GPU Name | GA100 | GA102 |
---|---|---|
Architektur | Ampere | Ampere |
Hersteller | TSMC | Samsung |
Prozessgröße | 7 nm | 8 nm |
Transistoren | 54,200 million | 28,300 million |
Chipgröße | 826 mm² | 628 mm² |
Veröffentlichungsdatum | May 14th, 2020 | Oct 5th, 2020 |
---|---|---|
Generation | Tesla | Quadro |
Produktion | Active | Active |
Businterface | PCIe 4.0 x16 | PCIe 4.0 x16 |
gpu.details.availability | — | Dec 15th, 2020 |
Originalpreis | — | 4,649 USD |
GPU-Taktung | 1410 MHz | — |
---|---|---|
Speicher-Taktung | 1215 MHz 2.4 Gbps effective | 2000 MHz 16 Gbps effective |
Basis-Taktfrequenz | 1095 MHz | 1410 MHz |
Boost-Takt | 1410 MHz | 1800 MHz |
Speichergröße | 40 GB | 48 GB |
---|---|---|
Speichertyp | HBM2E | GDDR6 |
Speicherbus | 5120 bit | 384 bit |
Bandbreite | 1,555 GB/s | 768.0 GB/s |
Shading-Einheiten | 6912 | 10752 |
---|---|---|
TMUs | 432 | 336 |
ROPs | 160 | 112 |
Anzahl SM | 108 | 84 |
Tensor Cores | 432 | 336 |
Cache L1 | 192 KB (per SM) | 128 KB (per SM) |
Cache L2 | 40 MB | 6 MB |
RT-Kerne | — | 84 |
Pixelrate | 225.6 GPixel/s | 201.6 GPixel/s |
---|---|---|
Texturrate | 609.1 GTexel/s | 604.8 GTexel/s |
FP16 (half) Leistung | 77.97 TFLOPS (4:1) | 38.71 TFLOPS (1:1) |
FP32 (float) Leistung | 19.49 TFLOPS | 38.71 TFLOPS |
FP64 (double) Leistung | 9.746 TFLOPS (1:2) | 1,210 GFLOPS (1:32) |
Steckplatzbreite | IGP | Dual-slot |
---|---|---|
TDP | 400 W | 300 W |
Vorgeschlagenes Netzteil | 800 W | 700 W |
Ausgabe | No outputs | 4x DisplayPort |
Stromverbindung | None | 8-pin EPS |
Länge | — | 267 mm 10.5 inches |
Breite | — | 112 mm 4.4 inches |
DirectX | — | 12 Ultimate (12_2) |
---|---|---|
OpenGL | — | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | — | 1.2 |
CUDA | 8.0 | 8.6 |
Shader-Modell | — | 6.6 |