Product Compare
AMD Radeon Instinct MI325X vs NVIDIA Tesla M40
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Oct 2024 | Nov 2015 |
| Generation | Radeon Instinct | Tesla Maxwell |
| Type | Professional | Professional |
| Bus Interface | PCIe 5.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 1000 MHz | 948 MHz |
| Boost Clock | 2100 MHz | 1112 MHz |
| Memory Clock | 1500 MHz | 1502 MHz |
| Memory | ||
| Memory Size | 256GB | 12GB |
| Memory Type | HBM3e | GDDR5 |
| Memory Bus | 8192bit | 384bit |
| Bandwidth | 6.14TB/s | 288.4GB/s |
| Render Config | ||
| Compute Units | 304 | |
| Shading Units | 19456 | 3072 |
| TMUs | 1216 | 192 |
| ROPs | 0 | 96 |
| Tensor Cores | 1216 | |
| L1 Cache | 16 KB (per CU) | 48 KB (per SMM) |
| L2 Cache | 16 MB | 3 MB |
| L3 Cache | 256 MB | |
| Theoretical Performance | ||
| Pixel Rate | 0 MPixel/s | 106.8 GPixel/s |
| Texture Rate | 2553.6 GTexel/s | 213.5 GTexel/s |
| FP16 (half) | 81.72 TFLOPS | |
| FP32 (float) | 81.72 TFLOPS | 6.832 TFLOPS |
| FP64 (double) | 40.86 TFLOPS | 213.5 GFLOPS |
| Graphics Processor | ||
| GPU Name | Aqua Vanjaram | GM200 |
| Architecture | CDNA 3.0 | Maxwell 2.0 |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 28 nm |
| Transistors | 153 billion | 8 billion |
| Die Size | 1017 mm² | 601 mm² |
| GPU Variant | GM200-895-A1 | |
| Board Design | ||
| TDP | 1000W | 250W |
| Suggested PSU | 1400 W | 600 W |
| Outputs | No outputs | No outputs |
| Power Connectors | None | 8-pin EPS |
| Graphics Features | ||
| DirectX | N/A | 12 (12_1) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.3 |
| Shader Model | N/A | 6.7 |
| CUDA | 5.2 | |