bandwidthtest fails--now what?

Accelerated Computing CUDA CUDA Setup and Installation
1

I just downloaded the CUDA toolkit for windows, ran the install, rebooted, compiled the sample code and tried to run the tests per the installation guide. devicequery seemed to run properly, bandwidthtest failed at default settings, passed quick mode with memory paged, failed quick test with memory pinned, failed shmoo

It seems that there is an issue but I have no idea how to troubleshoot it and would welcome any advice, including “RTFM” if someone can point me at the correct M.

Thank you.

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v9.0\bin\win64\Release>devicequery
devicequery Starting…

CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: “GeForce GTX 1080”
CUDA Driver Version / Runtime Version 9.0 / 9.0
CUDA Capability Major/Minor version number: 6.1
Total amount of global memory: 8192 MBytes (8589934592 bytes)
(20) Multiprocessors, (128) CUDA Cores/MP: 2560 CUDA Cores
GPU Max Clock rate: 1734 MHz (1.73 GHz)
Memory Clock rate: 5005 Mhz
Memory Bus Width: 256-bit
L2 Cache Size: 2097152 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: 2048
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 2 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
CUDA Device Driver Mode (TCC or WDDM): WDDM (Windows Display Driver Model)
Device supports Unified Addressing (UVA): Yes
Supports Cooperative Kernel Launch: No
Supports MultiDevice Co-op Kernel Launch: No
Device PCI Domain ID / Bus ID / location ID: 0 / 10 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 9.0, CUDA Runtime Version = 9.0, NumDevs = 1
Result = PASS

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v9.0\bin\win64\Release>bandwidthtest
[CUDA Bandwidth Test] - Starting…
Running on…

Device 0: GeForce GTX 1080
Quick Mode

CUDA error at C:/ProgramData/NVIDIA Corporation/CUDA Samples/v9.0/1_Utilities/bandwidthTest/bandwidthTest.cu:805 code=4(cudaErrorLaunchFailure) “cudaDeviceSynchronize()”

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v9.0\bin\win64\Release>bandwidthtest --memory=pageable
[CUDA Bandwidth Test] - Starting…
Running on…

Device 0: GeForce GTX 1080
Quick Mode

Host to Device Bandwidth, 1 Device(s)
PAGEABLE Memory Transfers
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 737.9

Device to Host Bandwidth, 1 Device(s)
PAGEABLE Memory Transfers
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 770.5

Device to Device Bandwidth, 1 Device(s)
PAGEABLE Memory Transfers
Transfer Size (Bytes) Bandwidth(MB/s)
33554432 226621.6

Result = PASS

NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v9.0\bin\win64\Release>bandwidthtest --memory=pinned
[CUDA Bandwidth Test] - Starting…
Running on…

Device 0: GeForce GTX 1080
Quick Mode

CUDA error at C:/ProgramData/NVIDIA Corporation/CUDA Samples/v9.0/1_Utilities/bandwidthTest/bandwidthTest.cu:805 code=4(cudaErrorLaunchFailure) “cudaDeviceSynchronize()”

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v9.0\bin\win64\Release>bandwidthtest --mode=shmoo
[CUDA Bandwidth Test] - Starting…
Running on…

Device 0: GeForce GTX 1080
Shmoo Mode

…CUDA error at C:/ProgramData/NVIDIA Corporation/CUDA Samples/v9.0/1_Utilities/bandwidthTest/bandwidthTest.cu:805 code=4(cudaErrorLaunchFailure) “cudaDeviceSynchronize()”

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v9.0\bin\win64\Release>

2

The reported device/host bandwidth is incredibly low, it should be around 11,000 MB/s for a PCIe gen3 x16 slot. Either the GPU is inserted into the wrong PCIe slot (the data rate looks like it is using a x1 connection!), or there is some sort of issue with the PCIe connector (e.g. GPU not properly plugged into the connector, damaged pins, dirt in the connector).

3

Thank you very much.

Turns out that the board was shifted a slot from where it was supposed to be and was in fact in a PCIE 2.0 1x slot. The strange thing is that it has been working nicely as a video board since last January in that slot. Now it’s passing bandwidthtest at better than 12000.

Thank you again.