Nom du GPU | Polaris 20 | TU104B |
---|---|---|
GPU variant | Polaris 20 XL (215-0910052) | — |
Architecture | GCN 4.0 | Turing |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 12 nm |
Transistors | 5,700 million | 13,600 million |
Taille des matrices | 232 mm² | 545 mm² |
Date de publication | Apr 11th, 2018 | — |
---|---|---|
Génération | Polaris | — |
Production | Active | — |
Bus interface | PCIe 3.0 x16 | — |
Prédécesseur | Polaris | — |
Successeur | Vega | — |
Base clock | 1168 MHz | 1035 MHz |
---|---|---|
Boost clock | 1244 MHz | 1545 MHz |
Mémoire clock | 1750 MHz 7 Gbps effective | 1750 MHz 14 Gbps effective |
Taille de la mémoire | 8 GB | 16 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR6 |
Bus mémoire | 256 bit | 256 bit |
Bande passante | 224.0 GB/s | 448.0 GB/s |
Shading units | 2048 | 3072 |
---|---|---|
TMUs | 128 | 192 |
ROPs | 32 | 64 |
Compute units | 32 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 2 MB | 4 MB |
Comptage SM | — | 48 |
Tensor cores | — | 384 |
RT cores | — | 48 |
Taux de pixel | 39.81 GPixel/s | 98.88 GPixel/s |
---|---|---|
Taux de texture | 159.2 GTexel/s | 296.6 GTexel/s |
FP16 (half) performance | 5.095 TFLOPS (1:1) | 18.98 TFLOPS (2:1) |
FP32 (float) performance | 5.095 TFLOPS | 9.492 TFLOPS |
FP64 (double) performance | 318.5 GFLOPS (1:16) | 296.6 GFLOPS (1:32) |
Taille Slot | Dual-slot | IGP |
---|---|---|
Longueur | 241 mm 9.5 inches | — |
TDP | 150 W | 110 W |
Suggestions pour le PSU | 450 W | — |
Sorties | 1x DVI1x HDMI3x DisplayPort | No outputs |
Connecteurs de puissance | 1x 6-pin | None |
Board number | D000 | — |
DirectX | 12 (12_0) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.6 |
CUDA | — | 7.5 |
Date de publication | — | Jun 8th, 2020 |
---|---|---|
Génération | — | Quadro Mobile (Tx000) |
Production | — | Active |
Bus interface | — | PCIe 3.0 x16 |