Gainward RTX 3090 Phoenix GS
Graphics Card Gainward RTX 3090 Phoenix GS — Specifications, Tests & Benchmarks
Gainward RTX 3090 Phoenix GS
Nvidia GeForce 30
•
GA102
•
01.09.2020
•
24 GB
•
GDDR6X
•
384 bit
•
350W
🏆 Top #1576
Performance
Synthetic Score
27,031
PassMark
26,561
Efficiency
enthusiast
The Gainward RTX 3090 Phoenix GS graphics card from NVIDIA is built on the Ampere architecture and was officially introduced on 01.09.2020. Thanks to modern manufacturing technology, engineers managed to place 28.3 billion transistorsistors transistors on a 628 mm² die. The core configuration includes 10496 shader units, 82 RT Cores for ray tracing, and 328 Tensor Cores for AI tasks. 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 graphics chip operates at a base clock of 1395 MHz with dynamic acceleration capability up to 1725 MHz. The nominal thermal design power is 350 W. For stable system operation, a PSU of 750 W or more will be required.
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 | 1725 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 | 3 |
| Dimensions (L x W x H) | 294 x 61 x 112 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 | 193.2 GPixel/s |
| Texture Fill Rate | 565.8 GTexel/s |
| FP16 Performance (Half) | 36.21 TFLOPS (1:1) |
| FP32 Performance (Float) | 36.21 TFLOPS |
| FP64 Performance (Double) | 565.8 GFLOPS (1:64) |
Synthetic Tests & Benchmarks
| PassMark (G3D Mark) | 26 561 |
| PassMark (G2D Mark) | 1 068 |
| TPU Index Score | 44.74% |
| Performance Tier | enthusiast |
Всі тести
Тестів поки немає.
Comments
0Please log in to your account to leave a comment.
Log In or RegisterNo comments yet. Be the first to comment!
Are you sure you want to delete this comment? This action cannot be undone.