Incorrect ptx device specification?

[zealbell]

Is it normal for the Total Number of Block Threads to be 2147483647 whenever my backend is ptx

$ tornado --devices
WARNING: Using incubator modules: jdk.incubator.vector, jdk.incubator.foreign

Number of Tornado drivers: 1
Driver: PTX
  Total number of PTX devices  : 1
  Tornado device=1:0
        PTX -- PTX -- NVIDIA GeForce RTX 3080
                Global Memory Size: 11.8 GB
                Local Memory Size: 48.0 KB
                Workgroup Dimensions: 3
                Total Number of Block Threads: 2147483647 ##same value as  Integer.MAX_VALUE? 
                Max WorkGroup Configuration: [1024, 1024, 64]
                Device OpenCL C version: N/A

meanwhile whenever my backend is opencl Total Number of Block Threads is 1024

$ tornado --devices
WARNING: Using incubator modules: jdk.incubator.vector, jdk.incubator.foreign

Number of Tornado drivers: 1
Driver: OpenCL
  Total number of OpenCL devices  : 1
  Tornado device=0:0
        OPENCL --  [NVIDIA CUDA] -- NVIDIA GeForce RTX 3080
                Global Memory Size: 11.8 GB
                Local Memory Size: 48.0 KB
                Workgroup Dimensions: 3
                Total Number of Block Threads: 1024
                Max WorkGroup Configuration: [1024, 1024, 64]
                Device OpenCL C version: OpenCL C 1.2

NVIDIA-SMI 520.61.05 Driver Version: 520.61.05 CUDA Version: 11.8

[jjfumero]

Thanks for the report. This seems a bug in the TornadoVM Runtime. Can you please open an issue with this report?

[stratika]

Hi, I have just had a look and it seems that the tornado --devices reports the value that is being reported by the driver, and particularly using the CU_DEVICE_ATTRIBUTE_MAX_GRID_DIM_X [1]. In this case, the driver returns (2^31 -1) as the "maximum x-dimension of a grid of thread blocks" [2]. This is the phrasing used in the Nvidia documentation. For y and z dimensions this number is 65535. So, I am not sure that this is a mistake.

1. Do you anticipate to see any particular number different from the current one, based on your driver?
2. Or did the "Total Number of Block Threads" confuse you?

Regarding the second question, we tried to have a common reporting field for all backends (OpenCL, PTX, SPIR-V), so it can create confusion.

[1] https://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__DEVICE.html#group__CUDA__DEVICE_1g9c3e1414f0ad901d3278a4d6645fc266
[2] https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#features-and-technical-specifications

[jjfumero]

Let's continue the discussion in the issue #222