EVGA GT 640 4 GB
Graphics Card EVGA GT 640 4 GB — Specifications, Tests & Benchmarks
EVGA GT 640 4 GB
Nvidia GeForce 600
•
GK107
•
05.06.2012
•
4 GB
•
DDR3
•
128 bit
•
65W
🏆 Top #12115
Performance
Synthetic Score
1,166
PassMark
1,166
Efficiency
low
The EVGA GT 640 4 GB graphics adapter is based on the advanced Kepler architecture. NVIDIA announced this model on 05.06.2012. At the core of the card is a chip created with modern lithography. The die houses 1.3 billion transistorsistors transistors, and its area is 118 mm². The core configuration includes 384 shader units, 0 RT Cores for ray tracing, and 0 Tensor Cores for AI tasks. The graphics card is equipped with 4 GB of DDR3 memory. A 128 bit-bit bus is used, providing bandwidth at 28.51 GB/s. In standard mode, the core operates at 902 MHz, but auto-overclocking technology allows it to reach 0 MHz under load. The nominal thermal design power is 65 W. For stable system operation, a PSU of 250 W or more will be required.
General Information
| Release Date | 05.06.2012 |
| Usage Class | Office Use |
| Market Segment | Desktop |
| Series | Nvidia GeForce 600 |
| GPU Variant | GK107-300-A2 |
GPU
| Architecture | Kepler |
| Codename | GK107 |
| Process Node | 28 nm (TSMC) |
| Transistor Count | 1,270,000.0 million |
| Die Size | 118 mm² |
| Transistor Density | 10,800,000 million / mm² |
Rendering Configuration
| Shading Units (ALU) | 384 |
| Texture Mapping Units (TMU) | 32 |
| Render Output Units (ROP) | 16 |
Clock Speeds
| Base Clock | 902 MHz |
| Memory Clock (Actual) | 891 MHz |
| Memory Clock (Effective) | 1782 MHz |
Memory
| Memory Capacity | 4 GB |
| Memory Type | DDR3 |
| Memory Bus | 128 bit bit |
| Memory Bandwidth | 28.51 GB/s |
Cache Memory
| L1 Cache | 16 KB |
| L2 Cache | 256 KB |
Board Design & Power
| Interface | PCIe 3.0 x16 |
| Slot Width | 1 |
| Dimensions (L x W x H) | |
| Power Consumption (TDP) | 65 W |
| Recommended PSU | 250 W |
| Board Number | P2011 SKU 0 |
API Support
| DirectX | 12 (11_0) |
| OpenGL | 4.6 |
| OpenCL | |
| Vulkan | 1.2 |
| CUDA | |
| Shader Model |
Theoretical Performance
| Pixel Fill Rate | 7.216 GPixel/s |
| Texture Fill Rate | 28.86 GTexel/s |
| FP32 Performance (Float) | 384.7 GFLOPS |
| FP64 Performance (Double) | 57.7 GFLOPS (1:24) |
Synthetic Tests & Benchmarks
| PassMark (G3D Mark) | 1 166 |
| PassMark (G2D Mark) | 299 |
| TPU Index Score | 1.42% |
| Performance Tier | low |
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.