2

I want to access various NVidia GPU specifications using Numba or a similar Python CUDA pacakge. Information such as available device memory, L2 cache size, memory clock frequency, etc.

From reading this question, I learned I can access some of the information (but not all) through Numba's CUDA device interface.

from numba import cuda

device = cuda.get_current_device()
attribs = [s for s in dir(device) if s.isupper()]
for attr in attribs:
    print(attr, '=', getattr(device, attr))

Output on a test machine:

ASYNC_ENGINE_COUNT = 4
CAN_MAP_HOST_MEMORY = 1
COMPUTE_CAPABILITY = (5, 0)
MAX_BLOCK_DIM_X = 1024
MAX_BLOCK_DIM_Y = 1024
MAX_BLOCK_DIM_Z = 64
MAX_GRID_DIM_X = 2147483647
MAX_GRID_DIM_Y = 65535
MAX_GRID_DIM_Z = 65535
MAX_SHARED_MEMORY_PER_BLOCK = 49152
MAX_THREADS_PER_BLOCK = 1024
MULTIPROCESSOR_COUNT = 3
PCI_BUS_ID = 1
PCI_DEVICE_ID = 0
UNIFIED_ADDRESSING = 1
WARP_SIZE = 32

As you can see, I'm missing many fields listed here such as TOTAL_CONSTANT_MEMORY, MAX_SHARED_MEMORY_PER_BLOCK, MEMORY_CLOCK_RATE, and MAX_THREADS_PER_MULTI_PROCESSOR.

How can I view these values in Python?

user174358
  • 187
  • 1
  • 9

1 Answers1

5

All these values are lazily set to device object via __getattr__ method. You can access them with similar like in this method. You need to dir not a device, but enums itself:

from numba.cuda.cudadrv import enums
from numba import cuda

device = cuda.get_current_device()
attribs= [name.replace("CU_DEVICE_ATTRIBUTE_", "") for name in dir(enums) if name.startswith("CU_DEVICE_ATTRIBUTE_")]
for attr in attribs:
    print(attr, '=', getattr(device, attr))
prudenko
  • 1,663
  • 13
  • 19