NVIDIA A100 SXM4 80 GB vs NVIDIA Tesla V100 SXM3 32 GB
Graphics Processor
| GPU model | GA100 | GV100 |
|---|---|---|
| Architecture | Ampere | Volta |
| Foundry | TSMC | TSMC |
| Manufacturing process | 7 nm | 12 nm |
| Number of transistors | 54,200 million | 21,100 million |
| Die size | 826 mm² | 815 mm² |
Graphics Card
| Release date | Nov 16th, 2020 | Mar 27th, 2018 |
|---|---|---|
| Generation | Tesla | Tesla |
| Production | Active | End-of-life |
| Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Clocks
| Base clock | 1275 MHz | 1290 MHz |
|---|---|---|
| Boost clock | 1410 MHz | 1530 MHz |
| Memory clock | 1593 MHz 3.2 Gbps effective | 876 MHz 1752 Mbps effective |
Memory Configuration
| Memory size | 80 GB | 32 GB |
|---|---|---|
| Memory type | HBM2e | HBM2 |
| Memory bus width | 5120 bit | 4096 bit |
| Bandwidth | 2,039 GB/s | 897.0 GB/s |
Render Configuration
| Shading units | 6912 | 5120 |
|---|---|---|
| TMUs | 432 | 320 |
| ROPs | 160 | 128 |
| SM count | 108 | 80 |
| Tensor cores | 432 | 640 |
| Cache L1 | 192 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 40 MB | 6 MB |
Performance
| Pixel rate | 225.6 GPixel/s | 195.8 GPixel/s |
|---|---|---|
| Texture rate | 609.1 GTexel/s | 489.6 GTexel/s |
| FP16 (half) performance | 77.97 TFLOPS (4:1) | 31.33 TFLOPS (2:1) |
| FP32 (float) performance | 19.49 TFLOPS | 15.67 TFLOPS |
| FP64 (double) performance | 9.746 TFLOPS (1:2) | 7.834 TFLOPS (1:2) |
Dimensions & Outputs
| Slot width | IGP | Dual-slot |
|---|---|---|
| TDP | 400 W | 250 W |
| Suggested PSU | 800 W | 600 W |
| Outputs | No outputs | No outputs |
| Power connectors | None | None |
API Support & Features
| DirectX | — | 12 (12_1) |
|---|---|---|
| OpenGL | — | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | — | 1.2 |
| CUDA | 8.0 | 7.0 |
| Shader model | — | 6.6 |
