NVIDIA’s new Tesla P100 PCI-E GPU is a big step up for HPC users, and for GPU users in general. Although other workloads have been leveraging the newer “Maxwell” architecture, HPC applications have been using “Kepler” GPUs for a couple years. The new GPUs bring many improvements, including higher performance, faster connectivity, and more flexibility for users & programmers.
Because GPUs have proven themselves so well, there are now GPUs optimized for particular applications. For example, a video transcoding project would be unlikely to use the same GPU as a computational chemistry project. However, the Tesla P100 serves as the best all-round choice for those who need to support a variety of applications. With that in mind, there are three separate paths to be considered:
- Tesla P100 PCI-E GPUs (this post)
- Tesla P100 NVLink GPUs (with PCI-E connectivity to the host)
- Tesla P100 NVLink GPUs (with NVLink connectivity to the host)
Highlights of the new Tesla P100 PCI-E GPUs include:
- Up to 4.7 TFLOPS double- and 9.3 TFLOPS single-precision floating-point performance
- 16GB of on-die HBM2 CoWoS GPU memory, with bandwidths up to 732GB/s
- High-speed, on-die GPU memory provides a 3X improvement over older GPUs
- Pascal Unified Memory allows applications to directly access the memory of all GPUs and all of system memory
Improved Data Transfer Speeds
Although the Tesla P100 GPU uses the same generation of PCI-E connectivity, some optimizations have been made since the Kepler generation. With P100, you will be able to achieve transfers up to ~12.8GB/s between the host and the GPU:
[root@node6 ~]# ./bandwidthTest --memory=pinned --device=0 [CUDA Bandwidth Test] - Starting... Running on... Device 0: Tesla P100-PCIE-16GB Quick Mode Host to Device Bandwidth, 1 Device(s) PINNED Memory Transfers Transfer Size (Bytes) Bandwidth(MB/s) 33554432 11688.2 Device to Host Bandwidth, 1 Device(s) PINNED Memory Transfers Transfer Size (Bytes) Bandwidth(MB/s) 33554432 12886.0 Device to Device Bandwidth, 1 Device(s) PINNED Memory Transfers Transfer Size (Bytes) Bandwidth(MB/s) 33554432 444927.2* Result = PASS
* Note that there is also a 12GB version of the Tesla P100 PCI-E GPU – the memory operates 25% slower
Technical Details
Below are the technical details reported by nvidia-smi. Note that “Pascal” Tesla GPUs now include fully integrated memory ECC support that is always enabled (memory performance in previous generations could be improved by disabling ECC).
[root@node6 ~]# nvidia-smi -a -i 0
==============NVSMI LOG==============
Timestamp : Wed Sep 28 11:03:51 2016
Driver Version : 367.44
Attached GPUs : 1
GPU 0000:02:00.0
Product Name : Tesla P100-PCIE-16GB
Product Brand : Tesla
Display Mode : Disabled
Display Active : Disabled
Persistence Mode : Enabled
Accounting Mode : Enabled
Accounting Mode Buffer Size : 1920
Driver Model
Current : N/A
Pending : N/A
Serial Number : 032301607xxxx
GPU UUID : GPU-de136156-7f6d-ced1-869c-4dc56e09xxxx
Minor Number : 1
VBIOS Version : 86.00.26.00.01
MultiGPU Board : No
Board ID : 0x200
GPU Part Number : 900-2H400-0000-000
Inforom Version
Image Version : H400.0201.00.06
OEM Object : 1.1
ECC Object : 4.1
Power Management Object : N/A
GPU Operation Mode
Current : N/A
Pending : N/A
GPU Virtualization Mode
Virtualization mode : None
PCI
Bus : 0x02
Device : 0x00
Domain : 0x0000
Device Id : 0x15F810DE
Bus Id : 0000:02:00.0
Sub System Id : 0x118F10DE
GPU Link Info
PCIe Generation
Max : 3
Current : 3
Link Width
Max : 16x
Current : 16x
Bridge Chip
Type : N/A
Firmware : N/A
Replays since reset : 0
Tx Throughput : 0 KB/s
Rx Throughput : 0 KB/s
Fan Speed : N/A
Performance State : P0
Clocks Throttle Reasons
Idle : Active
Applications Clocks Setting : Not Active
SW Power Cap : Not Active
HW Slowdown : Not Active
Sync Boost : Not Active
Unknown : Not Active
FB Memory Usage
Total : 16276 MiB
Used : 0 MiB
Free : 16276 MiB
BAR1 Memory Usage
Total : 16384 MiB
Used : 2 MiB
Free : 16382 MiB
Compute Mode : Default
Utilization
Gpu : 0 %
Memory : 0 %
Encoder : 0 %
Decoder : 0 %
Ecc Mode
Current : Enabled
Pending : Enabled
ECC Errors
Volatile
Single Bit
Device Memory : 0
Register File : 0
L1 Cache : N/A
