[chibi@rhel8 ~]$ cat /etc/redhat-release Red Hat Enterprise Linux release 8.3 (Ootpa) [chibi@rhel8 ~]$ nvcc -V nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2020 NVIDIA Corporation Built on Wed_Jul_22_19:09:09_PDT_2020 Cuda compilation tools, release 11.0, V11.0.221 Build cuda_11.0_bu.TC445_37.28845127_0 [chibi@rhel8 ~]$ nvidia-smi nvlink -c GPU 0: GeForce RTX 2080 Ti (UUID: GPU-13277ce5-e1e9-0cb1-8cee-6c9e6618e774) Link 0, P2P is supported: true Link 0, Access to system memory supported: true Link 0, P2P atomics supported: true Link 0, System memory atomics supported: true Link 0, SLI is supported: true Link 0, Link is supported: false Link 1, P2P is supported: true Link 1, Access to system memory supported: true Link 1, P2P atomics supported: true Link 1, System memory atomics supported: true Link 1, SLI is supported: true Link 1, Link is supported: false GPU 1: GeForce RTX 2080 Ti (UUID: GPU-1ac935c2-557f-282e-14e5-3f749ffd63ac) Link 0, P2P is supported: true Link 0, Access to system memory supported: true Link 0, P2P atomics supported: true Link 0, System memory atomics supported: true Link 0, SLI is supported: true Link 0, Link is supported: false Link 1, P2P is supported: true Link 1, Access to system memory supported: true Link 1, P2P atomics supported: true Link 1, System memory atomics supported: true Link 1, SLI is supported: true Link 1, Link is supported: false [chibi@rhel8 ~]$ ls NVIDIA-Linux-x86_64-450.66.run rtl8812au NVIDIA_CUDA-11.0_Samples ダウンロード containerd.io-1.2.10-3.2.el7.x86_64.rpm テンプレート cuda-repo-rhel8-11-0-local-11.0.3_450.51.06-1.x86_64.rpm デスクトップ docker-ce-19.03.5-3.el7.x86_64.rpm ドキュメント docker-ce-cli-19.03.5-3.el7.x86_64.rpm ビデオ hddtemp-0.3-0.43.beta15.el8.x86_64.rpm 音楽 libcudnn8-8.0.4.30-1.cuda11.0.x86_64.rpm 画像 libcudnn8-devel-8.0.4.30-1.cuda11.0.x86_64.rpm 公開 [chibi@rhel8 ~]$ cd NVIDIA_CUDA-11.0_Samples [chibi@rhel8 NVIDIA_CUDA-11.0_Samples]$ ls 0_Simple 3_Imaging 6_Advanced LICENSE common 1_Utilities 4_Finance 7_CUDALibraries Makefile 2_Graphics 5_Simulations EULA.txt bin [chibi@rhel8 NVIDIA_CUDA-11.0_Samples]$ cd 0_Simple [chibi@rhel8 0_Simple]$ ls UnifiedMemoryStreams simpleCooperativeGroups asyncAPI simpleCubemapTexture bf16TensorCoreGemm simpleCudaGraphs binaryPartitionCG simpleDrvRuntime cdpSimplePrint simpleIPC cdpSimpleQuicksort simpleLayeredTexture clock simpleMPI clock_nvrtc simpleMultiCopy cppIntegration simpleMultiGPU cppOverload simpleOccupancy cudaNvSci simpleP2P cudaOpenMP simplePitchLinearTexture cudaTensorCoreGemm simplePrintf dmmaTensorCoreGemm simpleSeparateCompilation fp16ScalarProduct simpleStreams globalToShmemAsyncCopy simpleSurfaceWrite immaTensorCoreGemm simpleTemplates inlinePTX simpleTemplates_nvrtc inlinePTX_nvrtc simpleTexture matrixMul simpleTextureDrv matrixMulCUBLAS simpleVoteIntrinsics matrixMulDrv simpleVoteIntrinsics_nvrtc matrixMul_nvrtc simpleZeroCopy memMapIPCDrv systemWideAtomics simpleAWBarrier template simpleAssert tf32TensorCoreGemm simpleAssert_nvrtc vectorAdd simpleAtomicIntrinsics vectorAddDrv simpleAtomicIntrinsics_nvrtc vectorAddMMAP simpleAttributes vectorAdd_nvrtc simpleCallback [chibi@rhel8 0_Simple]$ cd simpleP2P [chibi@rhel8 simpleP2P]$ ./simpleP2P [./simpleP2P] - Starting... Checking for multiple GPUs... CUDA-capable device count: 2 Checking GPU(s) for support of peer to peer memory access... > Peer access from GeForce RTX 2080 Ti (GPU0) -> GeForce RTX 2080 Ti (GPU1) : Yes > Peer access from