NVIDIA Tesla P40

NVIDIA Tesla P40

About GPU

The NVIDIA Tesla P40 GPU is a powerhouse of a professional platform, designed to handle the most demanding computational tasks with ease. With a base clock speed of 1303MHz and a boost clock speed of 1531MHz, this GPU delivers exceptional performance for a wide range of applications. The 24GB of GDDR5X memory and a memory clock speed of 1808MHz ensure that the P40 can handle large datasets and complex simulations with ease. The 3840 shading units and 3MB of L2 cache further contribute to its impressive performance, allowing for fast and efficient processing of complex calculations. With a TDP of 250W and a theoretical performance of 11.76 TFLOPS, the P40 is a reliable and powerful GPU for professional workloads. Whether you're working with deep learning, scientific simulations, or graphic design, the P40 has the capabilities to handle it all. One of the standout features of the P40 is its ability to support multiple virtual desktops, making it an ideal choice for virtualized environments. This versatility allows for greater flexibility in deployment, making it a valuable asset in a professional setting. Overall, the NVIDIA Tesla P40 GPU is a high-performance and reliable option for professionals in need of a powerful computing solution. Its impressive specs and versatile capabilities make it well-suited for a variety of demanding applications.

Basic

Label Name
NVIDIA
Platform
Professional
Launch Date
September 2016
Model Name
Tesla P40
Generation
Tesla Pascal
Base Clock
1303MHz
Boost Clock
1531MHz
Bus Interface
PCIe 3.0 x16

Memory Specifications

Memory Size
24GB
Memory Type
GDDR5X
Memory Bus
?
The memory bus width refers to the number of bits of data that the video memory can transfer within a single clock cycle. The larger the bus width, the greater the amount of data that can be transmitted instantaneously, making it one of the crucial parameters of video memory. The memory bandwidth is calculated as: Memory Bandwidth = Memory Frequency x Memory Bus Width / 8. Therefore, when the memory frequencies are similar, the memory bus width will determine the size of the memory bandwidth.
384bit
Memory Clock
1808MHz
Bandwidth
?
Memory bandwidth refers to the data transfer rate between the graphics chip and the video memory. It is measured in bytes per second, and the formula to calculate it is: memory bandwidth = working frequency × memory bus width / 8 bits.
694.3 GB/s

Theoretical Performance

Pixel Rate
?
Pixel fill rate refers to the number of pixels a graphics processing unit (GPU) can render per second, measured in MPixels/s (million pixels per second) or GPixels/s (billion pixels per second). It is the most commonly used metric to evaluate the pixel processing performance of a graphics card.
147.0 GPixel/s
Texture Rate
?
Texture fill rate refers to the number of texture map elements (texels) that a GPU can map to pixels in a single second.
367.4 GTexel/s
FP16 (half)
?
An important metric for measuring GPU performance is floating-point computing capability. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy.
183.7 GFLOPS
FP64 (double)
?
An important metric for measuring GPU performance is floating-point computing capability. Double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy, while single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
367.4 GFLOPS
FP32 (float)
?
An important metric for measuring GPU performance is floating-point computing capability. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
11.995 TFLOPS

Miscellaneous

SM Count
?
Multiple Streaming Processors (SPs), along with other resources, form a Streaming Multiprocessor (SM), which is also referred to as a GPU's major core. These additional resources include components such as warp schedulers, registers, and shared memory. The SM can be considered the heart of the GPU, similar to a CPU core, with registers and shared memory being scarce resources within the SM.
30
Shading Units
?
The most fundamental processing unit is the Streaming Processor (SP), where specific instructions and tasks are executed. GPUs perform parallel computing, which means multiple SPs work simultaneously to process tasks.
3840
L1 Cache
48 KB (per SM)
L2 Cache
3MB
TDP
250W
Vulkan Version
?
Vulkan is a cross-platform graphics and compute API by Khronos Group, offering high performance and low CPU overhead. It lets developers control the GPU directly, reduces rendering overhead, and supports multi-threading and multi-core processors.
1.3
OpenCL Version
3.0

Benchmarks

FP32 (float)
Score
11.995 TFLOPS
Blender
Score
802
OctaneBench
Score
163

Compared to Other GPU

FP32 (float) / TFLOPS
12.044 +0.4%
12.036 +0.3%
11.995
11.985 -0.1%
Blender
807 +0.6%
802
OctaneBench
180 +10.4%
176 +8%
163
159 -2.5%