Inno3D iChill RTX 4090 FROSTBITE PRO
Graphics Card Inno3D iChill RTX 4090 FROSTBITE PRO — Specifications, Tests & Benchmarks
Inno3D iChill RTX 4090 FROSTBITE PRO
Nvidia GeForce 40
•
AD102
•
20.09.2022
•
24 GB
•
GDDR6X
•
384 bit
•
450W
🏆 Top #333
Performance
Synthetic Score
38,090
PassMark
38,090
Efficiency
enthusiast
The Inno3D iChill RTX 4090 FROSTBITE PRO graphics adapter is based on the advanced Ada Lovelace architecture. NVIDIA announced this model on 20.09.2022. The graphics processor is manufactured using a modern process. The 609 mm² die contains approximately 76.3 billion transistorsistors transistors. For graphics processing, 16384 shader units are provided. The technological equipment is complemented by 128 RT Cores and 512 Tensor Cores. The memory subsystem features GDDR6X modules with a total capacity of 24 GB. The bus width is 384 bit bits, and the peak data exchange rate is 1034.24 GB/s. In standard mode, the core operates at 2235 MHz, but auto-overclocking technology allows it to reach 2520 MHz under load. The card's power consumption (TDP) is stated at 450 W. The manufacturer recommends using a power supply unit with a wattage of at least 850 W.
General Information
| Release Date | 20.09.2022 |
| Usage Class | Hardcore Gaming |
| Market Segment | Desktop |
| Series | Nvidia GeForce 40 |
| GPU Variant | AD102-300-A1 |
GPU
| Architecture | Ada Lovelace |
| Codename | AD102 |
| Process Node | 5 nm (TSMC) |
| Transistor Count | 76,300,000.0 million |
| Die Size | 609 mm² |
| Transistor Density | 125,300,000 million / mm² |
Rendering Configuration
| Shading Units (ALU) | 16384 |
| Texture Mapping Units (TMU) | 512 |
| Render Output Units (ROP) | 176 |
| Tensor Cores | 512 |
| RT Cores (Ray Tracing) | 128 |
| Compute Units (SM/CU) | 128 |
Clock Speeds
| Base Clock | 2235 MHz |
| Boost Clock | 2520 MHz |
| Memory Clock (Actual) | 1313 MHz |
| Memory Clock (Effective) | 21000 MHz |
Memory
| Memory Capacity | 24 GB |
| Memory Type | GDDR6X |
| Memory Bus | 384 bit bit |
| Memory Bandwidth | 1034.24 GB/s |
Cache Memory
| L1 Cache | 16384 KB |
| L2 Cache | 72 MB |
Board Design & Power
| Interface | PCIe 4.0 x16 |
| Slot Width | 1 |
| Dimensions (L x W x H) | 208 x 23 x 134 mm |
| Power Consumption (TDP) | 450 W |
| Recommended PSU | 850 W |
| Power Connectors | 1x 16-pin |
| Board Number | PG139 SKU 330 |
API Support
| DirectX | 12 Ultimate (12_2) |
| OpenGL | 4.6 |
| OpenCL | |
| Vulkan | 1.4 |
| CUDA | |
| Shader Model |
Theoretical Performance
| Pixel Fill Rate | 443.5 GPixel/s |
| Texture Fill Rate | 290.2 GTexel/s |
| FP16 Performance (Half) | 82.58 TFLOPS (1:1) |
| FP32 Performance (Float) | 82.58 TFLOPS |
| FP64 Performance (Double) | 290.2 GFLOPS (1:64) |
Synthetic Tests & Benchmarks
| PassMark (G3D Mark) | 38 090 |
| PassMark (G2D Mark) | 1 303 |
| TPU Index Score | 76.27% |
| Performance Tier | enthusiast |
How this graphics card performs in games
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.