NVIDIA : Install HPC SDK2022/08/29

	Install NVIDIA HPC SDK.
[1]	Install NVIDIA driver first, refer to here.
[2]	Install NVIDIA HPC SDK.

root@dlp:~#

echo 'deb [trusted=yes] https://developer.download.nvidia.com/hpc-sdk/ubuntu/amd64 /' | tee /etc/apt/sources.list.d/nvhpc.list

root@dlp:~#

apt update

root@dlp:~#

apt install -y nvhpc-21-9 environment-modules

root@dlp:~#

vi /etc/environment-modules/modulespath

# add to the end

/opt/nvidia/hpc_sdk/modulefiles

root@dlp:~#

source /etc/profile.d/modules.sh

root@dlp:~#

module avail

------------------------ /usr/share/modules/modulefiles ------------------------
dot  module-git  module-info  modules  null  use.own

----------------------- /opt/nvidia/hpc_sdk/modulefiles ------------------------
nvhpc-byo-compiler/21.9   nvhpc-nompi/21.9   nvhpc/21.9
nvhpc-byo-compiler/21.11  nvhpc-nompi/21.11  nvhpc/21.11

Key:
modulepath

root@dlp:~#

module load nvhpc/21.9

root@dlp:~#

nvc --version


nvc 21.9-0 64-bit target on x86-64 Linux -tp haswell
NVIDIA Compilers and Tools
Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.

root@dlp:~#

nvaccelinfo


CUDA Driver Version:           11060
NVRM version:                  NVIDIA UNIX x86_64 Kernel Module  510.85.02  Tue Jul 12 16:51:23 UTC 2022

Device Number:                 0
Device Name:                   NVIDIA GeForce GTX 1060 6GB
Device Revision Number:        6.1
Global Memory Size:            6373376000
Number of Multiprocessors:     10
Concurrent Copy and Execution: Yes
Total Constant Memory:         65536
Total Shared Memory per Block: 49152
Registers per Block:           65536
Warp Size:                     32
Maximum Threads per Block:     1024
Maximum Block Dimensions:      1024, 1024, 64
Maximum Grid Dimensions:       2147483647 x 65535 x 65535
Maximum Memory Pitch:          2147483647B
Texture Alignment:             512B
Clock Rate:                    1847 MHz
Execution Timeout:             No
Integrated Device:             No
Can Map Host Memory:           Yes
Compute Mode:                  default
Concurrent Kernels:            Yes
ECC Enabled:                   No
Memory Clock Rate:             4004 MHz
Memory Bus Width:              192 bits
L2 Cache Size:                 1572864 bytes
Max Threads Per SMP:           2048
Async Engines:                 2
Unified Addressing:            Yes
Managed Memory:                Yes
Concurrent Managed Memory:     Yes
Preemption Supported:          Yes
Cooperative Launch:            Yes
  Multi-Device:                Yes
Default Target:                cc61

Matched Content