUDA 3	
NUMA 0	0	12203	12223	12220	12222	
CUDA 0	12979	0	47413	47744	47742	
CUDA 1	12979	47751	0	47761	47764	
CUDA 2	12979	47750	47746	0	47639	
CUDA 3	12980	47769	47765	47757	0	

NUMA 0	0	9	9	9	9	
CUDA 0	8	0	10	10	10	
CUDA 1	8	10	0	10	10	
CUDA 2	8	10	10	0	10	
CUDA 3	8	10	10	10	0	

GPU	NUMA in preference order (logical index), host-to-device, device-to-host
CUDA_0	 0	
CUDA_1	 0	
CUDA_2	 0	
CUDA_3	 0