Product Compare
NVIDIA Tesla M40 24 GB vs Intel Arc A770
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2015 | Oct 2022 |
| Generation | Tesla Maxwell | Alchemist(Arc 7) |
| Type | Professional | Desktop |
| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 948 MHz | 2100 MHz |
| Boost Clock | 1112 MHz | 2400 MHz |
| Memory Clock | 1502 MHz | 2000 MHz |
| Memory | ||
| Memory Size | 24GB | 16GB |
| Memory Type | GDDR5 | GDDR6 |
| Memory Bus | 384bit | 256bit |
| Bandwidth | 288.4GB/s | 512.0GB/s |
| Render Config | ||
| Shading Units | 3072 | 4096 |
| TMUs | 192 | 256 |
| ROPs | 96 | 128 |
| L1 Cache | 48 KB (per SMM) | |
| L2 Cache | 3 MB | 16 MB |
| Tensor Cores | 512 | |
| RT Cores | 32 | |
| Theoretical Performance | ||
| Pixel Rate | 106.8 GPixel/s | 307.2 GPixel/s |
| Texture Rate | 213.5 GTexel/s | 614.4 GTexel/s |
| FP32 (float) | 6.832 TFLOPS | 19.66 TFLOPS |
| FP64 (double) | 213.5 GFLOPS | 2.458 TFLOPS |
| FP16 (half) | 39.32 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GM200 | DG2-512 |
| GPU Variant | GM200-895-A1 | ACM-G10 |
| Architecture | Maxwell 2.0 | Generation 12.7 |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 6 nm |
| Transistors | 8 billion | 21.7 billion |
| Die Size | 601 mm² | 406 mm² |
| Board Design | ||
| TDP | 250W | 225W |
| Suggested PSU | 600 W | 550 W |
| Outputs | No outputs | 1x HDMI 2.13x DisplayPort 2.0 |
| Power Connectors | 8-pin EPS | 1x 6-pin + 1x 8-pin |
| Graphics Features | ||
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 5.2 | |
| Shader Model | 6.7 | 6.6 |
| Benchmarks | ||
| 3DMark Time Spy | 5066 | 13560 |
| 3DMark Time Spy Extreme | 2425 | 6525 |