ATI Radeon 9000 PRO vs NVIDIA A100 PCIe
Processeur graphique
| Nom du GPU | RV250 | GA100 |
|---|---|---|
| GPU variant | RV250 9000 PRO (215R7BCGA12H) | — |
| Architecture | Rage 7 | Ampere |
| Fonderie | TSMC | TSMC |
| Taille du processus | 150 nm | 7 nm |
| Transistors | 36 million | 54,200 million |
| Taille des matrices | 97 mm² | 826 mm² |
Carte graphique
| Date de publication | Jul 18th, 2002 | Jun 22nd, 2020 |
|---|---|---|
| Génération | Radeon R200 | Tesla |
| Production | End-of-life | Active |
| Bus interface | AGP 4x | PCIe 4.0 x16 |
| Prédécesseur | Radeon R100 | — |
| Successeur | Radeon R300 | — |
Vitesse clock
| GPU clock | 275 MHz | 1410 MHz |
|---|---|---|
| Mémoire clock | 275 MHz 550 Mbps effective | 1215 MHz 2.4 Gbps effective |
| Base clock | — | 765 MHz |
| Boost clock | — | 1410 MHz |
Mémoire
| Taille de la mémoire | 128 MB | 40 GB |
|---|---|---|
| Type de mémoire | DDR | HBM2E |
| Bus mémoire | 128 bit | 5120 bit |
| Bande passante | 8.800 GB/s | 1,555 GB/s |
Render Config
| Pixel shaders | 4 | — |
|---|---|---|
| Vertex shaders | 1 | — |
| TMUs | 4 | 432 |
| ROPs | 4 | 160 |
| Shading units | — | 6912 |
| Comptage SM | — | 108 |
| Tensor cores | — | 432 |
| Cache L1 | — | 192 KB (per SM) |
| Cache L2 | — | 40 MB |
Performance théorique
| Taux de pixel | 1.100 GPixel/s | 225.6 GPixel/s |
|---|---|---|
| Vertex rate | 68.75 MVertices/s | — |
| Taux de texture | 1.100 GTexel/s | 609.1 GTexel/s |
| FP16 (half) performance | — | 77.97 TFLOPS (4:1) |
| FP32 (float) performance | — | 19.49 TFLOPS |
| FP64 (double) performance | — | 9.746 TFLOPS (1:2) |
Board Design
| Taille Slot | Single-slot | Dual-slot |
|---|---|---|
| TDP | 28 W | 250 W |
| Suggestions pour le PSU | 200 W | 600 W |
| Sorties | 1x DVI1x VGA1x S-Video | No outputs |
| Connecteurs de puissance | None | 8-pin EPS |
| Board number | 964 | P1001 SKU 200 |
| Longueur | 167 mm 6.6 inches | 267 mm 10.5 inches |
| Taille | 111 mm 4.4 inches | — |
Caractéristiques graphiques
| DirectX | 8.1 | — |
|---|---|---|
| OpenGL | 1.4 | — |
| OpenCL | — | 3.0 |
| Vulkan | — | — |
| Pixel shader | 1.4 | — |
| Vertex shader | 1.1 | — |
| CUDA | — | 8.0 |
| Shader model | — | — |