GeForce RTX 2080 Ti (GPU1) -> GeForce RTX 2080 Ti (GPU0) : Yes Enabling peer access between GPU0 and GPU1... Allocating buffers (64MB on GPU0, GPU1 and CPU Host)... Creating event handles... cudaMemcpyPeer / cudaMemcpy between GPU0 and GPU1: 43.54GB/s Preparing host buffer and memcpy to GPU0... Run kernel on GPU1, taking source data from GPU0 and writing to GPU1... Run kernel on GPU0, taking source data from GPU1 and writing to GPU0... Copy data back to host from GPU0 and verify results... Disabling peer access... Shutting down... Test passed [chibi@rhel8 simpleP2P]$ cd ~/NVIDIA_CUDA-11.0_Samples/1_Utilities/p2pBandwidthLatencyTest [chibi@rhel8 p2pBandwidthLatencyTest]$ ./p2pBandwidthLatencyTest [P2P (Peer-to-Peer) GPU Bandwidth Latency Test] Device: 0, GeForce RTX 2080 Ti, pciBusID: 81, pciDeviceID: 0, pciDomainID:0 Device: 1, GeForce RTX 2080 Ti, pciBusID: 82, pciDeviceID: 0, pciDomainID:0 Device=0 CAN Access Peer Device=1 Device=1 CAN Access Peer Device=0 ***NOTE: In case a device doesn't have P2P access to other one, it falls back to normal memcopy procedure. So you can see lesser Bandwidth (GB/s) and unstable Latency (us) in those cases. P2P Connectivity Matrix D\D 0 1 0 1 1 1 1 1 Unidirectional P2P=Disabled Bandwidth Matrix (GB/s) D\D 0 1 0 541.90 11.59 1 11.65 530.99 Unidirectional P2P=Enabled Bandwidth (P2P Writes) Matrix (GB/s) D\D 0 1 0 532.20 47.10 1 47.10 530.97 Bidirectional P2P=Disabled Bandwidth Matrix (GB/s) D\D 0 1 0 531.34 13.08 1 13.19 519.45 Bidirectional P2P=Enabled Bandwidth Matrix (GB/s) D\D 0 1 0 530.00 94.13 1 94.09 529.60 P2P=Disabled Latency Matrix (us) GPU 0 1 0 1.58 19.60 1 21.56 1.27 CPU 0 1 0 4.19 12.43 1 12.33 4.12 P2P=Enabled Latency (P2P Writes) Matrix (us) GPU 0 1 0 1.39 1.77 1 1.77 1.27 CPU 0 1 0 4.17 3.61 1 3.67 4.19 NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled. [chibi@rhel8 p2pBandwidthLatencyTest]$ cd ~/NVIDIA_CUDA-11.0_Samples/1_Utilities/bandwidthTest [chibi@rhel8 bandwidthTest]$ ./bandwidthTest [CUDA Bandwidth Test] - Starting... Running on... Device 0: GeForce RTX 2080 Ti Quick Mode Host to Device Bandwidth, 1 Device(s) PINNED Memory Transfers Transfer Size (Bytes) Bandwidth(GB/s) 32000000 11.8 Device to Host Bandwidth, 1 Device(s) PINNED Memory Transfers Transfer Size (Bytes) Bandwidth(GB/s) 32000000 9.8 Device to Device Bandwidth, 1 Device(s) PINNED Memory Transfers Transfer Size (Bytes) Bandwidth(GB/s) 32000000 518.8 Result = PASS NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled. [chibi@rhel8 bandwidthTest]$ cd ~/NVIDIA_CUDA-11.0_Samples/1_Utilities/deviceQuery [chibi@rhel8 deviceQuery]$ ./deviceQuery ./deviceQuery Starting... CUDA Device Query (Runtime API) version (CUDART static linking) Detected 2 CUDA Capable device(s) Device 0: "GeForce RTX 2080 Ti" CUDA Driver Version / Runtime Version 11.0 / 11.0 CUDA Capability Major/Minor version number: 7.5 Total amount of global memory: 11019 MBytes (11554324480 bytes) (68) Multiprocessors, ( 64) CUDA Cores/MP: 4352 CUDA Cores GPU Max Clock rate: 1635 MHz (1.63 GHz) Memory Clock rate: 7000 Mhz Memory Bus Width: 352-bit L2 Cache Size: 5767168 bytes Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384) Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers Total amount of constant memory: 65536 bytes Total amount of shared memory per block: 49152 bytes Total number of registers available per block: 65536 Warp size: 32 Maximum number of threads per multiprocessor: 1024 