Hi,
I’m just wondering if it is possible to run lammps on a CPU which has an internal GPU.
I was able to compile lammps on MacOS with an Intel CPU which has a GPU included.
However, when trying to execute LAMMPS with gpu, always the CPU device is chosen by opencl (which does not work by the way, some opencl error) and I have found no possibility to choose the GPU device.
Ocl_get_devices returns:
Found 1 platform(s).
Using platform: Apple Apple OpenCL 1.2 (Jun 23 2019 21:50:55)
Platform 0:
Device 0: “Intel® Core™ i5-5675R CPU @ 3.10GHz”
Type of device: CPU
Double precision support: Yes
Total amount of global memory: 8 GB
Number of compute units/multiprocessors: 4
Total amount of constant memory: 65536 bytes
Total amount of local/shared memory per block: 32768 bytes
Maximum group size (# of threads per block) 1024
Maximum item sizes (# threads for each dim) 1024 x 1 x 1
Clock rate: 3.1 GHz
ECC support: No
Device fission into equal partitions: No
Device fission by counts: No
Device fission by affinity: No
Maximum subdevices from fission: 0
Device 1: “Intel® Iris™ Pro Graphics 6200”
Type of device: GPU
Double precision support: No
Total amount of global memory: 1.5 GB
Number of compute units/multiprocessors: 48
Total amount of constant memory: 65536 bytes
Total amount of local/shared memory per block: 65536 bytes
Maximum group size (# of threads per block) 256
Maximum item sizes (# threads for each dim) 256 x 256 x 256
Clock rate: 1.1 GHz
ECC support: No
Device fission into equal partitions: No
Device fission by counts: No
Device fission by affinity: No
Maximum subdevices from fission: 0
Best regards,
Holger