ATI Radeon 9600 PRO vs NVIDIA Tesla V100 SXM2 16 GB
Graphics Processor
| GPU model | RV350 | GV100 |
|---|---|---|
| GPU variant | RV350 PRO (215R8JAGA12F) | — |
| Architecture | Rage 8 | Volta |
| Foundry | TSMC | TSMC |
| Manufacturing process | 130 nm | 12 nm |
| Number of transistors | 60 million | 21,100 million |
| Die size | 76 mm² | 815 mm² |
Graphics Card
| Release date | Oct 1st, 2003 | Nov 26th, 2019 |
|---|---|---|
| Generation | Radeon R300 | Tesla |
| Production | End-of-life | End-of-life |
| Interface | AGP 8x | PCIe 3.0 x16 |
| Reviews | 14 in our database | — |
| Predecessor | Radeon R200 | — |
| Successor | Radeon R400 AGP | — |
Clocks
| GPU clock | 400 MHz | — |
|---|---|---|
| Memory clock | 300 MHz 600 Mbps effective | 1106 MHz 2.2 Gbps effective |
| Base clock | — | 1245 MHz |
| Boost clock | — | 1597 MHz |
Memory Configuration
| Memory size | 128 MB | 16 GB |
|---|---|---|
| Memory type | DDR | HBM2 |
| Memory bus width | 128 bit | 4096 bit |
| Bandwidth | 9.600 GB/s | 1,133 GB/s |
Render Configuration
| Pixel shaders | 4 | — |
|---|---|---|
| Vertex shaders | 2 | — |
| TMUs | 4 | 320 |
| ROPs | 4 | 128 |
| Shading units | — | 5120 |
| SM count | — | 80 |
| Tensor cores | — | 640 |
| Cache L1 | — | 128 KB (per SM) |
| Cache L2 | — | 6 MB |
Performance
| Pixel rate | 1.600 GPixel/s | 204.4 GPixel/s |
|---|---|---|
| Vertex rate | 200.0 MVertices/s | — |
| Texture rate | 1.600 GTexel/s | 511.0 GTexel/s |
| FP16 (half) performance | — | 32.71 TFLOPS (2:1) |
| FP32 (float) performance | — | 16.35 TFLOPS |
| FP64 (double) performance | — | 8.177 TFLOPS (1:2) |
Dimensions & Outputs
| Slot width | Single-slot | Dual-slot |
|---|---|---|
| TDP | 18 W | 250 W |
| Suggested PSU | 200 W | 600 W |
| Outputs | 1x DVI1x VGA1x S-Video | No outputs |
| Power connectors | None | None |
| Board number | 852 | PG500 |
API Support & Features
| DirectX | 9.0 (9_0) | 12 (12_1) |
|---|---|---|
| OpenGL | 2.0 | 4.6 |
| OpenCL | — | 3.0 |
| Vulkan | — | 1.2 |
| Pixel shader | 2.0 | — |
| Vertex shader | 2.0 | — |
| CUDA | — | 7.0 |
| Shader model | — | 6.6 |