Maximum number of threads per block: 1024 Max dimension size of a thread block (x,y,z): (1024, 1024, 64) Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535) Maximum memory pitch: 2147483647 bytes Texture alignment: 512 bytes Concurrent copy and kernel execution: Yes with 3 copy engine(s) Run time limit on kernels: Yes Integrated GPU sharing Host Memory: No Support host page-locked memory mapping: Yes Alignment requirement for Surfaces: Yes Device has ECC support: Disabled Device supports Unified Addressing (UVA): Yes Device supports Managed Memory: Yes Device supports Compute Preemption: Yes Supports Cooperative Kernel Launch: Yes Supports MultiDevice Co-op Kernel Launch: Yes Device PCI Domain ID / Bus ID / location ID: 0 / 129 / 0 Compute Mode: < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) > Device 1: "GeForce RTX 2080 Ti" CUDA Driver Version / Runtime Version 11.0 / 11.0 CUDA Capability Major/Minor version number: 7.5 Total amount of global memory: 11019 MBytes (11554717696 bytes) (68) Multiprocessors, ( 64) CUDA Cores/MP: 4352 CUDA Cores GPU Max Clock rate: 1635 MHz (1.63 GHz) Memory Clock rate: 7000 Mhz Memory Bus Width: 352-bit L2 Cache Size: 5767168 bytes Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384) Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers Total amount of constant memory: 65536 bytes Total amount of shared memory per block: 49152 bytes Total number of registers available per block: 65536 Warp size: 32 Maximum number of threads per multiprocessor: 1024 Maximum number of threads per block: 1024 Max dimension size of a thread block (x,y,z): (1024, 1024, 64) Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535) Maximum memory pitch: 2147483647 bytes Texture alignment: 512 bytes Concurrent copy and kernel execution: Yes with 3 copy engine(s) Run time limit on kernels: Yes Integrated GPU sharing Host Memory: No Support host page-locked memory mapping: Yes Alignment requirement for Surfaces: Yes Device has ECC support: Disabled Device supports Unified Addressing (UVA): Yes Device supports Managed Memory: Yes Device supports Compute Preemption: Yes Supports Cooperative Kernel Launch: Yes Supports MultiDevice Co-op Kernel Launch: Yes Device PCI Domain ID / Bus ID / location ID: 0 / 130 / 0 Compute Mode: < Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) > > Peer access from GeForce RTX 2080 Ti (GPU0) -> GeForce RTX 2080 Ti (GPU1) : Yes > Peer access from GeForce RTX 2080 Ti (GPU1) -> GeForce RTX 2080 Ti (GPU0) : Yes deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 11.0, CUDA Runtime Version = 11.0, NumDevs = 2 Result = PASS [chibi@rhel8 deviceQuery]$ nvidia-smi Mon Nov 30 06:43:58 2020 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 450.66 Driver Version: 450.66 CUDA Version: 11.0 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 GeForce RTX 208... Off | 00000000:81:00.0 Off | N/A | | 41% 27C P8 15W / 260W | 232MiB / 11019MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ | 1 GeForce RTX 208... Off | 00000000:82:00.0 Off | N/A | | 41% 25C P8 19W / 260W | 6MiB / 11019MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ +-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | 0 N/A N/A 1918 G /usr/libexec/Xorg 105MiB | | 0 N/A N/A 2471 G /usr/bin/gnome-shell 123MiB | | 1 N/A N/A 1918 G /usr/libexec/Xorg 4MiB | +-----------------------------------------------------------------------------+ [chibi@rhel8 deviceQuery]$ lscpu アーキテクチャ: x86_64 CPU 操作モード: 32-bit, 64-bit バイト順序: Little Endian CPU: 32 オンラインになっている CPU のリスト: 0-31 コアあたりのスレッド数: 2 ソケットあたりのコア数: 16 ソケット数: 1 NUMA ノード数: 1 ベンダー ID: AuthenticAMD CPU ファミリー: 23 モデル: 49 モデル名: AMD EPYC 7302P 16-Core Processor ステッピング: 0 CPU MHz: 1793.332 CPU 最大 MHz: 3000.0000 CPU 最小 MHz: 1500.0000 BogoMIPS: 5988.73 仮想化: AMD-V L1d キャッシュ: 32K L1i キャッシュ: 32K L2 キャッシュ: 512K L3 キャッシュ: 16384K NUMA ノード 0 CPU: 0-31 フラグ: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate sme ssbd mba sev ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif umip rdpid overflow_recov succor smca [chibi@rhel8 deviceQuery]$ lsmem RANGE SIZE STATE REMOVABLE BLOCK 0x0000000000000000-0x0000000007ffffff 128M online no 0 0x0000000008000000-0x000000002fffffff 640M online yes 1-5 0x0000000030000000-0x0000000037ffffff 128M online no 6 0x0000000038000000-0x000000006fffffff 896M online yes 7-13 0x0000000070000000-0x0000000077ffffff 128M online no 14 0x0000000078000000-0x000000008fffffff 384M online yes 15-17 0x0000000090000000-0x00000000afffffff 512M online no 18-21 0x0000000100000000-0x0000000107ffffff 128M online no 32 0x0000000108000000-0x0000000dd7ffffff 51.3G online yes 33-442 0x0000000dd8000000-0x0000000ddfffffff 128M online no 443 0x0000000de0000000-0x0000000e97ffffff 2.9G online yes 444-466 0x0000000e98000000-0x0000000e9fffffff 128M online no 467 0x0000000ea0000000-0x0000000eafffffff 256M online yes 468-469 0x0000000eb0000000-0x0000000ebfffffff 256M online no 470-471 0x0000000ec0000000-0x0000000ecfffffff 256M online yes 472-473 0x0000000ed0000000-0x0000000edfffffff 256M online no 474-475 0x0000000ee0000000-0x0000000eefffffff 256M online yes 476-477 0x0000000ef0000000-0x0000000effffffff 256M online no 478-479 0x0000000f00000000-0x0000000f0fffffff 256M online yes 480-481 0x0000000f10000000-0x0000000f1fffffff 256M online no 482-483 0x0000000f20000000-0x0000000f37ffffff 384M online yes 484-486 0x0000000f38000000-0x0000000f3fffffff 128M online no 487 0x0000000f40000000-0x0000000f4fffffff 256M online yes 488-489 0x0000000f50000000-0x0000000f5fffffff 256M online no 490-491 0x0000000f60000000-0x0000000f6fffffff 256M online yes 492-493 0x0000000f70000000-0x0000000f7fffffff 256M online no 494-495 0x0000000f80000000-0x0000000f8fffffff 256M online yes 496-497 0x0000000f90000000-0x0000000f9fffffff 256M online no 498-499 0x0000000fa0000000-0x0000000fafffffff 256M online yes 500-501 0x0000000fb0000000-0x0000000fbfffffff 256M online no 502-503 0x0000000fc0000000-0x0000000fd7ffffff 384M online yes 504-506 0x0000000fd8000000-0x000000104fffffff 1.9G online no 507-521 メモリブロックサイズ 128M Total online memory: 64G Total offline memory: 0B [chibi@rhel8 deviceQuery]$ free total used free shared buff/cache available Mem: 65616004 1301676 63396376 12064 917952 63650592 Swap: 0 0 0 [chibi@rhel8 deviceQuery]$ lscpu アーキテクチャ: x86_64 CPU 操作モード: 32-bit, 64-bit バイト順序: Little Endian CPU: 32 オンラインになっている CPU のリスト: 0-31 コアあたりのスレッド数: 2 ソケットあたりのコア数: 16 ソケット数: 1 NUMA ノード数: 1 ベンダー ID: AuthenticAMD CPU ファミリー: 23 モデル: 49 モデル名: AMD EPYC 7302P 16-Core Processor ステッピング: 0 CPU MHz: 1793.174 CPU 最大 MHz: 3000.0000 CPU 最小 MHz: 1500.0000 BogoMIPS: 5988.73 仮想化: AMD-V L1d キャッシュ: 32K L1i キャッシュ: 32K L2 キャッシュ: 512K L3 キャッシュ: 16384K NUMA ノード 0 CPU: 0-31 フラグ: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate sme ssbd mba sev ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif umip rdpid overflow_recov succor smca [chibi@rhel8 deviceQuery]$