ATI Radeon HD 2400 PRO vs NVIDIA Tesla V100 DGXS 32 GB
Graphics Processor
| GPU model | RV610 | GV100 |
|---|---|---|
| GPU variant | RV610 LE (215LKCAKA14FG) | — |
| Architecture | TeraScale | Volta |
| Foundry | TSMC | TSMC |
| Manufacturing process | 65 nm | 12 nm |
| Number of transistors | 180 million | 21,100 million |
| Die size | 85 mm² | 815 mm² |
Graphics Card
| Release date | Jun 28th, 2007 | Mar 27th, 2018 |
|---|---|---|
| Generation | Radeon R600 | Tesla |
| Production | End-of-life | End-of-life |
| Interface | PCIe 1.0 x16 | PCIe 3.0 x16 |
| Reviews | 32 in our database | — |
| Predecessor | Radeon R500 PCIe | — |
| Successor | Radeon R700 | — |
Clocks
| GPU clock | 525 MHz | — |
|---|---|---|
| Memory clock | 400 MHz 800 Mbps effective | 876 MHz 1752 Mbps effective |
| Base clock | — | 1297 MHz |
| Boost clock | — | 1530 MHz |
Memory Configuration
| Memory size | 256 MB | 32 GB |
|---|---|---|
| Memory type | DDR2 | HBM2 |
| Memory bus width | 64 bit | 4096 bit |
| Bandwidth | 6.400 GB/s | 897.0 GB/s |
Render Configuration
| Shading units | 40 | 5120 |
|---|---|---|
| TMUs | 4 | 320 |
| ROPs | 4 | 128 |
| Compute units | 2 | — |
| Cache L2 | 32 KB | 6 MB |
| SM count | — | 80 |
| Tensor cores | — | 640 |
| Cache L1 | — | 128 KB (per SM) |
Performance
| Pixel rate | 2.100 GPixel/s | 195.8 GPixel/s |
|---|---|---|
| Texture rate | 2.100 GTexel/s | 489.6 GTexel/s |
| FP32 (float) performance | 42.00 GFLOPS | 15.67 TFLOPS |
| FP16 (half) performance | — | 31.33 TFLOPS (2:1) |
| FP64 (double) performance | — | 7.834 TFLOPS (1:2) |
Dimensions & Outputs
| Slot width | Single-slot | Dual-slot |
|---|---|---|
| TDP | 20 W | 250 W |
| Suggested PSU | 200 W | 600 W |
| Outputs | 1x DVI1x VGA1x S-Video | No outputs |
| Power connectors | None | None |
| Board number | B169 | — |
API Support & Features
| DirectX | 10.0 (10_0) | 12 (12_1) |
|---|---|---|
| OpenGL | 3.3 | 4.6 |
| OpenCL | — | 3.0 |
| Vulkan | — | 1.2 |
| Shader model | 4.0 | 6.6 |
| CUDA | — | 7.0 |
