GeekRadar / The comparison desk

COMPARE.

GPU

Unspecified

Tesla T40 24 GB

Graphics processor

Video memory: 24 GB^*
Memory bus: 384 bit^*
Rated memory bandwidth: 624 GB/s^*

Graphics & compute benchmarks

Archived cohort medians

GFXBench, GLBenchmark and CompuBench results retain the tested system, API, operating system and resolution. Offscreen tests fix the render resolution; onscreen results also reflect the display workload. These historical submissions do not establish performance in current games.

4K Aztec Ruins High Tier OffscreenWindows / DirectX 12 / 3840 x 2160 / offscreen · fps

Higher is better.

Tesla T40 24 GB

148.17^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

4K Aztec Ruins High Tier OffscreenWindows / DirectX 12 / 3840 x 2160 / offscreen · fps

Higher is better.

Tesla T40 24 GB

154.22^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

Aztec Ruins High Tier OffscreenWindows / DirectX 12 / 2560 x 1440 / offscreen · fps

Higher is better.

Tesla T40 24 GB

267.05^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

Aztec Ruins High Tier OffscreenWindows / DirectX 12 / 2560 x 1440 / offscreen · fps

Higher is better.

Tesla T40 24 GB

264.01^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

Aztec Ruins Normal Tier OffscreenWindows / DirectX 12 / 1920 x 1080 / offscreen · fps

Higher is better.

Tesla T40 24 GB

403.99^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

Aztec Ruins Normal Tier OffscreenWindows / DirectX 12 / 1920 x 1080 / offscreen · fps

Higher is better.

Tesla T40 24 GB

402.02^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

Aztec Ruins High TierWindows / DirectX 12 / 1920 x 1200 / onscreen · fps

Higher is better.

Tesla T40 24 GB

240.05^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

Aztec Ruins High TierWindows / DirectX 12 / 2560 x 1600 / onscreen · fps

Higher is better.

Tesla T40 24 GB

59.70^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

Aztec Ruins Normal TierWindows / DirectX 12 / 1920 x 1200 / onscreen · fps

Higher is better.

Tesla T40 24 GB

363.28^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

Aztec Ruins Normal TierWindows / DirectX 12 / 2560 x 1600 / onscreen · fps

Higher is better.

Tesla T40 24 GB

59.90^* fps

NVIDIA Tesla t40 24 GB

Host configuration not reported.

Median results, not the best run. Sample counts and individual test dates are unreported. Different systems using the same GPU remain separate configurations.

Processing & platform

Architecture: Turing^*
Process node: 12 nm^*
GPU cores: 4,608^*
GPU base clock: 1,305 MHz^*
Graphics interface: PCIe 3.0 x16^*
Reported chip die area: 754 mm²^*
Transistors: 18,600 million^*
GPU L2 cache: 6 MB^*
Graphics processor: TU102^*
Texture mapping units: 288^*
Raster output units: 96^*
Streaming multiprocessors: 72^*
Tensor cores: 576^*
Ray tracing cores: 72^*
Chip foundry: TSMC^*
Card or module format: Dual-slot^*
Declared GPU TDP: 250 W^*
Suggested system PSU: 600 W^*
External power connectors: 1x 8-pin^*
DirectX / feature level: 12 Ultimate (12_2)^*
OpenGL: 4.6^*
OpenCL: 3.0^*
Vulkan: 1.4^*
CUDA compute capability: 7.5^*
Shader model: 6.9^*

Memory & storage

Memory options: 24^*
Video memory: 24 GB^*
Video memory type: GDDR6^*
Memory bus: 384 bit^*
Rated memory bandwidth: 624 GB/s^*

Power specifications

Thermal design power: 250 W^*

System configuration

Detailed specifications

Specifications 1 · 30 fields

proc transistors: 18,600 million^*
proc die size: 754^* mm²
cores: 4,608^*
tensor cores: 576^*
rt cores: 72^*
sm count: 72^*
base clock: 1,305^*
boost clock: 1,560^*
memory clock: 1,625^*
ram: 24^*
name: NVIDIA Tesla T40 24 GB^*
ram type: GDDR6^*
bus width: 384^*
bus interface: PCIe 3.0 x16^*
ram bandwidth: 624^* GB/s
fp16 performance: 28.75^*
fp32 performance: 14.38^*
fp64 performance: 0.4493^*
tdp: 250^* W
suggested psu: 600^* W
slot width: Dual-slot^*
power connectors: 1x 8-pin^*
api cuda: 7.5^*
is retail board: No^*
gpi value: 11.13^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Turing^*
proc foundry: TSMC^*
proc process size: 12^* nm

Specifications 2 · 40 fields

CUDA compute capability

7.5^*

DirectX / feature level

12 Ultimate (12_2)^*

OpenCL

3.0^*

OpenGL

4.6^*

Shader model

6.9^*

Vulkan

1.4^*

Architecture

Turing^*

Graphics interface

PCIe 3.0 x16^*

Memory bus

384^* bit

Reported shader processors

4,608^*

Reported theoretical FP16 peak

28.75^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

14.38^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.4493^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

64 KB (per SM)^*

Declared GPU L2 cache

6 MB^*

Reported display outputs

No outputs^*

Theoretical pixel fill rate

149.8 GPixel/s^*

External power connectors

1x 8-pin^*

Reported chip die area

754 mm²^*

Chip foundry

TSMC^*

Process node declaration

12 nm^*

Transistors

18,600 million^*

Graphics processor

TU102^*

Reported video memory

24^* GB

Rated memory bandwidth

624.0 GB/s^*

Video memory type

GDDR6^*

Raster output units

96^*

Ray tracing cores

72^*

Reported shading units

4,608^*

Card or module format

Dual-slot^*

Streaming multiprocessors

72^*

Suggested system PSU

600 W^*

2:4 tensor sparsity

No^*

Declared GPU TDP

250 W^*

Tensor cores

576^*

Theoretical texture fill rate

449.3 GTexel/s^*

Texture mapping units

288^*

GPU cores

4,608^*

Video memory

24^* GB

Video memory type

GDDR6^*

Specifications 3 · 7 fields

Product Name: Tesla T40 24 GB^*
GPU Chip: TU102^*
Bus: PCIe 3.0 x16^*
Memory: 24 GB, GDDR6, 384 bit^*
GPU clock: 1,305^* MHz
Memory clock: 1,625^* MHz
Shaders / TMUs / ROPs: 4608 / 288 / 96^*

* Provisional data