L2 Cache : 0
Texture Memory : 0
Texture Shared : 0
Total : 0
Double Bit
Device Memory : 0
Register File : 0
L1 Cache : N/A
L2 Cache : 0
Texture Memory : 0
Texture Shared : 0
Total : 0
Aggregate
Single Bit
Device Memory : 0
Register File : 0
L1 Cache : N/A
L2 Cache : 0
Texture Memory : 0
Texture Shared : 0
Total : 0
Double Bit
Device Memory : 0
Register File : 0
L1 Cache : N/A
L2 Cache : 0
Texture Memory : 0
Texture Shared : 0
Total : 0
Retired Pages
Single Bit ECC : 0
Double Bit ECC : 0
Pending : No
Temperature
GPU Current Temp : 36 C
GPU Shutdown Temp : 85 C
GPU Slowdown Temp : 82 C
Power Readings
Power Management : Supported
Power Draw : 26.39 W
Power Limit : 250.00 W
Default Power Limit : 250.00 W
Enforced Power Limit : 250.00 W
Min Power Limit : 125.00 W
Max Power Limit : 250.00 W
Clocks
Graphics : 405 MHz
SM : 405 MHz
Memory : 715 MHz
Video : 835 MHz
Applications Clocks
Graphics : 1328 MHz
Memory : 715 MHz
Default Applications Clocks
Graphics : 1189 MHz
Memory : 715 MHz
Max Clocks
Graphics : 1328 MHz
SM : 1328 MHz
Memory : 715 MHz
Video : 1328 MHz
Clock Policy
Auto Boost : N/A
Auto Boost Default : N/A
Processes : None
The latest NVIDIA GPU architectures support large numbers of clock speeds, as well as automated boosting of the clock speed (when power and thermals allow). Administrators can also set specific power consumption limits and monitor the clock speeds (including explanations for any reasons the clocks are running at a lower speed).
[root@node6 ~]# nvidia-smi -q -d SUPPORTED_CLOCKS -i 0
==============NVSMI LOG==============
Timestamp : Wed Sep 28 11:05:36 2016
Driver Version : 367.44
Attached GPUs : 2
GPU 0000:02:00.0
Supported Clocks
Memory : 715 MHz
Graphics : 1328 MHz
Graphics : 1316 MHz
Graphics : 1303 MHz
Graphics : 1290 MHz
Graphics : 1278 MHz
Graphics : 1265 MHz
Graphics : 1252 MHz
Graphics : 1240 MHz
Graphics : 1227 MHz
Graphics : 1215 MHz
Graphics : 1202 MHz
Graphics : 1189 MHz
Graphics : 1177 MHz
Graphics : 1164 MHz
Graphics : 1151 MHz
Graphics : 1139 MHz
Graphics : 1126 MHz
Graphics : 1113 MHz
Graphics : 1101 MHz
Graphics : 1088 MHz
Graphics : 1075 MHz
Graphics : 1063 MHz
Graphics : 1050 MHz
Graphics : 1037 MHz
Graphics : 1025 MHz
Graphics : 1012 MHz
NVIDIA deviceQuery on Tesla P100 PCI-E 16GB GPU
Each new GPU generation brings tweaks to the design. The output below, from the CUDA 8.0 SDK samples, shows additional details of the architecture and capabilities of the “Pascal” Tesla P100 PCI-E GPU accelerators. Take note of the new Compute Capability 6.0, which is what you’ll want to target if you’re compiling your own CUDA code.
./deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s)
Device 0: "Tesla P100-PCIE-16GB"
CUDA Driver Version / Runtime Version 8.0 / 8.0
CUDA Capability Major/Minor version number: 6.0
Total amount of global memory: 16276 MBytes (17066885120 bytes)
(56) Multiprocessors, ( 64) CUDA Cores/MP: 3584 CUDA Cores
GPU Max Clock rate: 405 MHz (0.41 GHz)
Memory Clock rate: 715 Mhz
Memory Bus Width: 4096-bit
L2 Cache Size: 4194304 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: No
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Enabled
Device supports Unified Addressing (UVA): Yes
Device PCI Domain ID / Bus ID / location ID: 0 / 2 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 8.0, CUDA Runtime Version = 8.0, NumDevs = 1, Device0 = Tesla P100-PCIE-16GB
Result = PASS
Additional Information on Tesla P100 PCI-E GPUs
To learn more about the available P100 GPUs and to compare with other versions of the Tesla product line, please review our “Pascal” Tesla GPU knowledge center article:
If you’re thinking about using GPUs for the first time, please consider getting in touch with us. We’ve been implementing GPU-accelerated systems for nearly a decade and have the expertise to help make your project a success!
If you’re thinking about upgrading to P100, have a look at our list of P100 GPU-accelerated systems. You may also wish to review our posts on NVLink-connected Tesla P100 GPUs. If you’re hoping to install Tesla P100 PCI-E GPUs in your existing systems, take note that you’ll need a compatible server platform – one of our experts can help you review.
