NVIDIA RTX A4000 vs NVIDIA T1000
Processeur graphique
| Nom du GPU | GA104 | TU117 |
|---|---|---|
| Architecture | Ampere | Turing |
| Fonderie | Samsung | TSMC |
| Taille du processus | 8 nm | 12 nm |
| Transistors | 17,400 million | 4,700 million |
| Taille des matrices | 392 mm² | 200 mm² |
| GPU variant | GA104-875-A1 | — |
Carte graphique
| Date de publication | Apr 12th, 2021 | May 6th, 2021 |
|---|---|---|
| Génération | Quadro | Quadro |
| Production | Active | Active |
| Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Vitesse clock
| Base clock | 735 MHz | 1065 MHz |
|---|---|---|
| Boost clock | 1560 MHz | 1395 MHz |
| Mémoire clock | 1750 MHz 14 Gbps effective | 1250 MHz 10 Gbps effective |
Mémoire
| Taille de la mémoire | 16 GB | 4 GB |
|---|---|---|
| Type de mémoire | GDDR6 | GDDR6 |
| Bus mémoire | 256 bit | 128 bit |
| Bande passante | 448.0 GB/s | 160.0 GB/s |
Render Config
| Shading units | 6144 | 896 |
|---|---|---|
| TMUs | 192 | 56 |
| ROPs | 96 | 32 |
| Comptage SM | 48 | 14 |
| Tensor cores | 192 | — |
| RT cores | 48 | — |
| Cache L1 | 128 KB (per SM) | 64 KB (per SM) |
| Cache L2 | 4 MB | 1024 KB |
Performance théorique
| Taux de pixel | 149.8 GPixel/s | 44.64 GPixel/s |
|---|---|---|
| Taux de texture | 299.5 GTexel/s | 78.12 GTexel/s |
| FP16 (half) performance | 19.17 TFLOPS (1:1) | 5.000 TFLOPS (2:1) |
| FP32 (float) performance | 19.17 TFLOPS | 2.500 TFLOPS |
| FP64 (double) performance | 599.0 GFLOPS (1:32) | 78.12 GFLOPS (1:32) |
Board Design
| Taille Slot | Single-slot | Single-slot |
|---|---|---|
| Longueur | 241 mm 9.5 inches | — |
| Taille | 112 mm 4.4 inches | — |
| TDP | 140 W | 50 W |
| Suggestions pour le PSU | 300 W | 250 W |
| Sorties | 4x DisplayPort | 4x mini-DisplayPort |
| Connecteurs de puissance | 1x 6-pin | None |
Caractéristiques graphiques
| DirectX | 12 Ultimate (12_2) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 8.6 | 7.5 |
| Shader model | 6.6 | 6.6 |
