OCPC RTX 3090

Graphics Card OCPC RTX 3090 — Specifications, Tests & Benchmarks
NVIDIA

OCPC RTX 3090

Nvidia GeForce 30 GA102 01.09.2020 24 GB GDDR6X 384 bit 350W
🏆 Top #1706
Performance
Synthetic Score
26,561
PassMark
26,561
Efficiency
enthusiast
0 перегляди
0 порівняння
0 гри
0 користувачі
0 коментарі
0 закладки
The OCPC RTX 3090 graphics card from NVIDIA is built on the Ampere architecture and was officially introduced on 01.09.2020. The graphics processor is manufactured using a modern process. The 628 mm² die contains approximately 28.3 billion transistorsistors transistors. For graphics processing, 10496 shader units are provided. The technological equipment is complemented by 82 RT Cores and 328 Tensor Cores. The GDDR6X video memory capacity is 24 GB. Thanks to the 384 bit-bit bus, bandwidth reaches 936.20 GB/s, eliminating delays when working with demanding textures. The GPU's base clock speed is 1395 MHz, and in Boost mode, it can automatically increase up to 1695 MHz. The card's power consumption (TDP) is stated at 350 W. The manufacturer recommends using a power supply unit with a wattage of at least 750 W.

General Information

Release Date 01.09.2020
Usage Class Hardcore Gaming
Market Segment Desktop
Series Nvidia GeForce 30
GPU Variant GA102-300-A1

GPU

Architecture Ampere
Codename GA102
Process Node 8 nm (Samsung)
Transistor Count 28,300,000.0 million
Die Size 628 mm²
Transistor Density 45,100,000 million / mm²

Rendering Configuration

Shading Units (ALU) 10496
Texture Mapping Units (TMU) 328
Render Output Units (ROP) 112
Tensor Cores 328
RT Cores (Ray Tracing) 82
Compute Units (SM/CU) 82

Clock Speeds

Base Clock 1395 MHz
Boost Clock 1695 MHz
Memory Clock (Actual) 1219 MHz
Memory Clock (Effective) 19500 MHz

Memory

Memory Capacity 24 GB
Memory Type GDDR6X
Memory Bus 384 bit bit
Memory Bandwidth 936.20 GB/s

Cache Memory

L1 Cache 10496 KB
L2 Cache 6 MB

Board Design & Power

Interface PCIe 4.0 x16
Slot Width 2
Dimensions (L x W x H) 336 x 61 x 140 mm
Power Consumption (TDP) 350 W
Recommended PSU 750 W
Power Connectors 2x 8-pin
Board Number PG132 SKU 10

API Support

DirectX 12 Ultimate (12_2)
OpenGL 4.6
OpenCL
Vulkan 1.4
CUDA
Shader Model

Theoretical Performance

Pixel Fill Rate 189.8 GPixel/s
Texture Fill Rate 556 GTexel/s
FP16 Performance (Half) 35.58 TFLOPS (1:1)
FP32 Performance (Float) 35.58 TFLOPS
FP64 Performance (Double) 556 GFLOPS (1:64)

Synthetic Tests & Benchmarks

PassMark (G3D Mark) 26 561
PassMark (G2D Mark) 1 068
TPU Index Score 43.96%
Performance Tier enthusiast

How this graphics card performs in games

Всі тести
Тестів поки немає.

Comments

0

Please log in to your account to leave a comment.

Log In or Register

No comments yet. Be the first to comment!

Compare with another graphics card

Швидка навігація

We Use Cookies 🍪

This site uses cookies to enhance your user experience. By continuing to browse, you agree to our Privacy Policy.
By continuing to use this site, you agree to our Terms of Service and Privacy Policy.