GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA P106-090

Graphics processor

Video memory: 3 GB^*
Memory bus: 192 bit^*
Rated memory bandwidth: 192.20 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.

1080p ALU 2 OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

NVIDIA P106-090

422.16^* fps

NVIDIA P106-090

Host configuration not reported.

1080p Driver Overhead 2 OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

NVIDIA P106-090

61.44^* fps

NVIDIA P106-090

Host configuration not reported.

1080p Manhattan 3.1 OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

NVIDIA P106-090

153.97^* fps

NVIDIA P106-090

Host configuration not reported.

1080p Manhattan OffscreenWindows / DirectX / 1920 x 1080 / offscreen · fps

Higher is better.

NVIDIA P106-090

301.59^* fps

NVIDIA P106-090

Host configuration not reported.

1080p Manhattan OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

NVIDIA P106-090

149.55^* fps

NVIDIA P106-090

Host configuration not reported.

1080p T-Rex OffscreenWindows / DirectX / 1920 x 1080 / offscreen · fps

Higher is better.

NVIDIA P106-090

523.70^* fps

NVIDIA P106-090

Host configuration not reported.

1080p T-Rex OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · fps

Higher is better.

NVIDIA P106-090

391.83^* fps

NVIDIA P106-090

Host configuration not reported.

1080p Texturing OffscreenWindows / OpenGL / 1920 x 1080 / offscreen · MTexels/s

Higher is better.

NVIDIA P106-090

51,126^* MTexels/s

NVIDIA P106-090

Host configuration not reported.

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

Higher is better.

NVIDIA P106-090

24.00^* fps

NVIDIA P106-090

Host configuration not reported.

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

Higher is better.

NVIDIA P106-090

24.49^* fps

NVIDIA P106-090

Host configuration not reported.

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

Higher is better.

NVIDIA P106-090

28.10^* fps

NVIDIA P106-090

Host configuration not reported.

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

Higher is better.

NVIDIA P106-090

58.01^* fps

NVIDIA P106-090

Host configuration not reported.

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

Higher is better.

NVIDIA P106-090

56.34^* fps

NVIDIA P106-090

Host configuration not reported.

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

Higher is better.

NVIDIA P106-090

65.61^* fps

NVIDIA P106-090

Host configuration not reported.

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

Higher is better.

NVIDIA P106-090

153.74^* fps

NVIDIA P106-090

Host configuration not reported.

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

Higher is better.

NVIDIA P106-090

146.43^* fps

NVIDIA P106-090

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.

Benchmark results

Geekbench GPU (reported compilation) · version unreported · OpenCL21,280^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · Vulkan18,895^*Platform unreported Compare results

Processing & platform

Architecture: Pascal^*
Process node: 16 nm^*
GPU cores: 768^*
Reported GPU frequency: 1,354 MHz^*
Graphics interface: PCIe 1.0 x1^*
Reported chip die area: 200 mm²^*
Chip/package TDP: 75 W^*
Transistors: 4,400 million^*
Graphics processor: GP106^*
Texture mapping units: 48^*
Raster output units: 48^*
Streaming multiprocessors: 6^*
Chip foundry: TSMC^*
Card or module format: Dual-slot^*
Declared GPU TDP: 75 W^*
Suggested system PSU: 250 W^*
External power connectors: 1x 6-pin^*
DirectX / feature level: 12 (12_1)^*
OpenGL: 4.6^*
OpenCL: 3.0^*
Vulkan: 1.4^*
CUDA compute capability: 6.1^*
Shader model: 6.8^*
GPU L2 cache: 1,536 KB^*

Memory & storage

Memory options: 3^*
Video memory: 3 GB^*
Video memory type: GDDR5^*
Memory bus: 192 bit^*
Rated memory bandwidth: 192.20 GB/s^*

Power specifications

Thermal design power: 75 W^*

System configuration

Detailed specifications

Specifications 1 · 13 fields

Foundry: TSMC^*
Vendor: NVIDIA^*
FP16 GFLOPS: 36.74^* GFLOPS
FP32 GFLOPS: 2,352^* GFLOPS
FP64 GFLOPS: 73.49^* GFLOPS
Product: NVIDIA P106-090^*
Type: GPU^*
Release Date: 2017-07-31^*
Process Size (nm): 16^* nm
TDP (W): 75^* W
Die Size (mm^2): 200^* mm²
Transistors (million): 4,400^*
Freq (MHz): 1,354^* MHz

Specifications 2 · 29 fields

proc transistors: 4,400 million^*
proc die size: 200^* mm²
cores: 768^*
sm count: 6^*
base clock: 1,354^*
boost clock: 1,531^*
memory clock: 2,002^*
ram: 3^*
name: NVIDIA P106-090^*
ram type: GDDR5^*
bus width: 192^*
bus interface: PCIe 1.0 x1^*
ram bandwidth: 192.2^* GB/s
fp16 performance: 0.0367^*
fp32 performance: 2.352^*
fp64 performance: 0.0735^*
tdp: 75^* W
suggested psu: 250^* W
slot width: Dual-slot^*
power connectors: 1x 6-pin^*
api cuda: 6.1^*
is retail board: No^*
gpi value: 2.22^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Pascal^*
card release date: 2017-07-31^*
proc foundry: TSMC^*
proc process size: 16^* nm

Specifications 3 · 38 fields

CUDA compute capability

6.1^*

DirectX / feature level

12 (12_1)^*

OpenCL

3.0^*

OpenGL

4.6^*

Shader model

6.8^*

Vulkan

1.4^*

Architecture

Pascal^*

Graphics interface

PCIe 1.0 x1^*

Memory bus

192^* bit

Reported shader processors

768^*

Reported theoretical FP16 peak

0.0367^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

2.352^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.0735^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

48 KB (per SM)^*

Declared GPU L2 cache

1536 KB^*

Reported display outputs

No outputs^*

Theoretical pixel fill rate

73.49 GPixel/s^*

External power connectors

1x 6-pin^*

Reported chip die area

200 mm²^*

Chip foundry

TSMC^*

Process node declaration

16 nm^*

Transistors

4,400 million^*

Graphics processor

GP106^*

Reported video memory

3^* GB

Rated memory bandwidth

192.2 GB/s^*

Video memory type

GDDR5^*

Raster output units

48^*

Reported shading units

768^*

Card or module format

Dual-slot^*

Streaming multiprocessors

6^*

Suggested system PSU

250 W^*

2:4 tensor sparsity

No^*

Declared GPU TDP

75 W^*

Theoretical texture fill rate

73.49 GTexel/s^*

Texture mapping units

48^*

GPU cores

768^*

Video memory

3^* GB

Video memory type

GDDR5^*

Specifications 4 · 3 fields

Device

NVIDIA P106-090^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

OpenCL

21,280^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Vulkan

18,895^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

* Provisional data